the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
| 10 Jan 2023
How the recursive feature elimination affects the SVM and RF for wildfire modeling? A mountainous case study area
Abstract. This study aims to identify key fire factors via recursive feature elimination (RFE) to generate a forest fire susceptibility map (FSM) using support vector machine (SVM), and random forest (RF) models. The fire zones were derived from MODIS satellite imagery from 2012 to 2017. Further validation of these data has been provided by field surveys and reviews of land records in rangelands and forests; a total of 352 fire points were determined in this study. Seventeen factors involving topography, geomorphology, meteorology, hydrology, and anthropology were identified as being effective primary factors in triggering and spreading fires in the selected mountainous case study area. As a first step, the RFE models of the RF, Extra trees, Gradient boosting, and AdaBoost was used to identify important fire factors among all selected primary factors. The SVM and RF models were applied once on all factors and the second on those derived from RFE models as the key factors in FSM. Training and testing data were divided tenfold, and the model's performance was evaluated using cross-validation (CV). Different metrics were used to measure accuracy, including recall, precision, F1, accuracy, the area under the curve (AUC), Matthews correlation coefficient (MCC), and Kappa. The accuracy assessment process shows that the FSM results are further improved by leveraging RFE models to distinguish the key factors and not include unnecessary factors. The greatest improvement is for SVM, with more than 10.97 % and 8.61 % in the accuracy and AUC metrics, respectively.
This preprint has been withdrawn.
-
Withdrawal notice
This preprint has been withdrawn.
-
Preprint
(1504 KB)
Interactive discussion
Status: closed
-
CC1: 'Comment on egusphere-2022-1294', Carolina Ojeda, 13 Jan 2023
General comments: This article presented a study case in Iran in which a GIS-type forest fire hazard model is tested. Its novelty relies on the improvement of Fire Susceptibility Maps (FSM) results, which could help GIS experts to improve future analyses for similar topographical conditions.
Specific comments:
1. The subtitle is a bit crowded: "A mountainous case study area". My suggestion here is "A study case in Iran".
2. In the abstract line 15 and section 3.2 the concept "anthropology/anthropological" should be replaced by "human actions/factors" or "anthropic actions/factors" because anthropology is a discipline.
3. In the introduction lines 40-43 are redundant with the next paragraph ("in recent years"). Also, its main idea could be developed more by the authors, because forest fires have been modeling the landscapes, lives, and infrastructures since humans inhabited the planet, therefore, it is not an issue of "recent years".
4. In the introduction lines 45-46 are contradicting. If "natural processes have historically caused fires in forests" how could humans accelerate it? Also, what is a "firing process" that was accelerated?
5. In the study area lines 114-121 it could be explained more why "this province is known to be one of the most wildfire-prone regions in northern Iran" besides the reference to Adab et al. (2015). Also, the article could be benefited from a more detailed visual description of the topography (e.g. a topographic profile), which is a special feature remarked in the title "A mountainous case study area".
6. In the discussion section, the authors deliver more accurate information about the selected methods which improved the overall quality of the article and its scientific robustness. However, I missed a comparison with other studies doing the same methodologies in other mountain regions from Iran or other parts of the world with similar topography. Maybe the references named in lines 390-395 could be useful for that purpose if they are presented in a comparative table.
Technical corrections: Please be aware of the capital letter in the acronyms along the abstract (e.g., forest fire susceptibility map (FSM)). Also, the legend of figure 1 has a typo (boundaries).
Citation: https://doi.org/10.5194/egusphere-2022-1294-CC1 -
AC1: 'Reply on CC1', Parham Pahlavani, 30 Mar 2023
Dear Reviewer,
We very much appreciate your positive statements regarding our manuscript. You indeed kindly spent significant time on this manuscript and we are grateful for the detailed suggestions. You brought up interesting aspects and we believe that these suggestions and our respective reactions to them will improve the quality of the paper. We did our best to improve the scientific quality of the manuscript significantly. Based on your constructive comments on the initial version and our comprehensive revisions, we are confident that you will find this version now worthwhile to get published. All the revisions are specified with the Blue color in the text.
1) The subtitle is a bit crowded: "A mountainous case study area".To comply with the reviewer’s comment, we changed the subtitle to " A study case in Iran".
2) In the abstract line 15 and section 3.2 the concept "anthropology/anthropological" should be replaced by "human actions/factors" or "anthropic actions/factors" because anthropology is a discipline.This comment was taken into consideration. In this regard, anthropology factors have been changed to human factors.
3) In the introduction lines 40-43 are redundant with the next paragraph ("in recent years"). Also, its main idea could be developed more by the authors, because forest fires have been modeling the landscapes, lives, and infrastructures since humans inhabited the planet, therefore, it is not an issue of "recent years".
To comply with the reviewer’s comment, the paragraph was corrected and its "recent years" was deleted in the revised version of the manuscript.
4) In the introduction lines 45-46 are contradicting. If "natural processes have historically caused fires in forests" how could humans accelerate it? Also, what is a "firing process" that was accelerated?To comply with the reviewer’s comment, the sentence was rewritten as follows:
“Fires in forests have accelerated directly due to the increased human-environmental interactions by igniting and suppressing fires, and indirectly by changing the vegetation structure and composition, as well as destroying the landscapes (Rogers et al., 2020).”
5) In the study area lines 114-121 it could be explained more why "this province is known to be one of the most wildfire-prone regions in northern Iran" besides the reference to Adab et al. (2015). Also, the article could be benefited from a more detailed visual description of the topography (e.g. a topographic profile), which is a special feature remarked in the title "A mountainous case study area".To point out the prevalence of fire in this area, the following sentence was added: “This study experienced several harsh wildfires, which have impacted more than twenty settlements and villages (Gholamnia et al., 2020).”
6) In the discussion section, the authors deliver more accurate information about the selected methods which improved the overall quality of the article and its scientific robustness. However, I missed a comparison with other studies doing the same methodologies in other mountain regions from Iran or other parts of the world with similar topography. Maybe the references named in lines 390-395 could be useful for that purpose if they are presented in a comparative table.If we pay attention to the discussion, we will find that it is explained in the full discussion section that several researchers have investigated factors, but the factor of distance to power lines is also known as an effective factor in this research. Also, the research conducted by Ghorbanzadeh in this study area has been mentioned and compared with the results of the research.
Finally, we appreciate your support and your constructive suggestions. We strongly believe that we have addressed the issues concerning the logical flow of the manuscript and have improved the scientific aspect significantly. We hope that you will find this revised version worthwhile to be published.
Thank you very much again.
The authors
Citation: https://doi.org/10.5194/egusphere-2022-1294-AC1 -
CC2: 'Reply on CC1', Parham Pahlavani, 30 Mar 2023
Dear Reviewer,
We very much appreciate your positive statements regarding our manuscript. You indeed kindly spent significant time on this manuscript and we are grateful for the detailed suggestions. You brought up interesting aspects and we believe that these suggestions and our respective reactions to them will improve the quality of the paper. We did our best to improve the scientific quality of the manuscript significantly. Based on your constructive comments on the initial version and our comprehensive revisions, we are confident that you will find this version now worthwhile to get published. All the revisions are specified with the Blue color in the text.
1) The subtitle is a bit crowded: "A mountainous case study area".To comply with the reviewer’s comment, we changed the subtitle to " A study case in Iran".
2) In the abstract line 15 and section 3.2 the concept "anthropology/anthropological" should be replaced by "human actions/factors" or "anthropic actions/factors" because anthropology is a discipline.This comment was taken into consideration. In this regard, anthropology factors have been changed to human factors.
3) In the introduction lines 40-43 are redundant with the next paragraph ("in recent years"). Also, its main idea could be developed more by the authors, because forest fires have been modeling the landscapes, lives, and infrastructures since humans inhabited the planet, therefore, it is not an issue of "recent years".
To comply with the reviewer’s comment, the paragraph was corrected and its "recent years" was deleted in the revised version of the manuscript.
4) In the introduction lines 45-46 are contradicting. If "natural processes have historically caused fires in forests" how could humans accelerate it? Also, what is a "firing process" that was accelerated?To comply with the reviewer’s comment, the sentence was rewritten as follows:
“Fires in forests have accelerated directly due to the increased human-environmental interactions by igniting and suppressing fires, and indirectly by changing the vegetation structure and composition, as well as destroying the landscapes (Rogers et al., 2020).”
5) In the study area lines 114-121 it could be explained more why "this province is known to be one of the most wildfire-prone regions in northern Iran" besides the reference to Adab et al. (2015). Also, the article could be benefited from a more detailed visual description of the topography (e.g. a topographic profile), which is a special feature remarked in the title "A mountainous case study area".To point out the prevalence of fire in this area, the following sentence was added: “This study experienced several harsh wildfires, which have impacted more than twenty settlements and villages (Gholamnia et al., 2020).”
6) In the discussion section, the authors deliver more accurate information about the selected methods which improved the overall quality of the article and its scientific robustness. However, I missed a comparison with other studies doing the same methodologies in other mountain regions from Iran or other parts of the world with similar topography. Maybe the references named in lines 390-395 could be useful for that purpose if they are presented in a comparative table.If we pay attention to the discussion, we will find that it is explained in the full discussion section that several researchers have investigated factors, but the factor of distance to power lines is also known as an effective factor in this research. Also, the research conducted by Ghorbanzadeh in this study area has been mentioned and compared with the results of the research.
Finally, we appreciate your support and your constructive suggestions. We strongly believe that we have addressed the issues concerning the logical flow of the manuscript and have improved the scientific aspect significantly. We hope that you will find this revised version worthwhile to be published.
Thank you very much again.
The authors
Citation: https://doi.org/10.5194/egusphere-2022-1294-CC2 -
CC6: 'Reply on CC2', Parham Pahlavani, 30 Mar 2023
The comment was uploaded in the form of a supplement: https://egusphere.copernicus.org/preprints/2023/egusphere-2022-1294/egusphere-2022-1294-CC6-supplement.pdf
-
CC6: 'Reply on CC2', Parham Pahlavani, 30 Mar 2023
-
AC1: 'Reply on CC1', Parham Pahlavani, 30 Mar 2023
-
RC1: 'Comment on egusphere-2022-1294', Anonymous Referee #1, 14 Mar 2023
General overview of paper – there is some good work in here, but it reads too much like an thesis rather than a paper, thus inhibiting the communication. For instance – a lot of section 4 could/should be in the introduction, while the current introduction is verbose and not concise enough.
Additioanlly, in fire science slope, for instance, has been identified an important factor in wildfire modelling – however, your study area does not give details of slope or any of the 17 factors you’ve said are important. My inference therefore from your study and figure 7 is that the area is a) not overly sloped – which would be surprising for a mountainous region - or b) the fire areas and non-fire areas are equally sloped.
This then comes to the crux of the paper and its title – you are not modelling wildfire, you are modelling relative wildfire susceptibility in a certain area.
Lines 30-32 – provide reference to support claim.
Lines 33-34 – provide reference or specify that in this paper this is what you are calling a forest fire.
Line 35 – highly combustible trees compared to what?
Paragraph from line 33-42 – tell me why you are telling me this – why is this important.
Paragraph 43-53 – end sentences about life safety is new to para and out of generalised context of fires in Iran – this needs to be changed into two paras, with the latter being about human susceptibility.
Paragraph 54-64 – none of this is wrong, but it is not noteworthy – this is in my view – common knowledge.
Paragraph 64 – 79 – lots of repetition at the start, lots of “authors X did Y” and not enough depth to the review – a generic comment at the end about what is lacking without showing the reader that this is true.
Paragraph 80-104 – too long- consider splitting. As before lots of X did Y, not enough “however,…” there is some, but more needed.
Para 105 – 112 – need to explain why RFE is better than the other methods. Why have you chose this method. You then bring in terms such as adaboost, gradient boosting, random forests, and extra trees without any prior referencing in the text.
Resolution of Figure 1 could be improved. Please show an image from the timeframe being explored e.g., an image of the forest between 2012-2017
Can you explain the difference between a fire point and the polygons that you are using, and how they are used/interact with one another. Were there more than 352 fire points found and only 352 used or are you using all of the points that were found – I am confused as to why you have two different metrics to measure where a fire has been. How big is your fire point – what is the spatial resolution of your point?
How do you know the 17 factors are important – are there important factors that are not included? How has this list been determined or is it from other sources, in which case please reference these.
RFE – 4.1
Who is doing all this selecting/removing of features? Are these features independent of one another, or are they interdependent
Line 180 – cross-validation against what?
Again this comes back to the question about the factors/features of importance – knowing whether they are complete, and whether they are transferable between different geographical locations. This is not clear in the paper.
Line 194 & 207 – majority of votes – who’s voting?
195-201 – I do not see the importance of this part
205 What is a bootstrap sample – reference?
Please make the y axis in figures 3,4,5 and 6 the same so that the variability in each of the modelling approaches is abundantly clear. Do they need to be separate figures, it could be done on a single plot. What is the shading showing on these figures and why is this not discussed?
How are the models scored? What is the range of possible scores? is 0.87 considered acceptable?
Can the factors in table 2 and figure 7 please be in the same order
These are showing the same data – do these need to be duplicated?
Slope is an important factor in wildfire modelling – however, your study area does not give details of slope or any of the 17 factors you’ve said are important. My inference therefore from your study and figre 7 is that the area is not overly sloped – which would be surprising for a mountainous region - or the fire areas and non-fire areas are equally sloped.
This then comes to the crux of the paper and its title – you are not modelling wildfire, you are modelling relative wildfire susceptibility in a certain area.
Section 5.3 explains a statistical analysis of the different methods – it would be good to show what you mean by true and false positives. Tables 3-5 AUC are not described in the equations and not explained what it is – 6 equations 7 columns in the tables. There is no discussion over the merits of each method – so it just feels like noise.
The fire susceptibility maps – do these not just show that where there have been previous fires – these areas are susceptible to fires? There is no discussion of these images in any detail.
The discussion feels like an executive summary of the paper and the conclusions are lacking in conclusion.
Citation: https://doi.org/10.5194/egusphere-2022-1294-RC1 -
AC2: 'Reply on RC1', Parham Pahlavani, 30 Mar 2023
Dear Reviewer,
We very much appreciate your positive statements regarding our manuscript. You indeed kindly spent significant time on this manuscript and we are grateful for the detailed suggestions. You brought up interesting aspects and we believe that these suggestions and our respective reactions to them will improve the quality of the paper. We did our best to improve the scientific quality of the manuscript significantly. Based on your constructive comments on the initial version and our comprehensive revisions, we are confident that you will find this version now worthwhile to get published. All the revisions are specified with the Blue color in the text.
1) A general overview of the paper – there is some good work in here, but it reads too much like a thesis rather than a paper, thus inhibiting communication. For instance – a lot of section 4 could/should be in the introduction, while the current introduction is verbose and not concise enough.According to other comments, modifications have been made in the introduction, which also covers this comment.
2) Additionally, in fire science slope, for instance, has been identified as an important factor in wildfire modeling – however, your study area does not give details of slope or any of the 17 factors you’ve said are important. My inference therefore from your study and figure 7 is that the area is a) not overly sloped – which would be surprising for a mountainous region - or b) the fire areas and non-fire areas are equally slopedWe added this paragraph: "In fire science, the slope factor has been identified as an important factor in fire modeling, but in the case of our study, there are many non-fire points in steep areas, so the models do not recognize this factor as an important factor in the fire forest. However, the direction of slope and height have been identified as important factors."
3) This then comes to the crux of the paper and its title – you are not modeling wildfire, you are modeling relative wildfire susceptibility in a certain area.The title of the article was changed to " How the recursive feature elimination affects the SVM and RF for relative wildfire susceptibility in a certain area? A study case in Iran ".
4) Lines 30-32 – provide reference to support the claim.
Add reference.
5) Lines 33-34 – provide a reference or specify that in this paper this is what you are calling a forest fire.Add reference.
6) Line 35 – highly combustible trees compared to what?Change to sentence to " Fires in forests lead to a lot of environmental destruction due to the presence of combustible vegetation "
7) Paragraph from lines 33-42 – tell me why you are telling me this – why is this important.
We added this sentence " The main goal of modeling forest fires is to reduce the negative effects of fires on humans and the environment as much as possible (Hosseini and Lim, 2022). Also, by determining the areas with the possibility of fire, it leads to better management of natural hazards (Tehrany et al., 2021)."
8) Paragraph 43-53 – end sentences about life safety is new to para and out of the generalized context of fires in Iran – this needs to be changed into two paras, with the latter being about human susceptibility.
Paragraphs 43 to 53 were changed into two paragraphs.
9) Paragraphs 54-64 – none of this is wrong, but it is not noteworthy – this is in my view – common knowledge.
The desired paragraphs were deleted.
10) Paragraphs 64 – 79 – lots of repetition at the start, lots of “authors X did Y” and not enough depth to the review – a generic comment at the end about what is lacking without showing the reader that this is true.
We added these sentences "in their study, the random forests (RFs) model was utilized to link historical fire events to a set of wildfire causative factors to measure the importance of each factor on fire ignition. then employed support vector machines (SVMs), to produce an accurate estimate of wildfire probability across the study area"
We added this sentence " this study utilizes Genetic Algorithms (GA) to obtain the optimal combination of forest fire-related variables and apply data mining methods for constructing a forest fire susceptibility map"
11) Paragraphs 80-104 – too long- consider splitting. As before lots of X did Y, not enough “however,…” there is some, but more needed.
Paragraphs 80-104 were divided into several paragraphs.
12) Para 105 – 112 – need to explain why RFE is better than the other methods. Why have you chosen this method? You then bring in terms such as adaboost, gradient boosting, random forests, and extra trees without any prior referencing in the text.
We added this paragraph " As a greedy way of finding a nested subset of features, RFE was argued to be much more robust to data overfitting than wrapper methods (Zeng et al., 2009). RFE tends to remove redundant and weak features and retains independent features. RFE seeks to improve generalization performance by removing the least important features whose deletion will have the least effect, on training errors (Escanilla et al., 2018)".
We added this paragraph ". Feature selection is accomplished by recursive feature elimination (RFE), As a result of its simplicity and effectiveness, RFE is a popular feature selection algorithm because it can identify the feature in a training dataset that is most relevant to the prediction of the variable."
13) Resolution of Figure 1 could be improved. Please show an image from the timeframe being explored e.g., an image of the forest between 2012-2017.
Image No. 1 was changed and considering that the fire points are related to the reported fire polygons and each reported fire polygon has a date since the fire occurred, a date label was added on the map for the fire points.
14) Can you explain the difference between a fire point and the polygons that you are using, and how they are used/interact with one another? Were there more than 352 fire points found and only 352 used or are you using all of the points that were found – I am confused as to why you have two different metrics to measure where a fire has been. How big is your fire point – what is the spatial resolution of your point?
We added this paragraph: "the fire polygons provided to us by the state wildlife organization of Amol County (SWOAC), were matched and validated with the MODIS fire data, and 352 fire points were found. Although there could be more than 352 fire points, it is not certain about them, but at these 352 fire points, fires have occurred with absolute certainty"
15) How do you know the 17 factors are important – are there important factors that are not included? How has this list been determined or is it from other sources, in which case please reference these.
We added this paragraph: "These factors have been extracted based on the studies that happened in the previous research, especially the studies that happened in this area. By reviewing articles (Ghorbanzadeh et al., 2019; Gigović et al., 2019; Zhang et al., 2019; Eskandari et al., 2021; Gholamnia et al., 2020; Jaafari and Pourghasemi, 2019), these 17 available factors were extracted."
16) Who is doing all this selecting/removing of features? Are these features independent of one another, or are they interdependent
As explained in the article, in this method, by building a model on the entire set of problem variables, it calculates their importance for each variable. In the next step, the least important variable is removed, the model is rebuilt on the other remaining variables, and the importance of each variable is recalculated.
17) Again, this comes back to the question about the factors/features of importance – knowing whether they are complete and whether they are transferable between different geographical locations. This is not clear in the paper.
In conclusion, we added this sentence " It is possible that the factors that are known as important factors in this study case, in another geographical environment, other factors are identified as important factors by this method, on the other hand, these factors that are known in this study case The factors that have been used were the ones that could be accessed, so it can be argued that there are other factors as well, but because they are not accessible, they have not been investigated."
18) Line 194 & 207 – the majority of votes – who’s voting?
where the predictions of individual trees are treated as votes and the prediction of the random forest is determined by the majority of votes.
19) 195-201 – I do not see the importance of this part
Due to the fact that the RFE method is described in these sentences, their presence is mandatory.
20) 205 What is a bootstrap sample – reference?
We added this sentence "The bootstrap sampling method is a resampling method that uses random sampling and bootstrap sample is a smaller sample that is “bootstrapped” from a larger sample (Efron and Tibshirani, 1993)".
21) Please make the y-axis in figures 3,4,5 and 6 the same so that the variability in each of the modeling approaches is abundantly clear. Do they need to be separate figures, it could be done on a single plot. What is the shading showing on these figures and why is this not discussed?
All four graphs are displayed in the same figure to enable comparison.
22) How are the models scored? What is the range of possible scores? is 0.87 considered acceptable?
The score obtained by the model here is the auc criterion. The auc range is between 0 and 1. The AUC values are interpreted as reflecting the following model accuracies: 0.6–0.7 poor, 0.6–0.7 medium, 0.7–0.8 good, 0.8–0.9 very good, and 0.9–1 excellent (Pourghasemi et al., 2017). According to Hong's article (Hong et al., 2018), which considered the value of 0.7 for the AUC criterion as a good performance of the model, also in the article of Jafari and Pourghasemi (Pourghasemi et al., 2020), the AUC criterion equal to 0.8 is considered a very good performance for the model.
23) Can the factors in table 2 and figure 7 please be in the same order
Figure 7, its order was arranged according to table 2.
24) These are showing the same data – do these need to be duplicated?
Due to the large number of features in Table 2, for easy identification of the votes obtained for each feature, Figure 7 is displayed as a graph of the votes obtained.
25) Section 5.3 explains a statistical analysis of the different methods – it would be good to show what you mean by true and false positives. Tables 3-5 AUC is not described in the equations and not explained what it is – 6 equations 7 columns in the tables. There is no discussion over the merits of each method – so it just feels like noise.
Formula AUC was added along with formulas Specificity and Sensitivity.
We added this paragraph: " The AUC criterion, which is one of the most important evaluation criteria for models, indicates that the proportion of fire and non-fire points which are correctly classified. The Recall measure shows how many positive examples in the sample are predicted correctly. The fraction of relevant instances in the retrieved instances. The sensitivity criterion also indicates the percentage of fire points that are correctly classified. On the other hand, the specificity criterion indicates the percentage of non-fire points that are correctly classified."
26) The fire susceptibility maps – do these not just show that where there have been previous fires – these areas are susceptible to fires? There is no discussion of these images in any detail.
In section 5.5 we added this paragraph: " A forest fire susceptibility map depicts areas likely to have forest fire in the future by correlating some of the principal factors that contribute to forest fire with the past distribution. The forest fire susceptibility maps represent a measure of the probability of the occurrence of wildfires for a region based on considered conditioning factors. The natural breaks classification method (available in Arc map 10.8) was used to classify the resulting spatial prediction of wildfire susceptibility maps. This classification method is the most common method for categorizing prediction maps for interpreting values close to each class boundary (e.g., values between “High” and “Very high” susceptibility predictions). The model generates a number between 0 and 1 for each pixel according to its feature vector. Using a reclassification tool in the Spatial Analyst Tools ArcGIS 10.8 software, each final map cell is classified into five classes (very low, low, moderate, high, and very high) representing the forest fire hazard index, with the natural breaks method, all outcomes are divided into five classes."
27) The discussion feels like an executive summary of the paper and the conclusions are lacking in conclusion.
According to other comments, modifications have been made in the discussion and conclusions, which also cover this comment.
These two paragraphs were added in the discussion:
" Pourghasemi et al. (Pourghasemi et al., 2020) have identified the factors of distance from rivers and residential areas, TWI, rainfall, aspect, and temperature as important factors in the Boruta algorithm and these factors have also been identified as important factors in our method. But the factors of use and slope, which are not known as important factors in the scope of our study, are known as influential factors in the scope of their study, and this indicates that in order to make a correct comparison between the methods of feature selection and To determine their performance, they should be tested in different geographical environments."
" In fire science, the slope factor has been identified as an important factor in fire modeling (Hong et al., 2018; Pourghasemi et al., 2020) , But there are also articles that do not consider the slope factor due to the geography of the region (Satir et al., 2016; Kim et al., 2019; Cao et al., 2017). About our study area, there are many non-fire points in steep areas, so the models do not recognize this factor as an important factor in the fire forest . However, the direction of slope and height have been identified as important factors. In the table below, the distribution of fire and non-fire points in the study area can be seen according to the slope classification. As can be inferred from the table, the distribution of fire and non-fire points in steep areas are similar, so the factor could not be recognized as an important fire factor in this study area."
The Table 8 was added.
And this paragraph was added in the conclusion:
"It is possible that the factors that are known as important factors in this study case, in another geographical environment, other factors are identified as important factors by this method, on the other hand, these factors that are known in this study case The factors that have been used were the ones that could be accessed, so it can be argued that there are other factors as well, but because they are not accessible, they have not been investigated"
Finally, we appreciate your support and your constructive suggestions. We strongly believe that we have addressed the issues concerning the logical flow of the manuscript and have improved the scientific aspect significantly. We hope that you will find this revised version worthwhile to be published.
Thank you very much again.
The authors
Citation: https://doi.org/10.5194/egusphere-2022-1294-AC2 -
CC3: 'Reply on RC1', Parham Pahlavani, 30 Mar 2023
Dear Reviewer,
We very much appreciate your positive statements regarding our manuscript. You indeed kindly spent significant time on this manuscript and we are grateful for the detailed suggestions. You brought up interesting aspects and we believe that these suggestions and our respective reactions to them will improve the quality of the paper. We did our best to improve the scientific quality of the manuscript significantly. Based on your constructive comments on the initial version and our comprehensive revisions, we are confident that you will find this version now worthwhile to get published. All the revisions are specified with the Blue color in the text.
1) A general overview of the paper – there is some good work in here, but it reads too much like a thesis rather than a paper, thus inhibiting communication. For instance – a lot of section 4 could/should be in the introduction, while the current introduction is verbose and not concise enough.According to other comments, modifications have been made in the introduction, which also covers this comment.
2) Additionally, in fire science slope, for instance, has been identified as an important factor in wildfire modeling – however, your study area does not give details of slope or any of the 17 factors you’ve said are important. My inference therefore from your study and figure 7 is that the area is a) not overly sloped – which would be surprising for a mountainous region - or b) the fire areas and non-fire areas are equally slopedWe added this paragraph: "In fire science, the slope factor has been identified as an important factor in fire modeling, but in the case of our study, there are many non-fire points in steep areas, so the models do not recognize this factor as an important factor in the fire forest. However, the direction of slope and height have been identified as important factors."
3) This then comes to the crux of the paper and its title – you are not modeling wildfire, you are modeling relative wildfire susceptibility in a certain area.The title of the article was changed to " How the recursive feature elimination affects the SVM and RF for relative wildfire susceptibility in a certain area? A study case in Iran ".
4) Lines 30-32 – provide reference to support the claim.
Add reference.
5) Lines 33-34 – provide a reference or specify that in this paper this is what you are calling a forest fire.Add reference.
6) Line 35 – highly combustible trees compared to what?Change to sentence to " Fires in forests lead to a lot of environmental destruction due to the presence of combustible vegetation "
7) Paragraph from lines 33-42 – tell me why you are telling me this – why is this important.
We added this sentence " The main goal of modeling forest fires is to reduce the negative effects of fires on humans and the environment as much as possible (Hosseini and Lim, 2022). Also, by determining the areas with the possibility of fire, it leads to better management of natural hazards (Tehrany et al., 2021)."
8) Paragraph 43-53 – end sentences about life safety is new to para and out of the generalized context of fires in Iran – this needs to be changed into two paras, with the latter being about human susceptibility.
Paragraphs 43 to 53 were changed into two paragraphs.
9) Paragraphs 54-64 – none of this is wrong, but it is not noteworthy – this is in my view – common knowledge.
The desired paragraphs were deleted.
10) Paragraphs 64 – 79 – lots of repetition at the start, lots of “authors X did Y” and not enough depth to the review – a generic comment at the end about what is lacking without showing the reader that this is true.
We added these sentences "in their study, the random forests (RFs) model was utilized to link historical fire events to a set of wildfire causative factors to measure the importance of each factor on fire ignition. then employed support vector machines (SVMs), to produce an accurate estimate of wildfire probability across the study area"
We added this sentence " this study utilizes Genetic Algorithms (GA) to obtain the optimal combination of forest fire-related variables and apply data mining methods for constructing a forest fire susceptibility map"
11) Paragraphs 80-104 – too long- consider splitting. As before lots of X did Y, not enough “however,…” there is some, but more needed.
Paragraphs 80-104 were divided into several paragraphs.
12) Para 105 – 112 – need to explain why RFE is better than the other methods. Why have you chosen this method? You then bring in terms such as adaboost, gradient boosting, random forests, and extra trees without any prior referencing in the text.
We added this paragraph " As a greedy way of finding nested subset of features, RFE was argued to be much more robust to data overfitting than wrapper methods (Zeng et al., 2009). RFE tends to remove redundant and weak features and retains independent features. RFE seeks to improve generalization performance by removing the least important features whose deletion will have the least effect, on training errors (Escanilla et al., 2018)".
We added this paragraph ". Feature selection is accomplished by recursive feature elimination (RFE), As a result of its simplicity and effectiveness, RFE is a popular feature selection algorithm because it can identify the feature in a training dataset that is most relevant to the prediction of the variable."
13) Resolution of Figure 1 could be improved. Please show an image from the timeframe being explored e.g., an image of the forest between 2012-2017.
Image No. 1 was changed and considering that the fire points are related to the reported fire polygons and each reported fire polygon has a date since the fire occurred, a date label was added on the map for the fire points.
14) Can you explain the difference between a fire point and the polygons that you are using, and how they are used/interact with one another? Were there more than 352 fire points found and only 352 used or are you using all of the points that were found – I am confused as to why you have two different metrics to measure where a fire has been. How big is your fire point – what is the spatial resolution of your point?
We added this paragraph: "the fire polygons provided to us by the state wildlife organization of Amol County (SWOAC), were matched and validated with the MODIS fire data, and 352 fire points were found. Although there could be more than 352 fire points, it is not certain about them, but at these 352 fire points, fires have occurred with absolute certainty"
15) How do you know the 17 factors are important – are there important factors that are not included? How has this list been determined or is it from other sources, in which case please reference these.
We added this paragraph: "These factors have been extracted based on the studies that happened in the previous research, especially the studies that happened in this area. By reviewing articles (Ghorbanzadeh et al., 2019; Gigović et al., 2019; Zhang et al., 2019; Eskandari et al., 2021; Gholamnia et al., 2020; Jaafari and Pourghasemi, 2019), these 17 available factors were extracted."
16) Who is doing all this selecting/removing of features? Are these features independent of one another, or are they interdependent
As explained in the article, in this method, by building a model on the entire set of problem variables, it calculates their importance for each variable. In the next step, the least important variable is removed, the model is rebuilt on the other remaining variables, and the importance of each variable is recalculated.
17) Again, this comes back to the question about the factors/features of importance – knowing whether they are complete and whether they are transferable between different geographical locations. This is not clear in the paper.
In conclusion, we added this sentence " It is possible that the factors that are known as important factors in this study case, in another geographical environment, other factors are identified as important factors by this method, on the other hand, these factors that are known in this study case The factors that have been used were the ones that could be accessed, so it can be argued that there are other factors as well, but because they are not accessible, they have not been investigated."
18) Line 194 & 207 – the majority of votes – who’s voting?
where the predictions of individual trees are treated as votes and the prediction of the random forest is determined by the majority of votes.
19) 195-201 – I do not see the importance of this part
Due to the fact that the RFE method is described in these sentences, their presence is mandatory.
20) 205 What is a bootstrap sample – reference?
We added this sentence "The bootstrap sampling method is a resampling method that uses random sampling and bootstrap sample is a smaller sample that is “bootstrapped” from a larger sample (Efron and Tibshirani, 1993)".
21) Please make the y-axis in figures 3,4,5 and 6 the same so that the variability in each of the modeling approaches is abundantly clear. Do they need to be separate figures, it could be done on a single plot. What is the shading showing on these figures and why is this not discussed?
All four graphs are displayed in the same figure to enable comparison.
22) How are the models scored? What is the range of possible scores? is 0.87 considered acceptable?
The score obtained by the model here is the auc criterion. The auc range is between 0 and 1. The AUC values are interpreted as reflecting the following model accuracies: 0.6–0.7 poor, 0.6–0.7 medium, 0.7–0.8 good, 0.8–0.9 very good, and 0.9–1 excellent (Pourghasemi et al., 2017). According to Hong's article (Hong et al., 2018), which considered the value of 0.7 for the AUC criterion as a good performance of the model, also in the article of Jafari and Pourghasemi (Pourghasemi et al., 2020), the AUC criterion equal to 0.8 is considered a very good performance for the model.
23) Can the factors in table 2 and figure 7 please be in the same order
Figure 7, its order was arranged according to table 2.
24) These are showing the same data – do these need to be duplicated?
Due to the large number of features in Table 2, for easy identification of the votes obtained for each feature, Figure 7 is displayed as a graph of the votes obtained.
25) Section 5.3 explains a statistical analysis of the different methods – it would be good to show what you mean by true and false positives. Tables 3-5 AUC is not described in the equations and not explained what it is – 6 equations 7 columns in the tables. There is no discussion over the merits of each method – so it just feels like noise.
Formula AUC was added along with formulas Specificity and Sensitivity.
We added this paragraph: " The AUC criterion, which is one of the most important evaluation criteria for models, indicates that the proportion of fire and non-fire points which are correctly classified. The Recall measure shows how many positive examples in the sample are predicted correctly. The fraction of relevant instances in the retrieved instances. The sensitivity criterion also indicates the percentage of fire points that are correctly classified. On the other hand, the specificity criterion indicates the percentage of non-fire points that are correctly classified."
26) The fire susceptibility maps – do these not just show that where there have been previous fires – these areas are susceptible to fires? There is no discussion of these images in any detail.
In section 5.5 we added this paragraph: " A forest fire susceptibility map depicts areas likely to have forest fire in the future by correlating some of the principal factors that contribute to forest fire with the past distribution. The forest fire susceptibility maps represent a measure of the probability of the occurrence of wildfires for a region based on considered conditioning factors. The natural breaks classification method (available in Arc map 10.8) was used to classify the resulting spatial prediction of wildfire susceptibility maps. This classification method is the most common method for categorizing prediction maps for interpreting values close to each class boundary (e.g., values between “High” and “Very high” susceptibility predictions). The model generates a number between 0 and 1 for each pixel according to its feature vector. Using a reclassification tool in the Spatial Analyst Tools ArcGIS 10.8 software, each final map cell is classified into five classes (very low, low, moderate, high, and very high) representing the forest fire hazard index, with the natural breaks method, all outcomes are divided into five classes."
27) The discussion feels like an executive summary of the paper and the conclusions are lacking in conclusion.
According to other comments, modifications have been made in the discussion and conclusions, which also cover this comment.
These two paragraphs were added in the discussion:
" Pourghasemi et al. (Pourghasemi et al., 2020) have identified the factors of distance from rivers and residential areas, TWI, rainfall, aspect, and temperature as important factors in the Boruta algorithm and these factors have also been identified as important factors in our method. But the factors of use and slope, which are not known as important factors in the scope of our study, are known as influential factors in the scope of their study, and this indicates that in order to make a correct comparison between the methods of feature selection and To determine their performance, they should be tested in different geographical environments."
" In fire science, the slope factor has been identified as an important factor in fire modeling (Hong et al., 2018; Pourghasemi et al., 2020) , But there are also articles that do not consider the slope factor due to the geography of the region (Satir et al., 2016; Kim et al., 2019; Cao et al., 2017). About our study area, there are many non-fire points in steep areas, so the models do not recognize this factor as an important factor in the fire forest . However, the direction of slope and height have been identified as important factors. In the table below, the distribution of fire and non-fire points in the study area can be seen according to the slope classification. As can be inferred from the table, the distribution of fire and non-fire points in steep areas are similar, so the factor could not be recognized as an important fire factor in this study area."
The Table 8 was added.
And this paragraph was added in the conclusion:
"It is possible that the factors that are known as important factors in this study case, in another geographical environment, other factors are identified as important factors by this method, on the other hand, these factors that are known in this study case The factors that have been used were the ones that could be accessed, so it can be argued that there are other factors as well, but because they are not accessible, they have not been investigated"
Finally, we appreciate your support and your constructive suggestions. We strongly believe that we have addressed the issues concerning the logical flow of the manuscript and have improved the scientific aspect significantly. We hope that you will find this revised version worthwhile to be published.
Thank you very much again.
The authors
Citation: https://doi.org/10.5194/egusphere-2022-1294-CC3 -
CC4: 'Reply on RC1', Parham Pahlavani, 30 Mar 2023
Dear Reviewer,
We very much appreciate your positive statements regarding our manuscript. You indeed kindly spent significant time on this manuscript and we are grateful for the detailed suggestions. You brought up interesting aspects and we believe that these suggestions and our respective reactions to them will improve the quality of the paper. We did our best to improve the scientific quality of the manuscript significantly. Based on your constructive comments on the initial version and our comprehensive revisions, we are confident that you will find this version now worthwhile to get published. All the revisions are specified with the Blue color in the text.
1) A general overview of the paper – there is some good work in here, but it reads too much like a thesis rather than a paper, thus inhibiting communication. For instance – a lot of section 4 could/should be in the introduction, while the current introduction is verbose and not concise enough.According to other comments, modifications have been made in the introduction, which also covers this comment.
2) Additionally, in fire science slope, for instance, has been identified as an important factor in wildfire modeling – however, your study area does not give details of slope or any of the 17 factors you’ve said are important. My inference therefore from your study and figure 7 is that the area is a) not overly sloped – which would be surprising for a mountainous region - or b) the fire areas and non-fire areas are equally slopedWe added this paragraph: "In fire science, the slope factor has been identified as an important factor in fire modeling, but in the case of our study, there are many non-fire points in steep areas, so the models do not recognize this factor as an important factor in the fire forest. However, the direction of slope and height have been identified as important factors."
3) This then comes to the crux of the paper and its title – you are not modeling wildfire, you are modeling relative wildfire susceptibility in a certain area.The title of the article was changed to " How the recursive feature elimination affects the SVM and RF for relative wildfire susceptibility in a certain area? A study case in Iran ".
4) Lines 30-32 – provide reference to support the claim.
Add reference.
5) Lines 33-34 – provide a reference or specify that in this paper this is what you are calling a forest fire.Add reference.
6) Line 35 – highly combustible trees compared to what?Change to sentence to " Fires in forests lead to a lot of environmental destruction due to the presence of combustible vegetation "
7) Paragraph from lines 33-42 – tell me why you are telling me this – why is this important.
We added this sentence " The main goal of modeling forest fires is to reduce the negative effects of fires on humans and the environment as much as possible (Hosseini and Lim, 2022). Also, by determining the areas with the possibility of fire, it leads to better management of natural hazards (Tehrany et al., 2021)."
8) Paragraph 43-53 – end sentences about life safety is new to para and out of the generalized context of fires in Iran – this needs to be changed into two paras, with the latter being about human susceptibility.
Paragraphs 43 to 53 were changed into two paragraphs.
9) Paragraphs 54-64 – none of this is wrong, but it is not noteworthy – this is in my view – common knowledge.
The desired paragraphs were deleted.
10) Paragraphs 64 – 79 – lots of repetition at the start, lots of “authors X did Y” and not enough depth to the review – a generic comment at the end about what is lacking without showing the reader that this is true.
We added these sentences "in their study, the random forests (RFs) model was utilized to link historical fire events to a set of wildfire causative factors to measure the importance of each factor on fire ignition. then employed support vector machines (SVMs), to produce an accurate estimate of wildfire probability across the study area"
We added this sentence " this study utilizes Genetic Algorithms (GA) to obtain the optimal combination of forest fire-related variables and apply data mining methods for constructing a forest fire susceptibility map"
11) Paragraphs 80-104 – too long- consider splitting. As before lots of X did Y, not enough “however,…” there is some, but more needed.
Paragraphs 80-104 were divided into several paragraphs.
12) Para 105 – 112 – need to explain why RFE is better than the other methods. Why have you chosen this method? You then bring in terms such as adaboost, gradient boosting, random forests, and extra trees without any prior referencing in the text.
We added this paragraph " As a greedy way of finding nested subset of features, RFE was argued to be much more robust to data overfitting than wrapper methods (Zeng et al., 2009). RFE tends to remove redundant and weak features and retains independent features. RFE seeks to improve generalization performance by removing the least important features whose deletion will have the least effect, on training errors (Escanilla et al., 2018)".
We added this paragraph ". Feature selection is accomplished by recursive feature elimination (RFE), As a result of its simplicity and effectiveness, RFE is a popular feature selection algorithm because it can identify the feature in a training dataset that is most relevant to the prediction of the variable."
13) Resolution of Figure 1 could be improved. Please show an image from the timeframe being explored e.g., an image of the forest between 2012-2017.
Image No. 1 was changed and considering that the fire points are related to the reported fire polygons and each reported fire polygon has a date since the fire occurred, a date label was added on the map for the fire points.
14) Can you explain the difference between a fire point and the polygons that you are using, and how they are used/interact with one another? Were there more than 352 fire points found and only 352 used or are you using all of the points that were found – I am confused as to why you have two different metrics to measure where a fire has been. How big is your fire point – what is the spatial resolution of your point?
We added this paragraph: "the fire polygons provided to us by the state wildlife organization of Amol County (SWOAC), were matched and validated with the MODIS fire data, and 352 fire points were found. Although there could be more than 352 fire points, it is not certain about them, but at these 352 fire points, fires have occurred with absolute certainty"
15) How do you know the 17 factors are important – are there important factors that are not included? How has this list been determined or is it from other sources, in which case please reference these.
We added this paragraph: "These factors have been extracted based on the studies that happened in the previous research, especially the studies that happened in this area. By reviewing articles (Ghorbanzadeh et al., 2019; Gigović et al., 2019; Zhang et al., 2019; Eskandari et al., 2021; Gholamnia et al., 2020; Jaafari and Pourghasemi, 2019), these 17 available factors were extracted."
16) Who is doing all this selecting/removing of features? Are these features independent of one another, or are they interdependent
As explained in the article, in this method, by building a model on the entire set of problem variables, it calculates their importance for each variable. In the next step, the least important variable is removed, the model is rebuilt on the other remaining variables, and the importance of each variable is recalculated.
17) Again, this comes back to the question about the factors/features of importance – knowing whether they are complete and whether they are transferable between different geographical locations. This is not clear in the paper.
In conclusion, we added this sentence " It is possible that the factors that are known as important factors in this study case, in another geographical environment, other factors are identified as important factors by this method, on the other hand, these factors that are known in this study case The factors that have been used were the ones that could be accessed, so it can be argued that there are other factors as well, but because they are not accessible, they have not been investigated."
18) Line 194 & 207 – the majority of votes – who’s voting?
where the predictions of individual trees are treated as votes and the prediction of the random forest is determined by the majority of votes.
19) 195-201 – I do not see the importance of this part
Due to the fact that the RFE method is described in these sentences, their presence is mandatory.
20) 205 What is a bootstrap sample – reference?
We added this sentence "The bootstrap sampling method is a resampling method that uses random sampling and bootstrap sample is a smaller sample that is “bootstrapped” from a larger sample (Efron and Tibshirani, 1993)".
21) Please make the y-axis in figures 3,4,5 and 6 the same so that the variability in each of the modeling approaches is abundantly clear. Do they need to be separate figures, it could be done on a single plot. What is the shading showing on these figures and why is this not discussed?
All four graphs are displayed in the same figure to enable comparison.
22) How are the models scored? What is the range of possible scores? is 0.87 considered acceptable?
The score obtained by the model here is the auc criterion. The auc range is between 0 and 1. The AUC values are interpreted as reflecting the following model accuracies: 0.6–0.7 poor, 0.6–0.7 medium, 0.7–0.8 good, 0.8–0.9 very good, and 0.9–1 excellent (Pourghasemi et al., 2017). According to Hong's article (Hong et al., 2018), which considered the value of 0.7 for the AUC criterion as a good performance of the model, also in the article of Jafari and Pourghasemi (Pourghasemi et al., 2020), the AUC criterion equal to 0.8 is considered a very good performance for the model.
23) Can the factors in table 2 and figure 7 please be in the same order
Figure 7, its order was arranged according to table 2.
24) These are showing the same data – do these need to be duplicated?
Due to the large number of features in Table 2, for easy identification of the votes obtained for each feature, Figure 7 is displayed as a graph of the votes obtained.
25) Section 5.3 explains a statistical analysis of the different methods – it would be good to show what you mean by true and false positives. Tables 3-5 AUC is not described in the equations and not explained what it is – 6 equations 7 columns in the tables. There is no discussion over the merits of each method – so it just feels like noise.
Formula AUC was added along with formulas Specificity and Sensitivity.
We added this paragraph: " The AUC criterion, which is one of the most important evaluation criteria for models, indicates that the proportion of fire and non-fire points which are correctly classified. The Recall measure shows how many positive examples in the sample are predicted correctly. The fraction of relevant instances in the retrieved instances. The sensitivity criterion also indicates the percentage of fire points that are correctly classified. On the other hand, the specificity criterion indicates the percentage of non-fire points that are correctly classified."
26) The fire susceptibility maps – do these not just show that where there have been previous fires – these areas are susceptible to fires? There is no discussion of these images in any detail.
In section 5.5 we added this paragraph: " A forest fire susceptibility map depicts areas likely to have forest fire in the future by correlating some of the principal factors that contribute to forest fire with the past distribution. The forest fire susceptibility maps represent a measure of the probability of the occurrence of wildfires for a region based on considered conditioning factors. The natural breaks classification method (available in Arc map 10.8) was used to classify the resulting spatial prediction of wildfire susceptibility maps. This classification method is the most common method for categorizing prediction maps for interpreting values close to each class boundary (e.g., values between “High” and “Very high” susceptibility predictions). The model generates a number between 0 and 1 for each pixel according to its feature vector. Using a reclassification tool in the Spatial Analyst Tools ArcGIS 10.8 software, each final map cell is classified into five classes (very low, low, moderate, high, and very high) representing the forest fire hazard index, with the natural breaks method, all outcomes are divided into five classes."
27) The discussion feels like an executive summary of the paper and the conclusions are lacking in conclusion.
According to other comments, modifications have been made in the discussion and conclusions, which also cover this comment.
These two paragraphs were added in the discussion:
" Pourghasemi et al. (Pourghasemi et al., 2020) have identified the factors of distance from rivers and residential areas, TWI, rainfall, aspect, and temperature as important factors in the Boruta algorithm and these factors have also been identified as important factors in our method. But the factors of use and slope, which are not known as important factors in the scope of our study, are known as influential factors in the scope of their study, and this indicates that in order to make a correct comparison between the methods of feature selection and To determine their performance, they should be tested in different geographical environments."
" In fire science, the slope factor has been identified as an important factor in fire modeling (Hong et al., 2018; Pourghasemi et al., 2020) , But there are also articles that do not consider the slope factor due to the geography of the region (Satir et al., 2016; Kim et al., 2019; Cao et al., 2017). About our study area, there are many non-fire points in steep areas, so the models do not recognize this factor as an important factor in the fire forest . However, the direction of slope and height have been identified as important factors. In the table below, the distribution of fire and non-fire points in the study area can be seen according to the slope classification. As can be inferred from the table, the distribution of fire and non-fire points in steep areas are similar, so the factor could not be recognized as an important fire factor in this study area."
The Table 8 was added.
And this paragraph was added in the conclusion:
"It is possible that the factors that are known as important factors in this study case, in another geographical environment, other factors are identified as important factors by this method, on the other hand, these factors that are known in this study case The factors that have been used were the ones that could be accessed, so it can be argued that there are other factors as well, but because they are not accessible, they have not been investigated"
Finally, we appreciate your support and your constructive suggestions. We strongly believe that we have addressed the issues concerning the logical flow of the manuscript and have improved the scientific aspect significantly. We hope that you will find this revised version worthwhile to be published.
Thank you very much again.
The authors
Citation: https://doi.org/10.5194/egusphere-2022-1294-CC4 -
CC5: 'Reply on CC4', Parham Pahlavani, 30 Mar 2023
The comment was uploaded in the form of a supplement: https://egusphere.copernicus.org/preprints/2023/egusphere-2022-1294/egusphere-2022-1294-CC5-supplement.pdf
-
CC5: 'Reply on CC4', Parham Pahlavani, 30 Mar 2023
-
AC2: 'Reply on RC1', Parham Pahlavani, 30 Mar 2023
-
CC7: 'Comment on egusphere-2022-1294', F. Hosseinali, 01 Jun 2023
I encountered a question when I read your article: How did you assess the independence of input factors such as vegetation, height, etc?
Citation: https://doi.org/10.5194/egusphere-2022-1294-CC7 -
CC8: 'Reply on CC7', Parham Pahlavani, 03 Jun 2023
The selected factors have been based on articles conducted in this area; therefore, their independence has been disregarded. However, the article acknowledges that filter methods solely assess the dependency of factors and do not consider the combination of independent and dependent factors. As a result, the utilization of recursive feature elimination is deemed reasonable. This method enables the attainment of the optimal combination of independent and dependent factors, thereby maximizing the improvement of the problem. Please refer to the paragraph starting with line 95 for more information:
"These methods only compare the correlation between factors, and this causes the impact of several characteristics to be ignored by putting together the occurrence of fire. However, the wrapper methods cover this defect and consider the combination of features as effective features in the problem. The wrapper method is also called the greedy search algorithm because this method scans all possible combinations of features before selecting the one that produces the best ML algorithm performance"
Citation: https://doi.org/10.5194/egusphere-2022-1294-CC8 -
AC3: 'Reply on CC7', Parham Pahlavani, 03 Jun 2023
The selected factors have been based on articles conducted in this area; therefore, their independence has been disregarded. However, the article acknowledges that filter methods solely assess the dependency of factors and do not consider the combination of independent and dependent factors. As a result, the utilization of recursive feature elimination is deemed reasonable. This method enables the attainment of the optimal combination of independent and dependent factors, thereby maximizing the improvement of the problem. Please refer to the paragraph starting with line 95 for more information:
"These methods only compare the correlation between factors, and this causes the impact of several characteristics to be ignored by putting together the occurrence of fire. However, the wrapper methods cover this defect and consider the combination of features as effective features in the problem. The wrapper method is also called the greedy search algorithm because this method scans all possible combinations of features before selecting the one that produces the best ML algorithm performance"
Citation: https://doi.org/10.5194/egusphere-2022-1294-AC3
-
CC8: 'Reply on CC7', Parham Pahlavani, 03 Jun 2023
-
RC2: 'Comment on egusphere-2022-1294', Anonymous Referee #2, 04 Nov 2023
General Comments
This study describes a method for selecting relevant factors for inclusion in fire susceptibility mapping aided by various analytical and machine learning approaches. The identified relevant factors are presented for each method along with consideration of the overall accuracy including for models with various numbers of factors.
I wonder if you could provide more details about the actual fire susceptibility mapping approach used thereby also providing greater context for the results presented in Section 5.1. This, along with greater description of the selection process for the 17 variables (and more detail on how these are defined and which variables are used) would aid understanding of the results presented and particularly of the factors excluded. This interpretation is presently quite difficult without detail on the mapping approach and particularly how each factor has been charactersied. Strengthening this I believe would increase further the general applicability and insights from this work.
Overall I believe this study provides a useful contribution however presently is limited by a lack of description of the susceptibility mapping approach and particularly sufficient description of the initial selection of the 17 factors and description of how each factor is measured/defined. Presently, this makes it difficult to interpret the study and it's results.
Specific Comments
I agree with previous comments that it should be clarified from the outset (and in the title) that it is forest fire susceptibility that is being modeled rather than the wildfire itself (i.e. behaviour, spread etc.).
How were the 17 factors identified (i.e. what process was involved). Is it worth separating out those that apply to ignition (‘triggering’) vs. spreading or both. Subsequently, RFE is used to select features from these initial 17 but the initial assessment and selection of a ‘longlist’ of factors would seem to be a very important part of any feature selection process to prevent the risk of optimizing for the wrong set of factors.
Abstract Lines 11-12: Could you clarify what the difference between accuracy (in both uses below is) ‘Different metrics were used to measure accuracy, including recall, precision, F1, accuracy, the area under the curve (AUC), Matthews correlation coefficient (MCC), and Kappa’. Perhaps by defining accuracy in the subsequent list? This will also help the interpretation of your overall conclusions presented in the final lines of the abstract ‘The greatest improvement is for SVM, with more than 10.97% and 8.61% in the accuracy and AUC metrics, respectively.’
Intro: The early sections of the introduction could perhaps benefit from a more specific selection of cited references, particularly where the effects of forest fires are discussed. For example, in several cases, it may be worth referring directly to one of the studies cited in the actual source cited. Additionally, a brief discussion of factors known to influence fire susceptibility (aided by the existing literature) may help the discussion of why the initial 17 factors were selected, and subsequently aid the discussion of excluded and selected factors.
Intro Line 2: Could a more relevant study perhaps be cited here? For example, one of the studies cited in Pourtaghi et al., 2016 in which the ecosystem services and carbon balance of forests are considered?
Intro Lines 4-6: ‘Therefore, most forest fires, whether natural or induced by humans, cause many negative ecological, social, and economic impacts on forest restoration’ Can this be reworded to allow for or acknowledge the increasingly important role of prescribed fire in many regions and the potential benefits. And similarly the beneficial historical role of fire in many regions. Perhaps rewording to ‘forest fires, whether natural or induced by humans, can cause many negative..’ Or this could be moved to appear after your definition of a forest fire (a citation for this definition could also be added if applicable).
Intro Lines 7-8: As above it would be good to acknowledge that ‘Fires in forests can lead to significant environmental damage’ rather than ‘Fires in forests lead to a lot of environmental destruction due to the presence of highly combustible trees’ as this is not necessarily always the case.
Intro Lines 25-26: Can you clarify what is meant by ‘It is important to take precautions and predict fire facilities in fire-prone areas to prevent forest fires.’. Is this referring to firefighting resources in a given area? Are these efforts actually targeted towards preventing forest fires (i.e. preventing ignition) or reducing risk/hazard mapping etc.?
Intro Lines 68-70: Could you clarify what is meant by ‘and this causes the impact of several characteristics to be ignored by putting together the occurrence of fire.’
Section 3.2 Line 8: Citation required for Aster Dem.
Section 3.2 Line 9: Can you clarify what is meant by wind effect? What is the actual continuous variable considered here?
Section 3.2, Table 1: In this table (or in an appendix?) could you provide more details on each of these factors? For example, what is the specific variable considered? So for wind effect is this for example max wind speed at a given height, average 10m AGL wind speed, gusting speed etc? For categorical variables could you present the different categories considered?
Methods: Could you add more details/description of the fire susceptibility mapping methods used?
Methods Line 1: The process involved in step 1 (‘identifying the forest fire factors associated with the study area’) could benefit from additional discussion.
Table 2: See earlier comments on Table 1. Providing more details on how these features are specifically defined (i.e. what are the categorical or continuous variables used) will provide greater context here. This would aid the discussion and may also help to address existing reviewer comments around the need to discuss the exclusion of factors known to affect flame spread e.g. slope. Similarly, an additional description of the fire susceptibility mapping approach may also aid this discussion by explaining the extent to which this study focuses on ignition (fire occurrence).
Discussion Lines 12-13: ‘According to previous studies conducted in this specific study area, 17 forest fire conditional factors have been selected for this study.’ Could you discuss this more in the introduction to help explain your choice of the initial 17 factors? The discussion could perhaps also address any study limitations based on factors not considered in the 17 original factors which may merit consideration in future studies.
Discussion Lines 38-40: Can you clarify if you are referring here to the other 7 factors selected in your study? Or if these are an additional 7 factors that you did not consider? ‘Several studies have identified seven other factors as effective factors in forest fires. (Bjånes et al., 2021; Eskandari et al., 2021; Mohajane et al., 2021; Naderpour et al., 2021; Tavakkoli Piralilou et al., 2022; Valdez et al., 2017).
Technical Comments
Abstract Line 9: ‘and the second on those derived from RFE model’ could be reworded for clarity e.g. ‘and secondly on those derived from the RFE model’.
Abstract Line 14: ‘and not include unnecessary factors, could be reworded for clarity e.g. ‘and to exclude unnecessary factors’.
Intro Line 11: This probably requires a full citation ‘According to Copernicus (https://effis.jrc.ec.europa.eu)’
Intro Line 28: ‘Contribute to the fire's susceptibility.’ Can you revisit the wording here? Maybe this should be ‘contribute to fire susceptibility’. (As it’s not the fire that is susceptible to something else but the susceptibility to fire that is being considered).
Intro Lines 52-53: ‘any evaluation if they play a significant role in their selected case study area.’ Typo should be ‘ any evaluation of if they play a significant…’
Intro Line 56: Typo ‘accuracies of the resulting FSMs caused’ should be ‘accuracies of the resulting FSMs are caused’
Study Area Line 1: province does not need to be capitalised.
Section 4.4 Line 7 – Missing full stop ‘We also weighed the weak classifier based on the classification effect of the sample set’
Issue with reference ‘Breiman, L.: [No title found], Machine Learning, 45, 5–32, https://doi.org/10.1023/A:1010933404324, 2001’
Reference details require correction ‘Bruinsma, J. (Ed.): World Agriculture: Towards 2015/2030, 0 ed., Routledge, https://doi.org/10.4324/9781315083858, 2017.’
Error in reference: Guyon, I., Weston, J., Barnhill, S., and Vapnik, V.: [No title found], Machine Learning, 46, 389–422, 470 https://doi.org/10.1023/A:1012487302797, 2002.
Reference details missing: Jahdi, R., Salis, M., Darvishsefat, A. A., Alcasena Urdiroz, F. J., Etemad, V., Mostafavi, M. A., Lozano, O. M., and Spano, D.: Calibration of FARSITE fire area simulator in Iranian northern forests, Other Hazards (e.g., Glacialand Snow Hazards, Karst, Wildfires Hazards, and Medical Geo-Hazards), https://doi.org/10.5194/nhessd-2-6201-2014, 2014.
Reference details missing: Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Müller, A., Nothman, J., Louppe, G., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., and Duchesnay, É.: Scikit-learn: Machine Learning in Python, https://doi.org/10.48550/ARXIV.1201.0490, 2012.
Citation: https://doi.org/10.5194/egusphere-2022-1294-RC2 -
AC4: 'Reply on RC2', Parham Pahlavani, 05 Dec 2023
Dear Reviewer,
I would like to express my sincere gratitude for the time and effort you dedicated to reviewing my manuscript. Your insightful comments and constructive feedback have significantly contributed to the improvement of the paper. I am thankful for the thoughtfulness of your review.
I am pleased to inform you that I have carefully addressed each of the comments and suggestions you provided. Your input has been invaluable in enhancing the quality and clarity of the manuscript. I believe that the revisions made have strengthened the overall content and presentation of the paper.
Once again, I extend my appreciation for your valuable contribution to this process. Your expertise and attention to detail have been instrumental in refining the manuscript, and I am truly grateful for your support.
Thank you for your time and consideration.
Sincerely,
Authors
- I agree with previous comments that it should be clarified from the outset (and in the title) that it is forest fire susceptibility that is being modeled rather than the wildfire itself (i.e. behavior, spread etc.).
Thank you for your valuable feedback. We have revised the title of the paper to better reflect the focus of our study. The new title, "Modeling Relative Wildfire Susceptibility in a Specific Area: A Study of Recursive Feature Elimination's Impact on SVM and RF—A Case Study in Iran," aims to clearly convey that our study is centered on modeling relative wildfire susceptibility and the impact of recursive feature elimination on SVM and RF in a specific area. We believe this revision effectively addresses your concern about clarifying the modeled factors in the title. We appreciate your input and hope that this change aligns with your expectations.
- How were the 17 factors identified (i.e. what process was involved). Is it worth separating out those that apply to ignition (‘triggering’) vs. spreading or both. Subsequently, RFE is used to select features from these initial 17 but the initial assessment and selection of a ‘longlist’ of factors would seem to be a very important part of any feature selection process to prevent the risk of optimizing for the wrong set of factors.
Thank you for your insightful comments and suggestions. We have carefully reviewed your feedback and have made the necessary revisions to address your concerns. The 17 factors were identified through a comprehensive review of existing literature and empirical studies in the field. These factors were selected based on their documented relevance to forest fire behavior and susceptibility. While the initial identification of these factors was not explicitly categorized into those that apply to ignition versus spreading, the subsequent use of Recursive Feature Elimination (RFE) allowed for the selection of the most influential factors for modeling. The RFE process involved iteratively fitting the model and identifying the most relevant features, thereby addressing the concern of optimizing for the wrong set of factors. This iterative approach ensured that the final set of features used in the analysis was well-suited for the specific objectives of the study, mitigating the risk of suboptimal feature selection. Additionally, the consideration of factors that specifically apply to ignition versus spreading could be a valuable avenue for further research, potentially enhancing the precision and applicability of the model. This distinction may offer insights into the distinct mechanisms driving the initiation and propagation of forest fires, thereby contributing to a more nuanced understanding of fire behavior and risk assessment. In summary, while the initial assessment and selection of the factors were crucial, the subsequent application of RFE provided a robust mechanism for refining the feature set and mitigating the risk of suboptimal feature selection. Further exploration of factors related to ignition and spreading could offer valuable insights for future research in this domain.
- Abstract Lines 11-12: Could you clarify what the difference between accuracy (in both uses below is) ‘Different metrics were used to measure accuracy, including recall, precision, F1, accuracy, the area under the curve (AUC), Matthews correlation coefficient (MCC), and Kappa’. Perhaps by defining accuracy in the subsequent list? This will also help the interpretation of your overall conclusions presented in the final lines of the abstract ‘The greatest improvement is for SVM, with more than 10.97% and 8.61% in the accuracy and AUC metrics, respectively.’
We have revised the sentence as per your suggestion. The updated version now reads: "Various metrics, including recall, precision, F1 score, accuracy, area under the curve (AUC), Matthews correlation coefficient (MCC), and Kappa, were employed to measure the performance of the models. The assessments demonstrate that leveraging RFE models enhances the FSM results by identifying key factors and excluding unnecessary ones. Notably, the SVM model exhibits significant improvement, achieving an increase of over 10.97% in accuracy and 8.61% in AUC metrics. This improvement underscores the effectiveness of the RFE approach in enhancing the predictive performance of the SVM model." We believe this modification aligns with your feedback and provides a clearer description of the assessment process and its implications. Thank you for your input, and we hope this change meets your expectations.
- Intro: The early sections of the introduction could perhaps benefit from a more specific selection of cited references, particularly where the effects of forest fires are discussed. For example, in several cases, it may be worth referring directly to one of the studies cited in the actual source cited. Additionally, a brief discussion of factors known to influence fire susceptibility (aided by the existing literature) may help the discussion of why the initial 17 factors were selected, and subsequently aid the discussion of excluded and selected factors.
In response to your suggestion to provide more specific references, especially when discussing the effects of forest fires and to discuss factors known to influence fire susceptibility based on existing literature, we have made the following changes:
In paragraph 55, we have added the following sentences to address the specific selection of cited references and to discuss factors known to influence fire susceptibility based on existing literature:
"Related topographic factors are crucial in forest fire susceptibility, widely used for forest fire susceptibility mapping (Kolden and Abatzoglou, 2018; Lautenberger, 2017). For example, the slope factor is essential due to its impact on fire spread, with steeper slopes leading to faster fire propagation (Ghorbanzadeh et al., 2018). Additionally, the difference in temperature and moisture between north- and south-facing slopes contributes to a higher risk of forest fires on south-facing slopes (Sayad et al., 2019). Altitude also plays a significant role, with higher moisture levels at greater altitudes (Ganteaume et al., 2013). The wind effect factor encompasses the degree of wind direction, wind speed, and altitude layer (Pourtaghi et al., 2015). Human-made factors include various distance measures, classified based on their relevance to forest fires, human activity radius, literature, and expert insights (Pourghasemi et al., 2016)."
- Intro Line 2: Could a more relevant study perhaps be cited here? For example, one of the studies cited in Pourtaghi et al., 2016 in which the ecosystem services and carbon balance of forests are considered?
In response to your comment regarding the need for a more relevant study to be cited in Intro Line 2, we have made the following changes:
We have added two additional references to support the discussion on ecosystem services and carbon balance of forests. The references added are as follows:
Manisalidis, I., Stavropoulou, E., Stavropoulos, A., and Bezirtzoglou, E.: Environmental and Health Impacts of Air Pollution: A Review, Front. Public Health, 8, 14.
Badea, O.: Climate Change and Air Pollution Effect on Forest Ecosystems, Forests, 12, 1642, https://doi.org/10.3390/f12121642, 2021
- Intro Lines 4-6: ‘Therefore, most forest fires, whether natural or induced by humans, cause many negative ecological, social, and economic impacts on forest restoration’ Can this be reworded to allow for or acknowledge the increasingly important role of prescribed fire in many regions and the potential benefits. And similarly the beneficial historical role of fire in many regions. Perhaps rewording to ‘forest fires, whether natural or induced by humans, can cause many negative..’ Or this could be moved to appear after your definition of a forest fire (a citation for this definition could also be added if applicable).
We have revised the specified section as per your suggestion. The revised content now appears after the definition of a forest fire. The revised section reads as follows: "Forest fires, whether natural or induced by humans, can have significant ecological, social, and economic impacts on forest restoration. However, it is important to acknowledge the increasingly important role of prescribed fire in many regions and the potential benefits it can bring. Similarly, historical fire regimes have played a beneficial role in many regions. Therefore, it is essential to consider the potential positive impacts of controlled or prescribed fires alongside the negative impacts of forest fires."
- Intro Lines 7-8: As above it would be good to acknowledge that ‘Fires in forests can lead to significant environmental damage’ rather than ‘Fires in forests lead to a lot of environmental destruction due to the presence of highly combustible trees’ as this is not necessarily always the case.
We have revised the sentence as per your suggestion. The revised sentence now reads: "Fires in forests can lead to significant environmental damage."
- Intro Lines 25-26: Can you clarify what is meant by ‘It is important to take precautions and predict fire facilities in fire-prone areas to prevent forest fires.’. Is this referring to firefighting resources in a given area? Are these efforts actually targeted towards preventing forest fires (i.e. preventing ignition) or reducing risk/hazard mapping etc.?
We have revised the sentence as per your suggestion. The revised sentence now reads: "It is important to take precautions and predict fire facilities in fire-prone areas to prevent forest fires, referring to the proactive measures and predictive strategies aimed at preventing the ignition of forest fires, rather than firefighting resources in a given area. These efforts are focused on reducing the risk of forest fires through preventive measures, such as hazard mapping, fire risk assessment, and implementing measures to minimize the likelihood of fire ignition in fire-prone areas."
- Intro Lines 68-70: Could you clarify what is meant by ‘and this causes the impact of several characteristics to be ignored by putting together the occurrence of fire.’
We have revised the paragraph in question based on your feedback. The revised paragraph now includes a specific source for the information provided about the potential disadvantage of the Boruta algorithm. Thank you for your guidance, and I hope this meets your expectations.
" One potential disadvantage of the Boruta algorithm is that it can be computationally intensive, especially when dealing with a large number of input features. Since Boruta works by creating shadow features and comparing their importance to the original features, this process can become time-consuming and resource-intensive when dealing with high-dimensional datasets. Additionally, the algorithm's performance may be sensitive to its parameters, requiring careful tuning for optimal results (Kursa and Rudnicki, 2010)."
- Section 3.2 Line 8: Citation required for Aster Dem
Thank you for your valuable feedback. In response to your comment regarding the need for a citation for Aster Dem in Section 3.2, we have added the appropriate citation as per your suggestion.
- Section 3.2 Line 9: Can you clarify what is meant by wind effect? What is the actual continuous variable considered here?
In response to your comment regarding the clarification of the wind effect in Section 3.2, we have added the following information: "The factor of wind effect was generated by three different factors, including the degree of wind direction, wind speed (m/s), and altitude layer (Pourtaghi et al., 2015)."
- Methods: Could you add more details/description of the fire susceptibility mapping methods used?
Thank you for your valuable feedback. In response to your request for additional details on the fire susceptibility mapping methods used, we have expanded the description of our approach to provide a more comprehensive overview of the techniques and methodologies employed in our research. We believe that these enhancements will address your concerns and provide a clearer understanding of the methods utilized in our study.
- Table 2: See earlier comments on Table 1. Providing more details on how these features are specifically defined (i.e. what are the categorical or continuous variables used) will provide greater context here. This would aid the discussion and may also help to address existing reviewer comments around the need to discuss the exclusion of factors known to affect flame spread e.g. slope. Similarly, an additional description of the fire susceptibility mapping approach may also aid this discussion by explaining the extent to which this study focuses on ignition (fire occurrence).
In section 3.2, We have included the paragraphs you suggested, which provide detailed insights into the factors influencing fire occurrence and spread. The references have been incorporated to support the information provided. These additions aim to enhance the comprehensiveness of the study and address the specific points raised. Thank you for your valuable feedback.
" Height is one of the main factors affecting the size and intensity of fire and is one of the most important spatial layers used in many fields. Accordingly, higher elevations are generally more dangerous than lower elevations when a fire occurs (Rothermel, 1972). In this regard, elevated areas are usually more dangerous than low-lying areas when a fire occurs, especially if the access roads are unpaved or unsuitable for the movement of firefighting teams and their large equipment. If the area in front of the fire is steep, the situation is worse.
The slope of the land is important in the spread of fire and its control, because areas with steep slopes require complex methods of fire control (Estes et al., 2017). Slope controls fire progress, whether it moves uphill or downhill. The direction of the slope affects the amount of solar radiation received by the earth and the amount of soil moisture. In addition, it has an indirect effect on the prevalence of fire because it determines the type and density of vegetation present in a particular location.
Land use is an important factor in determining where wildfires occur, as places with abundant weeds and crops are more vulnerable to fire than others, especially in summer when daytime temperatures are at their maximum. Meanwhile, the possibility of fire in residential areas and forests is less.
Normalized Vegetation Index (NDVI) maps are important maps for analyzing the vegetation cover of each area and identifying the fire vulnerable spots, especially in the presence of seasonal crops, weeds and pastures in each area. are. While the difference of NDVI values in areas with evergreen trees such as oak forests and olive groves is not much. NDVI maps are very different between summer and spring.
Temperature is the most important factor in fire occurrence in the study area. All fires occurred in the summer when the grass had dried and the crops were ready for harvest (MARTÍN and DÍEZ, 2010). No fire has occurred in winter or in low temperature conditions or its occurrence rate is very low. Temperature in the study area can vary from place to place, even in the same season. Wind speed has an effective role in the spread of fire after ignition and may make it impossible to control the spread of fire in some cases. Solar radiation is positively correlated with temperature and associated with fire occurrence (MARTÍN and DÍEZ, 2010), especially in areas dominated by dry grass and fields. Radiation usually varies from place to place due to many factors such as soil texture and moisture content. The topographic moisture index (TWI) is a morphological factor that describes the topography of an area and other related conditions that affect the spatial patterns of soil texture and soil moisture.
Distance from recreation centers is an important factor in fires because many fires are directly or indirectly caused by human activities and activities that allow flames to reach flammable woody biomass. Fires and the number of fires that occur in a given location are positively correlated with population density. Human presence and activity in forest areas increases the possibility of forest fires. As a result, forests are predicted to be always at risk of fire due to nearby human settlements."
- Discussion Lines 12-13: ‘According to previous studies conducted in this specific study area, 17 forest fire conditional factors have been selected for this study.’ Could you discuss this more in the introduction to help explain your choice of the initial 17 factors? The discussion could perhaps also address any study limitations based on factors not considered in the 17 original factors which may merit consideration in future studies.
In response to your suggestion, we have expanded the introduction to provide a more comprehensive discussion regarding the selection of the initial 17 forest fire conditional factors. This includes an explanation of the rationale behind their selection, drawing from previous studies conducted in the specific study area. Furthermore, we have addressed potential limitations based on factors not considered in the original 17, highlighting areas that may merit consideration in future studies. We believe that these additions contribute to a more thorough understanding of our research methodology and its implications.
- Discussion Lines 38-40: Can you clarify if you are referring here to the other 7 factors selected in your study? Or if these are an additional 7 factors that you did not consider? ‘Several studies have identified seven other factors as effective factors in forest fires. (Bjånes et al., 2021; Eskandari et al., 2021; Mohajane et al., 2021; Naderpour et al., 2021; Tavakkoli Piralilou et al., 2022; Valdez et al., 2017).
Thank you for your feedback. In the sentence "In Table 2, one of the outcomes of this study is identifying the distance from power transmission lines as one of eight factors affecting fire occurrence that is less discussed in other studies. Several studies have identified seven other factors as effective factors in forest fires," we are indeed referring to the other seven factors selected in our study, not additional factors that were not considered.
Technical Comments
- Abstract Line 9: ‘and the second on those derived from RFE model’ could be reworded for clarity e.g. ‘and secondly on those derived from the RFE model’.
In response to your suggestion, We have revised the sentence as follows: "The SVM and RF models were applied once on all factors and secondly on those derived from the RFE model as the key factors in FSM."
- Abstract Line 14: ‘and not include unnecessary factors, could be reworded for clarity e.g. ‘and to exclude unnecessary factors’.
Thank you for your feedback, We have revised the sentence as follows: "The assessments demonstrate that leveraging RFE models enhances the FSM results by identifying key factors and excluding unnecessary ones."
- Intro Line 11: This probably requires a full citation ‘According to Copernicus (https://effis.jrc.ec.europa.eu)’
The revised text now includes a citation to the United Nations Environment Programme (2022) report "Spreading like Wildfire – The Rising Threat of Extraordinary Landscape Fires" to support the information provided about the EFFIS - European Forest Fire Information System.
- Intro Lines 52-53: ‘any evaluation if they play a significant role in their selected case study area.’ Typo should be ‘any evaluation of if they play a significant…’
Thank you for pointing out the typo. We have revised the sentence as per your suggestion. The revised sentence now reads: 'The literature review clearly shows that most methodologies employed conditional wildfire criteria without any evaluation of if they play a significant role in their selected case study area.'
- Intro Line 56: Typo ‘accuracies of the resulting FSMs caused’ should be ‘accuracies of the resulting FSMs are caused’
Thank you for pointing out the typo. We have revised the sentence as per your suggestion. The revised sentence now reads: 'While some studies have used several fire conditional factors, it is unclear whether the limited derived accuracies of the resulting FSMs are caused by the model limitations or the adverse impact of some not fully related factors.'
- Study Area Line 1: province does not need to be capitalized.
Thank you for your feedback. We have made the necessary adjustments to the manuscript by removing the capitalization of "province" in the study area section.
- Section 4.4 Line 7 – Missing full stop ‘We also weighed the weak classifier based on the classification effect of the sample set’
Section 4.4 Line 7 – Missing full stop ‘We also weighed the weak classifier based on the classification effect of the sample set’
- Correction of references
We are pleased to inform you that all mentioned references have been thoroughly reviewed and corrected as per your feedback. Thank you for your guidance in ensuring the accuracy and completeness of the reference details.
Citation: https://doi.org/10.5194/egusphere-2022-1294-AC4 -
AC5: 'Reply on RC2', Parham Pahlavani, 05 Dec 2023
Dear Reviewer,
I would like to express my sincere gratitude for the time and effort you dedicated to reviewing my manuscript. Your insightful comments and constructive feedback have significantly contributed to the improvement of the paper. I am thankful for the thoughtfulness of your review.
I am pleased to inform you that I have carefully addressed each of the comments and suggestions you provided. Your input has been invaluable in enhancing the quality and clarity of the manuscript. I believe that the revisions made have strengthened the overall content and presentation of the paper.
Once again, I extend my appreciation for your valuable contribution to this process. Your expertise and attention to detail have been instrumental in refining the manuscript, and I am truly grateful for your support.
Thank you for your time and consideration.
Sincerely,
Authors
- I agree with previous comments that it should be clarified from the outset (and in the title) that it is forest fire susceptibility that is being modeled rather than the wildfire itself (i.e. behavior, spread etc.).
Thank you for your valuable feedback. We have revised the title of the paper to better reflect the focus of our study. The new title, "Modeling Relative Wildfire Susceptibility in a Specific Area: A Study of Recursive Feature Elimination's Impact on SVM and RF—A Case Study in Iran," aims to clearly convey that our study is centered on modeling relative wildfire susceptibility and the impact of recursive feature elimination on SVM and RF in a specific area. We believe this revision effectively addresses your concern about clarifying the modeled factors in the title. We appreciate your input and hope that this change aligns with your expectations.
- How were the 17 factors identified (i.e. what process was involved). Is it worth separating out those that apply to ignition (‘triggering’) vs. spreading or both. Subsequently, RFE is used to select features from these initial 17 but the initial assessment and selection of a ‘longlist’ of factors would seem to be a very important part of any feature selection process to prevent the risk of optimizing for the wrong set of factors.
Thank you for your insightful comments and suggestions. We have carefully reviewed your feedback and have made the necessary revisions to address your concerns. The 17 factors were identified through a comprehensive review of existing literature and empirical studies in the field. These factors were selected based on their documented relevance to forest fire behavior and susceptibility. While the initial identification of these factors was not explicitly categorized into those that apply to ignition versus spreading, the subsequent use of Recursive Feature Elimination (RFE) allowed for the selection of the most influential factors for modeling. The RFE process involved iteratively fitting the model and identifying the most relevant features, thereby addressing the concern of optimizing for the wrong set of factors. This iterative approach ensured that the final set of features used in the analysis was well-suited for the specific objectives of the study, mitigating the risk of suboptimal feature selection. Additionally, the consideration of factors that specifically apply to ignition versus spreading could be a valuable avenue for further research, potentially enhancing the precision and applicability of the model. This distinction may offer insights into the distinct mechanisms driving the initiation and propagation of forest fires, thereby contributing to a more nuanced understanding of fire behavior and risk assessment. In summary, while the initial assessment and selection of the factors were crucial, the subsequent application of RFE provided a robust mechanism for refining the feature set and mitigating the risk of suboptimal feature selection. Further exploration of factors related to ignition and spreading could offer valuable insights for future research in this domain.
- Abstract Lines 11-12: Could you clarify what the difference between accuracy (in both uses below is) ‘Different metrics were used to measure accuracy, including recall, precision, F1, accuracy, the area under the curve (AUC), Matthews correlation coefficient (MCC), and Kappa’. Perhaps by defining accuracy in the subsequent list? This will also help the interpretation of your overall conclusions presented in the final lines of the abstract ‘The greatest improvement is for SVM, with more than 10.97% and 8.61% in the accuracy and AUC metrics, respectively.’
We have revised the sentence as per your suggestion. The updated version now reads: "Various metrics, including recall, precision, F1 score, accuracy, area under the curve (AUC), Matthews correlation coefficient (MCC), and Kappa, were employed to measure the performance of the models. The assessments demonstrate that leveraging RFE models enhances the FSM results by identifying key factors and excluding unnecessary ones. Notably, the SVM model exhibits significant improvement, achieving an increase of over 10.97% in accuracy and 8.61% in AUC metrics. This improvement underscores the effectiveness of the RFE approach in enhancing the predictive performance of the SVM model." We believe this modification aligns with your feedback and provides a clearer description of the assessment process and its implications. Thank you for your input, and we hope this change meets your expectations.
- Intro: The early sections of the introduction could perhaps benefit from a more specific selection of cited references, particularly where the effects of forest fires are discussed. For example, in several cases, it may be worth referring directly to one of the studies cited in the actual source cited. Additionally, a brief discussion of factors known to influence fire susceptibility (aided by the existing literature) may help the discussion of why the initial 17 factors were selected, and subsequently aid the discussion of excluded and selected factors.
In response to your suggestion to provide more specific references, especially when discussing the effects of forest fires and to discuss factors known to influence fire susceptibility based on existing literature, we have made the following changes:
In paragraph 55, we have added the following sentences to address the specific selection of cited references and to discuss factors known to influence fire susceptibility based on existing literature:
"Related topographic factors are crucial in forest fire susceptibility, widely used for forest fire susceptibility mapping (Kolden and Abatzoglou, 2018; Lautenberger, 2017). For example, the slope factor is essential due to its impact on fire spread, with steeper slopes leading to faster fire propagation (Ghorbanzadeh et al., 2018). Additionally, the difference in temperature and moisture between north- and south-facing slopes contributes to a higher risk of forest fires on south-facing slopes (Sayad et al., 2019). Altitude also plays a significant role, with higher moisture levels at greater altitudes (Ganteaume et al., 2013). The wind effect factor encompasses the degree of wind direction, wind speed, and altitude layer (Pourtaghi et al., 2015). Human-made factors include various distance measures, classified based on their relevance to forest fires, human activity radius, literature, and expert insights (Pourghasemi et al., 2016)."
- Intro Line 2: Could a more relevant study perhaps be cited here? For example, one of the studies cited in Pourtaghi et al., 2016 in which the ecosystem services and carbon balance of forests are considered?
In response to your comment regarding the need for a more relevant study to be cited in Intro Line 2, we have made the following changes:
We have added two additional references to support the discussion on ecosystem services and carbon balance of forests. The references added are as follows:
Manisalidis, I., Stavropoulou, E., Stavropoulos, A., and Bezirtzoglou, E.: Environmental and Health Impacts of Air Pollution: A Review, Front. Public Health, 8, 14.
Badea, O.: Climate Change and Air Pollution Effect on Forest Ecosystems, Forests, 12, 1642, https://doi.org/10.3390/f12121642, 2021
- Intro Lines 4-6: ‘Therefore, most forest fires, whether natural or induced by humans, cause many negative ecological, social, and economic impacts on forest restoration’ Can this be reworded to allow for or acknowledge the increasingly important role of prescribed fire in many regions and the potential benefits. And similarly the beneficial historical role of fire in many regions. Perhaps rewording to ‘forest fires, whether natural or induced by humans, can cause many negative..’ Or this could be moved to appear after your definition of a forest fire (a citation for this definition could also be added if applicable).
We have revised the specified section as per your suggestion. The revised content now appears after the definition of a forest fire. The revised section reads as follows: "Forest fires, whether natural or induced by humans, can have significant ecological, social, and economic impacts on forest restoration. However, it is important to acknowledge the increasingly important role of prescribed fire in many regions and the potential benefits it can bring. Similarly, historical fire regimes have played a beneficial role in many regions. Therefore, it is essential to consider the potential positive impacts of controlled or prescribed fires alongside the negative impacts of forest fires."
- Intro Lines 7-8: As above it would be good to acknowledge that ‘Fires in forests can lead to significant environmental damage’ rather than ‘Fires in forests lead to a lot of environmental destruction due to the presence of highly combustible trees’ as this is not necessarily always the case.
We have revised the sentence as per your suggestion. The revised sentence now reads: "Fires in forests can lead to significant environmental damage."
- Intro Lines 25-26: Can you clarify what is meant by ‘It is important to take precautions and predict fire facilities in fire-prone areas to prevent forest fires.’. Is this referring to firefighting resources in a given area? Are these efforts actually targeted towards preventing forest fires (i.e. preventing ignition) or reducing risk/hazard mapping etc.?
We have revised the sentence as per your suggestion. The revised sentence now reads: "It is important to take precautions and predict fire facilities in fire-prone areas to prevent forest fires, referring to the proactive measures and predictive strategies aimed at preventing the ignition of forest fires, rather than firefighting resources in a given area. These efforts are focused on reducing the risk of forest fires through preventive measures, such as hazard mapping, fire risk assessment, and implementing measures to minimize the likelihood of fire ignition in fire-prone areas."
- Intro Lines 68-70: Could you clarify what is meant by ‘and this causes the impact of several characteristics to be ignored by putting together the occurrence of fire.’
We have revised the paragraph in question based on your feedback. The revised paragraph now includes a specific source for the information provided about the potential disadvantage of the Boruta algorithm. Thank you for your guidance, and I hope this meets your expectations.
" One potential disadvantage of the Boruta algorithm is that it can be computationally intensive, especially when dealing with a large number of input features. Since Boruta works by creating shadow features and comparing their importance to the original features, this process can become time-consuming and resource-intensive when dealing with high-dimensional datasets. Additionally, the algorithm's performance may be sensitive to its parameters, requiring careful tuning for optimal results (Kursa and Rudnicki, 2010)."
- Section 3.2 Line 8: Citation required for Aster Dem
Thank you for your valuable feedback. In response to your comment regarding the need for a citation for Aster Dem in Section 3.2, we have added the appropriate citation as per your suggestion.
- Section 3.2 Line 9: Can you clarify what is meant by wind effect? What is the actual continuous variable considered here?
In response to your comment regarding the clarification of the wind effect in Section 3.2, we have added the following information: "The factor of wind effect was generated by three different factors, including the degree of wind direction, wind speed (m/s), and altitude layer (Pourtaghi et al., 2015)."
- Methods: Could you add more details/description of the fire susceptibility mapping methods used?
Thank you for your valuable feedback. In response to your request for additional details on the fire susceptibility mapping methods used, we have expanded the description of our approach to provide a more comprehensive overview of the techniques and methodologies employed in our research. We believe that these enhancements will address your concerns and provide a clearer understanding of the methods utilized in our study.
- Table 2: See earlier comments on Table 1. Providing more details on how these features are specifically defined (i.e. what are the categorical or continuous variables used) will provide greater context here. This would aid the discussion and may also help to address existing reviewer comments around the need to discuss the exclusion of factors known to affect flame spread e.g. slope. Similarly, an additional description of the fire susceptibility mapping approach may also aid this discussion by explaining the extent to which this study focuses on ignition (fire occurrence).
In section 3.2, We have included the paragraphs you suggested, which provide detailed insights into the factors influencing fire occurrence and spread. The references have been incorporated to support the information provided. These additions aim to enhance the comprehensiveness of the study and address the specific points raised. Thank you for your valuable feedback.
" Height is one of the main factors affecting the size and intensity of fire and is one of the most important spatial layers used in many fields. Accordingly, higher elevations are generally more dangerous than lower elevations when a fire occurs (Rothermel, 1972). In this regard, elevated areas are usually more dangerous than low-lying areas when a fire occurs, especially if the access roads are unpaved or unsuitable for the movement of firefighting teams and their large equipment. If the area in front of the fire is steep, the situation is worse.
The slope of the land is important in the spread of fire and its control, because areas with steep slopes require complex methods of fire control (Estes et al., 2017). Slope controls fire progress, whether it moves uphill or downhill. The direction of the slope affects the amount of solar radiation received by the earth and the amount of soil moisture. In addition, it has an indirect effect on the prevalence of fire because it determines the type and density of vegetation present in a particular location.
Land use is an important factor in determining where wildfires occur, as places with abundant weeds and crops are more vulnerable to fire than others, especially in summer when daytime temperatures are at their maximum. Meanwhile, the possibility of fire in residential areas and forests is less.
Normalized Vegetation Index (NDVI) maps are important maps for analyzing the vegetation cover of each area and identifying the fire vulnerable spots, especially in the presence of seasonal crops, weeds and pastures in each area. are. While the difference of NDVI values in areas with evergreen trees such as oak forests and olive groves is not much. NDVI maps are very different between summer and spring.
Temperature is the most important factor in fire occurrence in the study area. All fires occurred in the summer when the grass had dried and the crops were ready for harvest (MARTÍN and DÍEZ, 2010). No fire has occurred in winter or in low temperature conditions or its occurrence rate is very low. Temperature in the study area can vary from place to place, even in the same season. Wind speed has an effective role in the spread of fire after ignition and may make it impossible to control the spread of fire in some cases. Solar radiation is positively correlated with temperature and associated with fire occurrence (MARTÍN and DÍEZ, 2010), especially in areas dominated by dry grass and fields. Radiation usually varies from place to place due to many factors such as soil texture and moisture content. The topographic moisture index (TWI) is a morphological factor that describes the topography of an area and other related conditions that affect the spatial patterns of soil texture and soil moisture.
Distance from recreation centers is an important factor in fires because many fires are directly or indirectly caused by human activities and activities that allow flames to reach flammable woody biomass. Fires and the number of fires that occur in a given location are positively correlated with population density. Human presence and activity in forest areas increases the possibility of forest fires. As a result, forests are predicted to be always at risk of fire due to nearby human settlements."
- Discussion Lines 12-13: ‘According to previous studies conducted in this specific study area, 17 forest fire conditional factors have been selected for this study.’ Could you discuss this more in the introduction to help explain your choice of the initial 17 factors? The discussion could perhaps also address any study limitations based on factors not considered in the 17 original factors which may merit consideration in future studies.
In response to your suggestion, we have expanded the introduction to provide a more comprehensive discussion regarding the selection of the initial 17 forest fire conditional factors. This includes an explanation of the rationale behind their selection, drawing from previous studies conducted in the specific study area. Furthermore, we have addressed potential limitations based on factors not considered in the original 17, highlighting areas that may merit consideration in future studies. We believe that these additions contribute to a more thorough understanding of our research methodology and its implications.
- Discussion Lines 38-40: Can you clarify if you are referring here to the other 7 factors selected in your study? Or if these are an additional 7 factors that you did not consider? ‘Several studies have identified seven other factors as effective factors in forest fires. (Bjånes et al., 2021; Eskandari et al., 2021; Mohajane et al., 2021; Naderpour et al., 2021; Tavakkoli Piralilou et al., 2022; Valdez et al., 2017).
Thank you for your feedback. In the sentence "In Table 2, one of the outcomes of this study is identifying the distance from power transmission lines as one of eight factors affecting fire occurrence that is less discussed in other studies. Several studies have identified seven other factors as effective factors in forest fires," we are indeed referring to the other seven factors selected in our study, not additional factors that were not considered.
Technical Comments
- Abstract Line 9: ‘and the second on those derived from RFE model’ could be reworded for clarity e.g. ‘and secondly on those derived from the RFE model’.
In response to your suggestion, We have revised the sentence as follows: "The SVM and RF models were applied once on all factors and secondly on those derived from the RFE model as the key factors in FSM."
- Abstract Line 14: ‘and not include unnecessary factors, could be reworded for clarity e.g. ‘and to exclude unnecessary factors’.
Thank you for your feedback, We have revised the sentence as follows: "The assessments demonstrate that leveraging RFE models enhances the FSM results by identifying key factors and excluding unnecessary ones."
- Intro Line 11: This probably requires a full citation ‘According to Copernicus (https://effis.jrc.ec.europa.eu)’
The revised text now includes a citation to the United Nations Environment Programme (2022) report "Spreading like Wildfire – The Rising Threat of Extraordinary Landscape Fires" to support the information provided about the EFFIS - European Forest Fire Information System.
- Intro Lines 52-53: ‘any evaluation if they play a significant role in their selected case study area.’ Typo should be ‘any evaluation of if they play a significant…’
Thank you for pointing out the typo. We have revised the sentence as per your suggestion. The revised sentence now reads: 'The literature review clearly shows that most methodologies employed conditional wildfire criteria without any evaluation of if they play a significant role in their selected case study area.'
- Intro Line 56: Typo ‘accuracies of the resulting FSMs caused’ should be ‘accuracies of the resulting FSMs are caused’
Thank you for pointing out the typo. We have revised the sentence as per your suggestion. The revised sentence now reads: 'While some studies have used several fire conditional factors, it is unclear whether the limited derived accuracies of the resulting FSMs are caused by the model limitations or the adverse impact of some not fully related factors.'
- Study Area Line 1: province does not need to be capitalized.
Thank you for your feedback. We have made the necessary adjustments to the manuscript by removing the capitalization of "province" in the study area section.
- Section 4.4 Line 7 – Missing full stop ‘We also weighed the weak classifier based on the classification effect of the sample set’
Section 4.4 Line 7 – Missing full stop ‘We also weighed the weak classifier based on the classification effect of the sample set’
- Correction of references
We are pleased to inform you that all mentioned references have been thoroughly reviewed and corrected as per your feedback. Thank you for your guidance in ensuring the accuracy and completeness of the reference details.
Citation: https://doi.org/10.5194/egusphere-2022-1294-AC5
-
AC4: 'Reply on RC2', Parham Pahlavani, 05 Dec 2023
Interactive discussion
Status: closed
-
CC1: 'Comment on egusphere-2022-1294', Carolina Ojeda, 13 Jan 2023
General comments: This article presented a study case in Iran in which a GIS-type forest fire hazard model is tested. Its novelty relies on the improvement of Fire Susceptibility Maps (FSM) results, which could help GIS experts to improve future analyses for similar topographical conditions.
Specific comments:
1. The subtitle is a bit crowded: "A mountainous case study area". My suggestion here is "A study case in Iran".
2. In the abstract line 15 and section 3.2 the concept "anthropology/anthropological" should be replaced by "human actions/factors" or "anthropic actions/factors" because anthropology is a discipline.
3. In the introduction lines 40-43 are redundant with the next paragraph ("in recent years"). Also, its main idea could be developed more by the authors, because forest fires have been modeling the landscapes, lives, and infrastructures since humans inhabited the planet, therefore, it is not an issue of "recent years".
4. In the introduction lines 45-46 are contradicting. If "natural processes have historically caused fires in forests" how could humans accelerate it? Also, what is a "firing process" that was accelerated?
5. In the study area lines 114-121 it could be explained more why "this province is known to be one of the most wildfire-prone regions in northern Iran" besides the reference to Adab et al. (2015). Also, the article could be benefited from a more detailed visual description of the topography (e.g. a topographic profile), which is a special feature remarked in the title "A mountainous case study area".
6. In the discussion section, the authors deliver more accurate information about the selected methods which improved the overall quality of the article and its scientific robustness. However, I missed a comparison with other studies doing the same methodologies in other mountain regions from Iran or other parts of the world with similar topography. Maybe the references named in lines 390-395 could be useful for that purpose if they are presented in a comparative table.
Technical corrections: Please be aware of the capital letter in the acronyms along the abstract (e.g., forest fire susceptibility map (FSM)). Also, the legend of figure 1 has a typo (boundaries).
Citation: https://doi.org/10.5194/egusphere-2022-1294-CC1 -
AC1: 'Reply on CC1', Parham Pahlavani, 30 Mar 2023
Dear Reviewer,
We very much appreciate your positive statements regarding our manuscript. You indeed kindly spent significant time on this manuscript and we are grateful for the detailed suggestions. You brought up interesting aspects and we believe that these suggestions and our respective reactions to them will improve the quality of the paper. We did our best to improve the scientific quality of the manuscript significantly. Based on your constructive comments on the initial version and our comprehensive revisions, we are confident that you will find this version now worthwhile to get published. All the revisions are specified with the Blue color in the text.
1) The subtitle is a bit crowded: "A mountainous case study area".To comply with the reviewer’s comment, we changed the subtitle to " A study case in Iran".
2) In the abstract line 15 and section 3.2 the concept "anthropology/anthropological" should be replaced by "human actions/factors" or "anthropic actions/factors" because anthropology is a discipline.This comment was taken into consideration. In this regard, anthropology factors have been changed to human factors.
3) In the introduction lines 40-43 are redundant with the next paragraph ("in recent years"). Also, its main idea could be developed more by the authors, because forest fires have been modeling the landscapes, lives, and infrastructures since humans inhabited the planet, therefore, it is not an issue of "recent years".
To comply with the reviewer’s comment, the paragraph was corrected and its "recent years" was deleted in the revised version of the manuscript.
4) In the introduction lines 45-46 are contradicting. If "natural processes have historically caused fires in forests" how could humans accelerate it? Also, what is a "firing process" that was accelerated?To comply with the reviewer’s comment, the sentence was rewritten as follows:
“Fires in forests have accelerated directly due to the increased human-environmental interactions by igniting and suppressing fires, and indirectly by changing the vegetation structure and composition, as well as destroying the landscapes (Rogers et al., 2020).”
5) In the study area lines 114-121 it could be explained more why "this province is known to be one of the most wildfire-prone regions in northern Iran" besides the reference to Adab et al. (2015). Also, the article could be benefited from a more detailed visual description of the topography (e.g. a topographic profile), which is a special feature remarked in the title "A mountainous case study area".To point out the prevalence of fire in this area, the following sentence was added: “This study experienced several harsh wildfires, which have impacted more than twenty settlements and villages (Gholamnia et al., 2020).”
6) In the discussion section, the authors deliver more accurate information about the selected methods which improved the overall quality of the article and its scientific robustness. However, I missed a comparison with other studies doing the same methodologies in other mountain regions from Iran or other parts of the world with similar topography. Maybe the references named in lines 390-395 could be useful for that purpose if they are presented in a comparative table.If we pay attention to the discussion, we will find that it is explained in the full discussion section that several researchers have investigated factors, but the factor of distance to power lines is also known as an effective factor in this research. Also, the research conducted by Ghorbanzadeh in this study area has been mentioned and compared with the results of the research.
Finally, we appreciate your support and your constructive suggestions. We strongly believe that we have addressed the issues concerning the logical flow of the manuscript and have improved the scientific aspect significantly. We hope that you will find this revised version worthwhile to be published.
Thank you very much again.
The authors
Citation: https://doi.org/10.5194/egusphere-2022-1294-AC1 -
CC2: 'Reply on CC1', Parham Pahlavani, 30 Mar 2023
Dear Reviewer,
We very much appreciate your positive statements regarding our manuscript. You indeed kindly spent significant time on this manuscript and we are grateful for the detailed suggestions. You brought up interesting aspects and we believe that these suggestions and our respective reactions to them will improve the quality of the paper. We did our best to improve the scientific quality of the manuscript significantly. Based on your constructive comments on the initial version and our comprehensive revisions, we are confident that you will find this version now worthwhile to get published. All the revisions are specified with the Blue color in the text.
1) The subtitle is a bit crowded: "A mountainous case study area".To comply with the reviewer’s comment, we changed the subtitle to " A study case in Iran".
2) In the abstract line 15 and section 3.2 the concept "anthropology/anthropological" should be replaced by "human actions/factors" or "anthropic actions/factors" because anthropology is a discipline.This comment was taken into consideration. In this regard, anthropology factors have been changed to human factors.
3) In the introduction lines 40-43 are redundant with the next paragraph ("in recent years"). Also, its main idea could be developed more by the authors, because forest fires have been modeling the landscapes, lives, and infrastructures since humans inhabited the planet, therefore, it is not an issue of "recent years".
To comply with the reviewer’s comment, the paragraph was corrected and its "recent years" was deleted in the revised version of the manuscript.
4) In the introduction lines 45-46 are contradicting. If "natural processes have historically caused fires in forests" how could humans accelerate it? Also, what is a "firing process" that was accelerated?To comply with the reviewer’s comment, the sentence was rewritten as follows:
“Fires in forests have accelerated directly due to the increased human-environmental interactions by igniting and suppressing fires, and indirectly by changing the vegetation structure and composition, as well as destroying the landscapes (Rogers et al., 2020).”
5) In the study area lines 114-121 it could be explained more why "this province is known to be one of the most wildfire-prone regions in northern Iran" besides the reference to Adab et al. (2015). Also, the article could be benefited from a more detailed visual description of the topography (e.g. a topographic profile), which is a special feature remarked in the title "A mountainous case study area".To point out the prevalence of fire in this area, the following sentence was added: “This study experienced several harsh wildfires, which have impacted more than twenty settlements and villages (Gholamnia et al., 2020).”
6) In the discussion section, the authors deliver more accurate information about the selected methods which improved the overall quality of the article and its scientific robustness. However, I missed a comparison with other studies doing the same methodologies in other mountain regions from Iran or other parts of the world with similar topography. Maybe the references named in lines 390-395 could be useful for that purpose if they are presented in a comparative table.If we pay attention to the discussion, we will find that it is explained in the full discussion section that several researchers have investigated factors, but the factor of distance to power lines is also known as an effective factor in this research. Also, the research conducted by Ghorbanzadeh in this study area has been mentioned and compared with the results of the research.
Finally, we appreciate your support and your constructive suggestions. We strongly believe that we have addressed the issues concerning the logical flow of the manuscript and have improved the scientific aspect significantly. We hope that you will find this revised version worthwhile to be published.
Thank you very much again.
The authors
Citation: https://doi.org/10.5194/egusphere-2022-1294-CC2 -
CC6: 'Reply on CC2', Parham Pahlavani, 30 Mar 2023
The comment was uploaded in the form of a supplement: https://egusphere.copernicus.org/preprints/2023/egusphere-2022-1294/egusphere-2022-1294-CC6-supplement.pdf
-
CC6: 'Reply on CC2', Parham Pahlavani, 30 Mar 2023
-
AC1: 'Reply on CC1', Parham Pahlavani, 30 Mar 2023
-
RC1: 'Comment on egusphere-2022-1294', Anonymous Referee #1, 14 Mar 2023
General overview of paper – there is some good work in here, but it reads too much like an thesis rather than a paper, thus inhibiting the communication. For instance – a lot of section 4 could/should be in the introduction, while the current introduction is verbose and not concise enough.
Additioanlly, in fire science slope, for instance, has been identified an important factor in wildfire modelling – however, your study area does not give details of slope or any of the 17 factors you’ve said are important. My inference therefore from your study and figure 7 is that the area is a) not overly sloped – which would be surprising for a mountainous region - or b) the fire areas and non-fire areas are equally sloped.
This then comes to the crux of the paper and its title – you are not modelling wildfire, you are modelling relative wildfire susceptibility in a certain area.
Lines 30-32 – provide reference to support claim.
Lines 33-34 – provide reference or specify that in this paper this is what you are calling a forest fire.
Line 35 – highly combustible trees compared to what?
Paragraph from line 33-42 – tell me why you are telling me this – why is this important.
Paragraph 43-53 – end sentences about life safety is new to para and out of generalised context of fires in Iran – this needs to be changed into two paras, with the latter being about human susceptibility.
Paragraph 54-64 – none of this is wrong, but it is not noteworthy – this is in my view – common knowledge.
Paragraph 64 – 79 – lots of repetition at the start, lots of “authors X did Y” and not enough depth to the review – a generic comment at the end about what is lacking without showing the reader that this is true.
Paragraph 80-104 – too long- consider splitting. As before lots of X did Y, not enough “however,…” there is some, but more needed.
Para 105 – 112 – need to explain why RFE is better than the other methods. Why have you chose this method. You then bring in terms such as adaboost, gradient boosting, random forests, and extra trees without any prior referencing in the text.
Resolution of Figure 1 could be improved. Please show an image from the timeframe being explored e.g., an image of the forest between 2012-2017
Can you explain the difference between a fire point and the polygons that you are using, and how they are used/interact with one another. Were there more than 352 fire points found and only 352 used or are you using all of the points that were found – I am confused as to why you have two different metrics to measure where a fire has been. How big is your fire point – what is the spatial resolution of your point?
How do you know the 17 factors are important – are there important factors that are not included? How has this list been determined or is it from other sources, in which case please reference these.
RFE – 4.1
Who is doing all this selecting/removing of features? Are these features independent of one another, or are they interdependent
Line 180 – cross-validation against what?
Again this comes back to the question about the factors/features of importance – knowing whether they are complete, and whether they are transferable between different geographical locations. This is not clear in the paper.
Line 194 & 207 – majority of votes – who’s voting?
195-201 – I do not see the importance of this part
205 What is a bootstrap sample – reference?
Please make the y axis in figures 3,4,5 and 6 the same so that the variability in each of the modelling approaches is abundantly clear. Do they need to be separate figures, it could be done on a single plot. What is the shading showing on these figures and why is this not discussed?
How are the models scored? What is the range of possible scores? is 0.87 considered acceptable?
Can the factors in table 2 and figure 7 please be in the same order
These are showing the same data – do these need to be duplicated?
Slope is an important factor in wildfire modelling – however, your study area does not give details of slope or any of the 17 factors you’ve said are important. My inference therefore from your study and figre 7 is that the area is not overly sloped – which would be surprising for a mountainous region - or the fire areas and non-fire areas are equally sloped.
This then comes to the crux of the paper and its title – you are not modelling wildfire, you are modelling relative wildfire susceptibility in a certain area.
Section 5.3 explains a statistical analysis of the different methods – it would be good to show what you mean by true and false positives. Tables 3-5 AUC are not described in the equations and not explained what it is – 6 equations 7 columns in the tables. There is no discussion over the merits of each method – so it just feels like noise.
The fire susceptibility maps – do these not just show that where there have been previous fires – these areas are susceptible to fires? There is no discussion of these images in any detail.
The discussion feels like an executive summary of the paper and the conclusions are lacking in conclusion.
Citation: https://doi.org/10.5194/egusphere-2022-1294-RC1 -
AC2: 'Reply on RC1', Parham Pahlavani, 30 Mar 2023
Dear Reviewer,
We very much appreciate your positive statements regarding our manuscript. You indeed kindly spent significant time on this manuscript and we are grateful for the detailed suggestions. You brought up interesting aspects and we believe that these suggestions and our respective reactions to them will improve the quality of the paper. We did our best to improve the scientific quality of the manuscript significantly. Based on your constructive comments on the initial version and our comprehensive revisions, we are confident that you will find this version now worthwhile to get published. All the revisions are specified with the Blue color in the text.
1) A general overview of the paper – there is some good work in here, but it reads too much like a thesis rather than a paper, thus inhibiting communication. For instance – a lot of section 4 could/should be in the introduction, while the current introduction is verbose and not concise enough.According to other comments, modifications have been made in the introduction, which also covers this comment.
2) Additionally, in fire science slope, for instance, has been identified as an important factor in wildfire modeling – however, your study area does not give details of slope or any of the 17 factors you’ve said are important. My inference therefore from your study and figure 7 is that the area is a) not overly sloped – which would be surprising for a mountainous region - or b) the fire areas and non-fire areas are equally slopedWe added this paragraph: "In fire science, the slope factor has been identified as an important factor in fire modeling, but in the case of our study, there are many non-fire points in steep areas, so the models do not recognize this factor as an important factor in the fire forest. However, the direction of slope and height have been identified as important factors."
3) This then comes to the crux of the paper and its title – you are not modeling wildfire, you are modeling relative wildfire susceptibility in a certain area.The title of the article was changed to " How the recursive feature elimination affects the SVM and RF for relative wildfire susceptibility in a certain area? A study case in Iran ".
4) Lines 30-32 – provide reference to support the claim.
Add reference.
5) Lines 33-34 – provide a reference or specify that in this paper this is what you are calling a forest fire.Add reference.
6) Line 35 – highly combustible trees compared to what?Change to sentence to " Fires in forests lead to a lot of environmental destruction due to the presence of combustible vegetation "
7) Paragraph from lines 33-42 – tell me why you are telling me this – why is this important.
We added this sentence " The main goal of modeling forest fires is to reduce the negative effects of fires on humans and the environment as much as possible (Hosseini and Lim, 2022). Also, by determining the areas with the possibility of fire, it leads to better management of natural hazards (Tehrany et al., 2021)."
8) Paragraph 43-53 – end sentences about life safety is new to para and out of the generalized context of fires in Iran – this needs to be changed into two paras, with the latter being about human susceptibility.
Paragraphs 43 to 53 were changed into two paragraphs.
9) Paragraphs 54-64 – none of this is wrong, but it is not noteworthy – this is in my view – common knowledge.
The desired paragraphs were deleted.
10) Paragraphs 64 – 79 – lots of repetition at the start, lots of “authors X did Y” and not enough depth to the review – a generic comment at the end about what is lacking without showing the reader that this is true.
We added these sentences "in their study, the random forests (RFs) model was utilized to link historical fire events to a set of wildfire causative factors to measure the importance of each factor on fire ignition. then employed support vector machines (SVMs), to produce an accurate estimate of wildfire probability across the study area"
We added this sentence " this study utilizes Genetic Algorithms (GA) to obtain the optimal combination of forest fire-related variables and apply data mining methods for constructing a forest fire susceptibility map"
11) Paragraphs 80-104 – too long- consider splitting. As before lots of X did Y, not enough “however,…” there is some, but more needed.
Paragraphs 80-104 were divided into several paragraphs.
12) Para 105 – 112 – need to explain why RFE is better than the other methods. Why have you chosen this method? You then bring in terms such as adaboost, gradient boosting, random forests, and extra trees without any prior referencing in the text.
We added this paragraph " As a greedy way of finding a nested subset of features, RFE was argued to be much more robust to data overfitting than wrapper methods (Zeng et al., 2009). RFE tends to remove redundant and weak features and retains independent features. RFE seeks to improve generalization performance by removing the least important features whose deletion will have the least effect, on training errors (Escanilla et al., 2018)".
We added this paragraph ". Feature selection is accomplished by recursive feature elimination (RFE), As a result of its simplicity and effectiveness, RFE is a popular feature selection algorithm because it can identify the feature in a training dataset that is most relevant to the prediction of the variable."
13) Resolution of Figure 1 could be improved. Please show an image from the timeframe being explored e.g., an image of the forest between 2012-2017.
Image No. 1 was changed and considering that the fire points are related to the reported fire polygons and each reported fire polygon has a date since the fire occurred, a date label was added on the map for the fire points.
14) Can you explain the difference between a fire point and the polygons that you are using, and how they are used/interact with one another? Were there more than 352 fire points found and only 352 used or are you using all of the points that were found – I am confused as to why you have two different metrics to measure where a fire has been. How big is your fire point – what is the spatial resolution of your point?
We added this paragraph: "the fire polygons provided to us by the state wildlife organization of Amol County (SWOAC), were matched and validated with the MODIS fire data, and 352 fire points were found. Although there could be more than 352 fire points, it is not certain about them, but at these 352 fire points, fires have occurred with absolute certainty"
15) How do you know the 17 factors are important – are there important factors that are not included? How has this list been determined or is it from other sources, in which case please reference these.
We added this paragraph: "These factors have been extracted based on the studies that happened in the previous research, especially the studies that happened in this area. By reviewing articles (Ghorbanzadeh et al., 2019; Gigović et al., 2019; Zhang et al., 2019; Eskandari et al., 2021; Gholamnia et al., 2020; Jaafari and Pourghasemi, 2019), these 17 available factors were extracted."
16) Who is doing all this selecting/removing of features? Are these features independent of one another, or are they interdependent
As explained in the article, in this method, by building a model on the entire set of problem variables, it calculates their importance for each variable. In the next step, the least important variable is removed, the model is rebuilt on the other remaining variables, and the importance of each variable is recalculated.
17) Again, this comes back to the question about the factors/features of importance – knowing whether they are complete and whether they are transferable between different geographical locations. This is not clear in the paper.
In conclusion, we added this sentence " It is possible that the factors that are known as important factors in this study case, in another geographical environment, other factors are identified as important factors by this method, on the other hand, these factors that are known in this study case The factors that have been used were the ones that could be accessed, so it can be argued that there are other factors as well, but because they are not accessible, they have not been investigated."
18) Line 194 & 207 – the majority of votes – who’s voting?
where the predictions of individual trees are treated as votes and the prediction of the random forest is determined by the majority of votes.
19) 195-201 – I do not see the importance of this part
Due to the fact that the RFE method is described in these sentences, their presence is mandatory.
20) 205 What is a bootstrap sample – reference?
We added this sentence "The bootstrap sampling method is a resampling method that uses random sampling and bootstrap sample is a smaller sample that is “bootstrapped” from a larger sample (Efron and Tibshirani, 1993)".
21) Please make the y-axis in figures 3,4,5 and 6 the same so that the variability in each of the modeling approaches is abundantly clear. Do they need to be separate figures, it could be done on a single plot. What is the shading showing on these figures and why is this not discussed?
All four graphs are displayed in the same figure to enable comparison.
22) How are the models scored? What is the range of possible scores? is 0.87 considered acceptable?
The score obtained by the model here is the auc criterion. The auc range is between 0 and 1. The AUC values are interpreted as reflecting the following model accuracies: 0.6–0.7 poor, 0.6–0.7 medium, 0.7–0.8 good, 0.8–0.9 very good, and 0.9–1 excellent (Pourghasemi et al., 2017). According to Hong's article (Hong et al., 2018), which considered the value of 0.7 for the AUC criterion as a good performance of the model, also in the article of Jafari and Pourghasemi (Pourghasemi et al., 2020), the AUC criterion equal to 0.8 is considered a very good performance for the model.
23) Can the factors in table 2 and figure 7 please be in the same order
Figure 7, its order was arranged according to table 2.
24) These are showing the same data – do these need to be duplicated?
Due to the large number of features in Table 2, for easy identification of the votes obtained for each feature, Figure 7 is displayed as a graph of the votes obtained.
25) Section 5.3 explains a statistical analysis of the different methods – it would be good to show what you mean by true and false positives. Tables 3-5 AUC is not described in the equations and not explained what it is – 6 equations 7 columns in the tables. There is no discussion over the merits of each method – so it just feels like noise.
Formula AUC was added along with formulas Specificity and Sensitivity.
We added this paragraph: " The AUC criterion, which is one of the most important evaluation criteria for models, indicates that the proportion of fire and non-fire points which are correctly classified. The Recall measure shows how many positive examples in the sample are predicted correctly. The fraction of relevant instances in the retrieved instances. The sensitivity criterion also indicates the percentage of fire points that are correctly classified. On the other hand, the specificity criterion indicates the percentage of non-fire points that are correctly classified."
26) The fire susceptibility maps – do these not just show that where there have been previous fires – these areas are susceptible to fires? There is no discussion of these images in any detail.
In section 5.5 we added this paragraph: " A forest fire susceptibility map depicts areas likely to have forest fire in the future by correlating some of the principal factors that contribute to forest fire with the past distribution. The forest fire susceptibility maps represent a measure of the probability of the occurrence of wildfires for a region based on considered conditioning factors. The natural breaks classification method (available in Arc map 10.8) was used to classify the resulting spatial prediction of wildfire susceptibility maps. This classification method is the most common method for categorizing prediction maps for interpreting values close to each class boundary (e.g., values between “High” and “Very high” susceptibility predictions). The model generates a number between 0 and 1 for each pixel according to its feature vector. Using a reclassification tool in the Spatial Analyst Tools ArcGIS 10.8 software, each final map cell is classified into five classes (very low, low, moderate, high, and very high) representing the forest fire hazard index, with the natural breaks method, all outcomes are divided into five classes."
27) The discussion feels like an executive summary of the paper and the conclusions are lacking in conclusion.
According to other comments, modifications have been made in the discussion and conclusions, which also cover this comment.
These two paragraphs were added in the discussion:
" Pourghasemi et al. (Pourghasemi et al., 2020) have identified the factors of distance from rivers and residential areas, TWI, rainfall, aspect, and temperature as important factors in the Boruta algorithm and these factors have also been identified as important factors in our method. But the factors of use and slope, which are not known as important factors in the scope of our study, are known as influential factors in the scope of their study, and this indicates that in order to make a correct comparison between the methods of feature selection and To determine their performance, they should be tested in different geographical environments."
" In fire science, the slope factor has been identified as an important factor in fire modeling (Hong et al., 2018; Pourghasemi et al., 2020) , But there are also articles that do not consider the slope factor due to the geography of the region (Satir et al., 2016; Kim et al., 2019; Cao et al., 2017). About our study area, there are many non-fire points in steep areas, so the models do not recognize this factor as an important factor in the fire forest . However, the direction of slope and height have been identified as important factors. In the table below, the distribution of fire and non-fire points in the study area can be seen according to the slope classification. As can be inferred from the table, the distribution of fire and non-fire points in steep areas are similar, so the factor could not be recognized as an important fire factor in this study area."
The Table 8 was added.
And this paragraph was added in the conclusion:
"It is possible that the factors that are known as important factors in this study case, in another geographical environment, other factors are identified as important factors by this method, on the other hand, these factors that are known in this study case The factors that have been used were the ones that could be accessed, so it can be argued that there are other factors as well, but because they are not accessible, they have not been investigated"
Finally, we appreciate your support and your constructive suggestions. We strongly believe that we have addressed the issues concerning the logical flow of the manuscript and have improved the scientific aspect significantly. We hope that you will find this revised version worthwhile to be published.
Thank you very much again.
The authors
Citation: https://doi.org/10.5194/egusphere-2022-1294-AC2 -
CC3: 'Reply on RC1', Parham Pahlavani, 30 Mar 2023
Dear Reviewer,
We very much appreciate your positive statements regarding our manuscript. You indeed kindly spent significant time on this manuscript and we are grateful for the detailed suggestions. You brought up interesting aspects and we believe that these suggestions and our respective reactions to them will improve the quality of the paper. We did our best to improve the scientific quality of the manuscript significantly. Based on your constructive comments on the initial version and our comprehensive revisions, we are confident that you will find this version now worthwhile to get published. All the revisions are specified with the Blue color in the text.
1) A general overview of the paper – there is some good work in here, but it reads too much like a thesis rather than a paper, thus inhibiting communication. For instance – a lot of section 4 could/should be in the introduction, while the current introduction is verbose and not concise enough.According to other comments, modifications have been made in the introduction, which also covers this comment.
2) Additionally, in fire science slope, for instance, has been identified as an important factor in wildfire modeling – however, your study area does not give details of slope or any of the 17 factors you’ve said are important. My inference therefore from your study and figure 7 is that the area is a) not overly sloped – which would be surprising for a mountainous region - or b) the fire areas and non-fire areas are equally slopedWe added this paragraph: "In fire science, the slope factor has been identified as an important factor in fire modeling, but in the case of our study, there are many non-fire points in steep areas, so the models do not recognize this factor as an important factor in the fire forest. However, the direction of slope and height have been identified as important factors."
3) This then comes to the crux of the paper and its title – you are not modeling wildfire, you are modeling relative wildfire susceptibility in a certain area.The title of the article was changed to " How the recursive feature elimination affects the SVM and RF for relative wildfire susceptibility in a certain area? A study case in Iran ".
4) Lines 30-32 – provide reference to support the claim.
Add reference.
5) Lines 33-34 – provide a reference or specify that in this paper this is what you are calling a forest fire.Add reference.
6) Line 35 – highly combustible trees compared to what?Change to sentence to " Fires in forests lead to a lot of environmental destruction due to the presence of combustible vegetation "
7) Paragraph from lines 33-42 – tell me why you are telling me this – why is this important.
We added this sentence " The main goal of modeling forest fires is to reduce the negative effects of fires on humans and the environment as much as possible (Hosseini and Lim, 2022). Also, by determining the areas with the possibility of fire, it leads to better management of natural hazards (Tehrany et al., 2021)."
8) Paragraph 43-53 – end sentences about life safety is new to para and out of the generalized context of fires in Iran – this needs to be changed into two paras, with the latter being about human susceptibility.
Paragraphs 43 to 53 were changed into two paragraphs.
9) Paragraphs 54-64 – none of this is wrong, but it is not noteworthy – this is in my view – common knowledge.
The desired paragraphs were deleted.
10) Paragraphs 64 – 79 – lots of repetition at the start, lots of “authors X did Y” and not enough depth to the review – a generic comment at the end about what is lacking without showing the reader that this is true.
We added these sentences "in their study, the random forests (RFs) model was utilized to link historical fire events to a set of wildfire causative factors to measure the importance of each factor on fire ignition. then employed support vector machines (SVMs), to produce an accurate estimate of wildfire probability across the study area"
We added this sentence " this study utilizes Genetic Algorithms (GA) to obtain the optimal combination of forest fire-related variables and apply data mining methods for constructing a forest fire susceptibility map"
11) Paragraphs 80-104 – too long- consider splitting. As before lots of X did Y, not enough “however,…” there is some, but more needed.
Paragraphs 80-104 were divided into several paragraphs.
12) Para 105 – 112 – need to explain why RFE is better than the other methods. Why have you chosen this method? You then bring in terms such as adaboost, gradient boosting, random forests, and extra trees without any prior referencing in the text.
We added this paragraph " As a greedy way of finding nested subset of features, RFE was argued to be much more robust to data overfitting than wrapper methods (Zeng et al., 2009). RFE tends to remove redundant and weak features and retains independent features. RFE seeks to improve generalization performance by removing the least important features whose deletion will have the least effect, on training errors (Escanilla et al., 2018)".
We added this paragraph ". Feature selection is accomplished by recursive feature elimination (RFE), As a result of its simplicity and effectiveness, RFE is a popular feature selection algorithm because it can identify the feature in a training dataset that is most relevant to the prediction of the variable."
13) Resolution of Figure 1 could be improved. Please show an image from the timeframe being explored e.g., an image of the forest between 2012-2017.
Image No. 1 was changed and considering that the fire points are related to the reported fire polygons and each reported fire polygon has a date since the fire occurred, a date label was added on the map for the fire points.
14) Can you explain the difference between a fire point and the polygons that you are using, and how they are used/interact with one another? Were there more than 352 fire points found and only 352 used or are you using all of the points that were found – I am confused as to why you have two different metrics to measure where a fire has been. How big is your fire point – what is the spatial resolution of your point?
We added this paragraph: "the fire polygons provided to us by the state wildlife organization of Amol County (SWOAC), were matched and validated with the MODIS fire data, and 352 fire points were found. Although there could be more than 352 fire points, it is not certain about them, but at these 352 fire points, fires have occurred with absolute certainty"
15) How do you know the 17 factors are important – are there important factors that are not included? How has this list been determined or is it from other sources, in which case please reference these.
We added this paragraph: "These factors have been extracted based on the studies that happened in the previous research, especially the studies that happened in this area. By reviewing articles (Ghorbanzadeh et al., 2019; Gigović et al., 2019; Zhang et al., 2019; Eskandari et al., 2021; Gholamnia et al., 2020; Jaafari and Pourghasemi, 2019), these 17 available factors were extracted."
16) Who is doing all this selecting/removing of features? Are these features independent of one another, or are they interdependent
As explained in the article, in this method, by building a model on the entire set of problem variables, it calculates their importance for each variable. In the next step, the least important variable is removed, the model is rebuilt on the other remaining variables, and the importance of each variable is recalculated.
17) Again, this comes back to the question about the factors/features of importance – knowing whether they are complete and whether they are transferable between different geographical locations. This is not clear in the paper.
In conclusion, we added this sentence " It is possible that the factors that are known as important factors in this study case, in another geographical environment, other factors are identified as important factors by this method, on the other hand, these factors that are known in this study case The factors that have been used were the ones that could be accessed, so it can be argued that there are other factors as well, but because they are not accessible, they have not been investigated."
18) Line 194 & 207 – the majority of votes – who’s voting?
where the predictions of individual trees are treated as votes and the prediction of the random forest is determined by the majority of votes.
19) 195-201 – I do not see the importance of this part
Due to the fact that the RFE method is described in these sentences, their presence is mandatory.
20) 205 What is a bootstrap sample – reference?
We added this sentence "The bootstrap sampling method is a resampling method that uses random sampling and bootstrap sample is a smaller sample that is “bootstrapped” from a larger sample (Efron and Tibshirani, 1993)".
21) Please make the y-axis in figures 3,4,5 and 6 the same so that the variability in each of the modeling approaches is abundantly clear. Do they need to be separate figures, it could be done on a single plot. What is the shading showing on these figures and why is this not discussed?
All four graphs are displayed in the same figure to enable comparison.
22) How are the models scored? What is the range of possible scores? is 0.87 considered acceptable?
The score obtained by the model here is the auc criterion. The auc range is between 0 and 1. The AUC values are interpreted as reflecting the following model accuracies: 0.6–0.7 poor, 0.6–0.7 medium, 0.7–0.8 good, 0.8–0.9 very good, and 0.9–1 excellent (Pourghasemi et al., 2017). According to Hong's article (Hong et al., 2018), which considered the value of 0.7 for the AUC criterion as a good performance of the model, also in the article of Jafari and Pourghasemi (Pourghasemi et al., 2020), the AUC criterion equal to 0.8 is considered a very good performance for the model.
23) Can the factors in table 2 and figure 7 please be in the same order
Figure 7, its order was arranged according to table 2.
24) These are showing the same data – do these need to be duplicated?
Due to the large number of features in Table 2, for easy identification of the votes obtained for each feature, Figure 7 is displayed as a graph of the votes obtained.
25) Section 5.3 explains a statistical analysis of the different methods – it would be good to show what you mean by true and false positives. Tables 3-5 AUC is not described in the equations and not explained what it is – 6 equations 7 columns in the tables. There is no discussion over the merits of each method – so it just feels like noise.
Formula AUC was added along with formulas Specificity and Sensitivity.
We added this paragraph: " The AUC criterion, which is one of the most important evaluation criteria for models, indicates that the proportion of fire and non-fire points which are correctly classified. The Recall measure shows how many positive examples in the sample are predicted correctly. The fraction of relevant instances in the retrieved instances. The sensitivity criterion also indicates the percentage of fire points that are correctly classified. On the other hand, the specificity criterion indicates the percentage of non-fire points that are correctly classified."
26) The fire susceptibility maps – do these not just show that where there have been previous fires – these areas are susceptible to fires? There is no discussion of these images in any detail.
In section 5.5 we added this paragraph: " A forest fire susceptibility map depicts areas likely to have forest fire in the future by correlating some of the principal factors that contribute to forest fire with the past distribution. The forest fire susceptibility maps represent a measure of the probability of the occurrence of wildfires for a region based on considered conditioning factors. The natural breaks classification method (available in Arc map 10.8) was used to classify the resulting spatial prediction of wildfire susceptibility maps. This classification method is the most common method for categorizing prediction maps for interpreting values close to each class boundary (e.g., values between “High” and “Very high” susceptibility predictions). The model generates a number between 0 and 1 for each pixel according to its feature vector. Using a reclassification tool in the Spatial Analyst Tools ArcGIS 10.8 software, each final map cell is classified into five classes (very low, low, moderate, high, and very high) representing the forest fire hazard index, with the natural breaks method, all outcomes are divided into five classes."
27) The discussion feels like an executive summary of the paper and the conclusions are lacking in conclusion.
According to other comments, modifications have been made in the discussion and conclusions, which also cover this comment.
These two paragraphs were added in the discussion:
" Pourghasemi et al. (Pourghasemi et al., 2020) have identified the factors of distance from rivers and residential areas, TWI, rainfall, aspect, and temperature as important factors in the Boruta algorithm and these factors have also been identified as important factors in our method. But the factors of use and slope, which are not known as important factors in the scope of our study, are known as influential factors in the scope of their study, and this indicates that in order to make a correct comparison between the methods of feature selection and To determine their performance, they should be tested in different geographical environments."
" In fire science, the slope factor has been identified as an important factor in fire modeling (Hong et al., 2018; Pourghasemi et al., 2020) , But there are also articles that do not consider the slope factor due to the geography of the region (Satir et al., 2016; Kim et al., 2019; Cao et al., 2017). About our study area, there are many non-fire points in steep areas, so the models do not recognize this factor as an important factor in the fire forest . However, the direction of slope and height have been identified as important factors. In the table below, the distribution of fire and non-fire points in the study area can be seen according to the slope classification. As can be inferred from the table, the distribution of fire and non-fire points in steep areas are similar, so the factor could not be recognized as an important fire factor in this study area."
The Table 8 was added.
And this paragraph was added in the conclusion:
"It is possible that the factors that are known as important factors in this study case, in another geographical environment, other factors are identified as important factors by this method, on the other hand, these factors that are known in this study case The factors that have been used were the ones that could be accessed, so it can be argued that there are other factors as well, but because they are not accessible, they have not been investigated"
Finally, we appreciate your support and your constructive suggestions. We strongly believe that we have addressed the issues concerning the logical flow of the manuscript and have improved the scientific aspect significantly. We hope that you will find this revised version worthwhile to be published.
Thank you very much again.
The authors
Citation: https://doi.org/10.5194/egusphere-2022-1294-CC3 -
CC4: 'Reply on RC1', Parham Pahlavani, 30 Mar 2023
Dear Reviewer,
We very much appreciate your positive statements regarding our manuscript. You indeed kindly spent significant time on this manuscript and we are grateful for the detailed suggestions. You brought up interesting aspects and we believe that these suggestions and our respective reactions to them will improve the quality of the paper. We did our best to improve the scientific quality of the manuscript significantly. Based on your constructive comments on the initial version and our comprehensive revisions, we are confident that you will find this version now worthwhile to get published. All the revisions are specified with the Blue color in the text.
1) A general overview of the paper – there is some good work in here, but it reads too much like a thesis rather than a paper, thus inhibiting communication. For instance – a lot of section 4 could/should be in the introduction, while the current introduction is verbose and not concise enough.According to other comments, modifications have been made in the introduction, which also covers this comment.
2) Additionally, in fire science slope, for instance, has been identified as an important factor in wildfire modeling – however, your study area does not give details of slope or any of the 17 factors you’ve said are important. My inference therefore from your study and figure 7 is that the area is a) not overly sloped – which would be surprising for a mountainous region - or b) the fire areas and non-fire areas are equally slopedWe added this paragraph: "In fire science, the slope factor has been identified as an important factor in fire modeling, but in the case of our study, there are many non-fire points in steep areas, so the models do not recognize this factor as an important factor in the fire forest. However, the direction of slope and height have been identified as important factors."
3) This then comes to the crux of the paper and its title – you are not modeling wildfire, you are modeling relative wildfire susceptibility in a certain area.The title of the article was changed to " How the recursive feature elimination affects the SVM and RF for relative wildfire susceptibility in a certain area? A study case in Iran ".
4) Lines 30-32 – provide reference to support the claim.
Add reference.
5) Lines 33-34 – provide a reference or specify that in this paper this is what you are calling a forest fire.Add reference.
6) Line 35 – highly combustible trees compared to what?Change to sentence to " Fires in forests lead to a lot of environmental destruction due to the presence of combustible vegetation "
7) Paragraph from lines 33-42 – tell me why you are telling me this – why is this important.
We added this sentence " The main goal of modeling forest fires is to reduce the negative effects of fires on humans and the environment as much as possible (Hosseini and Lim, 2022). Also, by determining the areas with the possibility of fire, it leads to better management of natural hazards (Tehrany et al., 2021)."
8) Paragraph 43-53 – end sentences about life safety is new to para and out of the generalized context of fires in Iran – this needs to be changed into two paras, with the latter being about human susceptibility.
Paragraphs 43 to 53 were changed into two paragraphs.
9) Paragraphs 54-64 – none of this is wrong, but it is not noteworthy – this is in my view – common knowledge.
The desired paragraphs were deleted.
10) Paragraphs 64 – 79 – lots of repetition at the start, lots of “authors X did Y” and not enough depth to the review – a generic comment at the end about what is lacking without showing the reader that this is true.
We added these sentences "in their study, the random forests (RFs) model was utilized to link historical fire events to a set of wildfire causative factors to measure the importance of each factor on fire ignition. then employed support vector machines (SVMs), to produce an accurate estimate of wildfire probability across the study area"
We added this sentence " this study utilizes Genetic Algorithms (GA) to obtain the optimal combination of forest fire-related variables and apply data mining methods for constructing a forest fire susceptibility map"
11) Paragraphs 80-104 – too long- consider splitting. As before lots of X did Y, not enough “however,…” there is some, but more needed.
Paragraphs 80-104 were divided into several paragraphs.
12) Para 105 – 112 – need to explain why RFE is better than the other methods. Why have you chosen this method? You then bring in terms such as adaboost, gradient boosting, random forests, and extra trees without any prior referencing in the text.
We added this paragraph " As a greedy way of finding nested subset of features, RFE was argued to be much more robust to data overfitting than wrapper methods (Zeng et al., 2009). RFE tends to remove redundant and weak features and retains independent features. RFE seeks to improve generalization performance by removing the least important features whose deletion will have the least effect, on training errors (Escanilla et al., 2018)".
We added this paragraph ". Feature selection is accomplished by recursive feature elimination (RFE), As a result of its simplicity and effectiveness, RFE is a popular feature selection algorithm because it can identify the feature in a training dataset that is most relevant to the prediction of the variable."
13) Resolution of Figure 1 could be improved. Please show an image from the timeframe being explored e.g., an image of the forest between 2012-2017.
Image No. 1 was changed and considering that the fire points are related to the reported fire polygons and each reported fire polygon has a date since the fire occurred, a date label was added on the map for the fire points.
14) Can you explain the difference between a fire point and the polygons that you are using, and how they are used/interact with one another? Were there more than 352 fire points found and only 352 used or are you using all of the points that were found – I am confused as to why you have two different metrics to measure where a fire has been. How big is your fire point – what is the spatial resolution of your point?
We added this paragraph: "the fire polygons provided to us by the state wildlife organization of Amol County (SWOAC), were matched and validated with the MODIS fire data, and 352 fire points were found. Although there could be more than 352 fire points, it is not certain about them, but at these 352 fire points, fires have occurred with absolute certainty"
15) How do you know the 17 factors are important – are there important factors that are not included? How has this list been determined or is it from other sources, in which case please reference these.
We added this paragraph: "These factors have been extracted based on the studies that happened in the previous research, especially the studies that happened in this area. By reviewing articles (Ghorbanzadeh et al., 2019; Gigović et al., 2019; Zhang et al., 2019; Eskandari et al., 2021; Gholamnia et al., 2020; Jaafari and Pourghasemi, 2019), these 17 available factors were extracted."
16) Who is doing all this selecting/removing of features? Are these features independent of one another, or are they interdependent
As explained in the article, in this method, by building a model on the entire set of problem variables, it calculates their importance for each variable. In the next step, the least important variable is removed, the model is rebuilt on the other remaining variables, and the importance of each variable is recalculated.
17) Again, this comes back to the question about the factors/features of importance – knowing whether they are complete and whether they are transferable between different geographical locations. This is not clear in the paper.
In conclusion, we added this sentence " It is possible that the factors that are known as important factors in this study case, in another geographical environment, other factors are identified as important factors by this method, on the other hand, these factors that are known in this study case The factors that have been used were the ones that could be accessed, so it can be argued that there are other factors as well, but because they are not accessible, they have not been investigated."
18) Line 194 & 207 – the majority of votes – who’s voting?
where the predictions of individual trees are treated as votes and the prediction of the random forest is determined by the majority of votes.
19) 195-201 – I do not see the importance of this part
Due to the fact that the RFE method is described in these sentences, their presence is mandatory.
20) 205 What is a bootstrap sample – reference?
We added this sentence "The bootstrap sampling method is a resampling method that uses random sampling and bootstrap sample is a smaller sample that is “bootstrapped” from a larger sample (Efron and Tibshirani, 1993)".
21) Please make the y-axis in figures 3,4,5 and 6 the same so that the variability in each of the modeling approaches is abundantly clear. Do they need to be separate figures, it could be done on a single plot. What is the shading showing on these figures and why is this not discussed?
All four graphs are displayed in the same figure to enable comparison.
22) How are the models scored? What is the range of possible scores? is 0.87 considered acceptable?
The score obtained by the model here is the auc criterion. The auc range is between 0 and 1. The AUC values are interpreted as reflecting the following model accuracies: 0.6–0.7 poor, 0.6–0.7 medium, 0.7–0.8 good, 0.8–0.9 very good, and 0.9–1 excellent (Pourghasemi et al., 2017). According to Hong's article (Hong et al., 2018), which considered the value of 0.7 for the AUC criterion as a good performance of the model, also in the article of Jafari and Pourghasemi (Pourghasemi et al., 2020), the AUC criterion equal to 0.8 is considered a very good performance for the model.
23) Can the factors in table 2 and figure 7 please be in the same order
Figure 7, its order was arranged according to table 2.
24) These are showing the same data – do these need to be duplicated?
Due to the large number of features in Table 2, for easy identification of the votes obtained for each feature, Figure 7 is displayed as a graph of the votes obtained.
25) Section 5.3 explains a statistical analysis of the different methods – it would be good to show what you mean by true and false positives. Tables 3-5 AUC is not described in the equations and not explained what it is – 6 equations 7 columns in the tables. There is no discussion over the merits of each method – so it just feels like noise.
Formula AUC was added along with formulas Specificity and Sensitivity.
We added this paragraph: " The AUC criterion, which is one of the most important evaluation criteria for models, indicates that the proportion of fire and non-fire points which are correctly classified. The Recall measure shows how many positive examples in the sample are predicted correctly. The fraction of relevant instances in the retrieved instances. The sensitivity criterion also indicates the percentage of fire points that are correctly classified. On the other hand, the specificity criterion indicates the percentage of non-fire points that are correctly classified."
26) The fire susceptibility maps – do these not just show that where there have been previous fires – these areas are susceptible to fires? There is no discussion of these images in any detail.
In section 5.5 we added this paragraph: " A forest fire susceptibility map depicts areas likely to have forest fire in the future by correlating some of the principal factors that contribute to forest fire with the past distribution. The forest fire susceptibility maps represent a measure of the probability of the occurrence of wildfires for a region based on considered conditioning factors. The natural breaks classification method (available in Arc map 10.8) was used to classify the resulting spatial prediction of wildfire susceptibility maps. This classification method is the most common method for categorizing prediction maps for interpreting values close to each class boundary (e.g., values between “High” and “Very high” susceptibility predictions). The model generates a number between 0 and 1 for each pixel according to its feature vector. Using a reclassification tool in the Spatial Analyst Tools ArcGIS 10.8 software, each final map cell is classified into five classes (very low, low, moderate, high, and very high) representing the forest fire hazard index, with the natural breaks method, all outcomes are divided into five classes."
27) The discussion feels like an executive summary of the paper and the conclusions are lacking in conclusion.
According to other comments, modifications have been made in the discussion and conclusions, which also cover this comment.
These two paragraphs were added in the discussion:
" Pourghasemi et al. (Pourghasemi et al., 2020) have identified the factors of distance from rivers and residential areas, TWI, rainfall, aspect, and temperature as important factors in the Boruta algorithm and these factors have also been identified as important factors in our method. But the factors of use and slope, which are not known as important factors in the scope of our study, are known as influential factors in the scope of their study, and this indicates that in order to make a correct comparison between the methods of feature selection and To determine their performance, they should be tested in different geographical environments."
" In fire science, the slope factor has been identified as an important factor in fire modeling (Hong et al., 2018; Pourghasemi et al., 2020) , But there are also articles that do not consider the slope factor due to the geography of the region (Satir et al., 2016; Kim et al., 2019; Cao et al., 2017). About our study area, there are many non-fire points in steep areas, so the models do not recognize this factor as an important factor in the fire forest . However, the direction of slope and height have been identified as important factors. In the table below, the distribution of fire and non-fire points in the study area can be seen according to the slope classification. As can be inferred from the table, the distribution of fire and non-fire points in steep areas are similar, so the factor could not be recognized as an important fire factor in this study area."
The Table 8 was added.
And this paragraph was added in the conclusion:
"It is possible that the factors that are known as important factors in this study case, in another geographical environment, other factors are identified as important factors by this method, on the other hand, these factors that are known in this study case The factors that have been used were the ones that could be accessed, so it can be argued that there are other factors as well, but because they are not accessible, they have not been investigated"
Finally, we appreciate your support and your constructive suggestions. We strongly believe that we have addressed the issues concerning the logical flow of the manuscript and have improved the scientific aspect significantly. We hope that you will find this revised version worthwhile to be published.
Thank you very much again.
The authors
Citation: https://doi.org/10.5194/egusphere-2022-1294-CC4 -
CC5: 'Reply on CC4', Parham Pahlavani, 30 Mar 2023
The comment was uploaded in the form of a supplement: https://egusphere.copernicus.org/preprints/2023/egusphere-2022-1294/egusphere-2022-1294-CC5-supplement.pdf
-
CC5: 'Reply on CC4', Parham Pahlavani, 30 Mar 2023
-
AC2: 'Reply on RC1', Parham Pahlavani, 30 Mar 2023
-
CC7: 'Comment on egusphere-2022-1294', F. Hosseinali, 01 Jun 2023
I encountered a question when I read your article: How did you assess the independence of input factors such as vegetation, height, etc?
Citation: https://doi.org/10.5194/egusphere-2022-1294-CC7 -
CC8: 'Reply on CC7', Parham Pahlavani, 03 Jun 2023
The selected factors have been based on articles conducted in this area; therefore, their independence has been disregarded. However, the article acknowledges that filter methods solely assess the dependency of factors and do not consider the combination of independent and dependent factors. As a result, the utilization of recursive feature elimination is deemed reasonable. This method enables the attainment of the optimal combination of independent and dependent factors, thereby maximizing the improvement of the problem. Please refer to the paragraph starting with line 95 for more information:
"These methods only compare the correlation between factors, and this causes the impact of several characteristics to be ignored by putting together the occurrence of fire. However, the wrapper methods cover this defect and consider the combination of features as effective features in the problem. The wrapper method is also called the greedy search algorithm because this method scans all possible combinations of features before selecting the one that produces the best ML algorithm performance"
Citation: https://doi.org/10.5194/egusphere-2022-1294-CC8 -
AC3: 'Reply on CC7', Parham Pahlavani, 03 Jun 2023
The selected factors have been based on articles conducted in this area; therefore, their independence has been disregarded. However, the article acknowledges that filter methods solely assess the dependency of factors and do not consider the combination of independent and dependent factors. As a result, the utilization of recursive feature elimination is deemed reasonable. This method enables the attainment of the optimal combination of independent and dependent factors, thereby maximizing the improvement of the problem. Please refer to the paragraph starting with line 95 for more information:
"These methods only compare the correlation between factors, and this causes the impact of several characteristics to be ignored by putting together the occurrence of fire. However, the wrapper methods cover this defect and consider the combination of features as effective features in the problem. The wrapper method is also called the greedy search algorithm because this method scans all possible combinations of features before selecting the one that produces the best ML algorithm performance"
Citation: https://doi.org/10.5194/egusphere-2022-1294-AC3
-
CC8: 'Reply on CC7', Parham Pahlavani, 03 Jun 2023
-
RC2: 'Comment on egusphere-2022-1294', Anonymous Referee #2, 04 Nov 2023
General Comments
This study describes a method for selecting relevant factors for inclusion in fire susceptibility mapping aided by various analytical and machine learning approaches. The identified relevant factors are presented for each method along with consideration of the overall accuracy including for models with various numbers of factors.
I wonder if you could provide more details about the actual fire susceptibility mapping approach used thereby also providing greater context for the results presented in Section 5.1. This, along with greater description of the selection process for the 17 variables (and more detail on how these are defined and which variables are used) would aid understanding of the results presented and particularly of the factors excluded. This interpretation is presently quite difficult without detail on the mapping approach and particularly how each factor has been charactersied. Strengthening this I believe would increase further the general applicability and insights from this work.
Overall I believe this study provides a useful contribution however presently is limited by a lack of description of the susceptibility mapping approach and particularly sufficient description of the initial selection of the 17 factors and description of how each factor is measured/defined. Presently, this makes it difficult to interpret the study and it's results.
Specific Comments
I agree with previous comments that it should be clarified from the outset (and in the title) that it is forest fire susceptibility that is being modeled rather than the wildfire itself (i.e. behaviour, spread etc.).
How were the 17 factors identified (i.e. what process was involved). Is it worth separating out those that apply to ignition (‘triggering’) vs. spreading or both. Subsequently, RFE is used to select features from these initial 17 but the initial assessment and selection of a ‘longlist’ of factors would seem to be a very important part of any feature selection process to prevent the risk of optimizing for the wrong set of factors.
Abstract Lines 11-12: Could you clarify what the difference between accuracy (in both uses below is) ‘Different metrics were used to measure accuracy, including recall, precision, F1, accuracy, the area under the curve (AUC), Matthews correlation coefficient (MCC), and Kappa’. Perhaps by defining accuracy in the subsequent list? This will also help the interpretation of your overall conclusions presented in the final lines of the abstract ‘The greatest improvement is for SVM, with more than 10.97% and 8.61% in the accuracy and AUC metrics, respectively.’
Intro: The early sections of the introduction could perhaps benefit from a more specific selection of cited references, particularly where the effects of forest fires are discussed. For example, in several cases, it may be worth referring directly to one of the studies cited in the actual source cited. Additionally, a brief discussion of factors known to influence fire susceptibility (aided by the existing literature) may help the discussion of why the initial 17 factors were selected, and subsequently aid the discussion of excluded and selected factors.
Intro Line 2: Could a more relevant study perhaps be cited here? For example, one of the studies cited in Pourtaghi et al., 2016 in which the ecosystem services and carbon balance of forests are considered?
Intro Lines 4-6: ‘Therefore, most forest fires, whether natural or induced by humans, cause many negative ecological, social, and economic impacts on forest restoration’ Can this be reworded to allow for or acknowledge the increasingly important role of prescribed fire in many regions and the potential benefits. And similarly the beneficial historical role of fire in many regions. Perhaps rewording to ‘forest fires, whether natural or induced by humans, can cause many negative..’ Or this could be moved to appear after your definition of a forest fire (a citation for this definition could also be added if applicable).
Intro Lines 7-8: As above it would be good to acknowledge that ‘Fires in forests can lead to significant environmental damage’ rather than ‘Fires in forests lead to a lot of environmental destruction due to the presence of highly combustible trees’ as this is not necessarily always the case.
Intro Lines 25-26: Can you clarify what is meant by ‘It is important to take precautions and predict fire facilities in fire-prone areas to prevent forest fires.’. Is this referring to firefighting resources in a given area? Are these efforts actually targeted towards preventing forest fires (i.e. preventing ignition) or reducing risk/hazard mapping etc.?
Intro Lines 68-70: Could you clarify what is meant by ‘and this causes the impact of several characteristics to be ignored by putting together the occurrence of fire.’
Section 3.2 Line 8: Citation required for Aster Dem.
Section 3.2 Line 9: Can you clarify what is meant by wind effect? What is the actual continuous variable considered here?
Section 3.2, Table 1: In this table (or in an appendix?) could you provide more details on each of these factors? For example, what is the specific variable considered? So for wind effect is this for example max wind speed at a given height, average 10m AGL wind speed, gusting speed etc? For categorical variables could you present the different categories considered?
Methods: Could you add more details/description of the fire susceptibility mapping methods used?
Methods Line 1: The process involved in step 1 (‘identifying the forest fire factors associated with the study area’) could benefit from additional discussion.
Table 2: See earlier comments on Table 1. Providing more details on how these features are specifically defined (i.e. what are the categorical or continuous variables used) will provide greater context here. This would aid the discussion and may also help to address existing reviewer comments around the need to discuss the exclusion of factors known to affect flame spread e.g. slope. Similarly, an additional description of the fire susceptibility mapping approach may also aid this discussion by explaining the extent to which this study focuses on ignition (fire occurrence).
Discussion Lines 12-13: ‘According to previous studies conducted in this specific study area, 17 forest fire conditional factors have been selected for this study.’ Could you discuss this more in the introduction to help explain your choice of the initial 17 factors? The discussion could perhaps also address any study limitations based on factors not considered in the 17 original factors which may merit consideration in future studies.
Discussion Lines 38-40: Can you clarify if you are referring here to the other 7 factors selected in your study? Or if these are an additional 7 factors that you did not consider? ‘Several studies have identified seven other factors as effective factors in forest fires. (Bjånes et al., 2021; Eskandari et al., 2021; Mohajane et al., 2021; Naderpour et al., 2021; Tavakkoli Piralilou et al., 2022; Valdez et al., 2017).
Technical Comments
Abstract Line 9: ‘and the second on those derived from RFE model’ could be reworded for clarity e.g. ‘and secondly on those derived from the RFE model’.
Abstract Line 14: ‘and not include unnecessary factors, could be reworded for clarity e.g. ‘and to exclude unnecessary factors’.
Intro Line 11: This probably requires a full citation ‘According to Copernicus (https://effis.jrc.ec.europa.eu)’
Intro Line 28: ‘Contribute to the fire's susceptibility.’ Can you revisit the wording here? Maybe this should be ‘contribute to fire susceptibility’. (As it’s not the fire that is susceptible to something else but the susceptibility to fire that is being considered).
Intro Lines 52-53: ‘any evaluation if they play a significant role in their selected case study area.’ Typo should be ‘ any evaluation of if they play a significant…’
Intro Line 56: Typo ‘accuracies of the resulting FSMs caused’ should be ‘accuracies of the resulting FSMs are caused’
Study Area Line 1: province does not need to be capitalised.
Section 4.4 Line 7 – Missing full stop ‘We also weighed the weak classifier based on the classification effect of the sample set’
Issue with reference ‘Breiman, L.: [No title found], Machine Learning, 45, 5–32, https://doi.org/10.1023/A:1010933404324, 2001’
Reference details require correction ‘Bruinsma, J. (Ed.): World Agriculture: Towards 2015/2030, 0 ed., Routledge, https://doi.org/10.4324/9781315083858, 2017.’
Error in reference: Guyon, I., Weston, J., Barnhill, S., and Vapnik, V.: [No title found], Machine Learning, 46, 389–422, 470 https://doi.org/10.1023/A:1012487302797, 2002.
Reference details missing: Jahdi, R., Salis, M., Darvishsefat, A. A., Alcasena Urdiroz, F. J., Etemad, V., Mostafavi, M. A., Lozano, O. M., and Spano, D.: Calibration of FARSITE fire area simulator in Iranian northern forests, Other Hazards (e.g., Glacialand Snow Hazards, Karst, Wildfires Hazards, and Medical Geo-Hazards), https://doi.org/10.5194/nhessd-2-6201-2014, 2014.
Reference details missing: Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Müller, A., Nothman, J., Louppe, G., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., and Duchesnay, É.: Scikit-learn: Machine Learning in Python, https://doi.org/10.48550/ARXIV.1201.0490, 2012.
Citation: https://doi.org/10.5194/egusphere-2022-1294-RC2 -
AC4: 'Reply on RC2', Parham Pahlavani, 05 Dec 2023
Dear Reviewer,
I would like to express my sincere gratitude for the time and effort you dedicated to reviewing my manuscript. Your insightful comments and constructive feedback have significantly contributed to the improvement of the paper. I am thankful for the thoughtfulness of your review.
I am pleased to inform you that I have carefully addressed each of the comments and suggestions you provided. Your input has been invaluable in enhancing the quality and clarity of the manuscript. I believe that the revisions made have strengthened the overall content and presentation of the paper.
Once again, I extend my appreciation for your valuable contribution to this process. Your expertise and attention to detail have been instrumental in refining the manuscript, and I am truly grateful for your support.
Thank you for your time and consideration.
Sincerely,
Authors
- I agree with previous comments that it should be clarified from the outset (and in the title) that it is forest fire susceptibility that is being modeled rather than the wildfire itself (i.e. behavior, spread etc.).
Thank you for your valuable feedback. We have revised the title of the paper to better reflect the focus of our study. The new title, "Modeling Relative Wildfire Susceptibility in a Specific Area: A Study of Recursive Feature Elimination's Impact on SVM and RF—A Case Study in Iran," aims to clearly convey that our study is centered on modeling relative wildfire susceptibility and the impact of recursive feature elimination on SVM and RF in a specific area. We believe this revision effectively addresses your concern about clarifying the modeled factors in the title. We appreciate your input and hope that this change aligns with your expectations.
- How were the 17 factors identified (i.e. what process was involved). Is it worth separating out those that apply to ignition (‘triggering’) vs. spreading or both. Subsequently, RFE is used to select features from these initial 17 but the initial assessment and selection of a ‘longlist’ of factors would seem to be a very important part of any feature selection process to prevent the risk of optimizing for the wrong set of factors.
Thank you for your insightful comments and suggestions. We have carefully reviewed your feedback and have made the necessary revisions to address your concerns. The 17 factors were identified through a comprehensive review of existing literature and empirical studies in the field. These factors were selected based on their documented relevance to forest fire behavior and susceptibility. While the initial identification of these factors was not explicitly categorized into those that apply to ignition versus spreading, the subsequent use of Recursive Feature Elimination (RFE) allowed for the selection of the most influential factors for modeling. The RFE process involved iteratively fitting the model and identifying the most relevant features, thereby addressing the concern of optimizing for the wrong set of factors. This iterative approach ensured that the final set of features used in the analysis was well-suited for the specific objectives of the study, mitigating the risk of suboptimal feature selection. Additionally, the consideration of factors that specifically apply to ignition versus spreading could be a valuable avenue for further research, potentially enhancing the precision and applicability of the model. This distinction may offer insights into the distinct mechanisms driving the initiation and propagation of forest fires, thereby contributing to a more nuanced understanding of fire behavior and risk assessment. In summary, while the initial assessment and selection of the factors were crucial, the subsequent application of RFE provided a robust mechanism for refining the feature set and mitigating the risk of suboptimal feature selection. Further exploration of factors related to ignition and spreading could offer valuable insights for future research in this domain.
- Abstract Lines 11-12: Could you clarify what the difference between accuracy (in both uses below is) ‘Different metrics were used to measure accuracy, including recall, precision, F1, accuracy, the area under the curve (AUC), Matthews correlation coefficient (MCC), and Kappa’. Perhaps by defining accuracy in the subsequent list? This will also help the interpretation of your overall conclusions presented in the final lines of the abstract ‘The greatest improvement is for SVM, with more than 10.97% and 8.61% in the accuracy and AUC metrics, respectively.’
We have revised the sentence as per your suggestion. The updated version now reads: "Various metrics, including recall, precision, F1 score, accuracy, area under the curve (AUC), Matthews correlation coefficient (MCC), and Kappa, were employed to measure the performance of the models. The assessments demonstrate that leveraging RFE models enhances the FSM results by identifying key factors and excluding unnecessary ones. Notably, the SVM model exhibits significant improvement, achieving an increase of over 10.97% in accuracy and 8.61% in AUC metrics. This improvement underscores the effectiveness of the RFE approach in enhancing the predictive performance of the SVM model." We believe this modification aligns with your feedback and provides a clearer description of the assessment process and its implications. Thank you for your input, and we hope this change meets your expectations.
- Intro: The early sections of the introduction could perhaps benefit from a more specific selection of cited references, particularly where the effects of forest fires are discussed. For example, in several cases, it may be worth referring directly to one of the studies cited in the actual source cited. Additionally, a brief discussion of factors known to influence fire susceptibility (aided by the existing literature) may help the discussion of why the initial 17 factors were selected, and subsequently aid the discussion of excluded and selected factors.
In response to your suggestion to provide more specific references, especially when discussing the effects of forest fires and to discuss factors known to influence fire susceptibility based on existing literature, we have made the following changes:
In paragraph 55, we have added the following sentences to address the specific selection of cited references and to discuss factors known to influence fire susceptibility based on existing literature:
"Related topographic factors are crucial in forest fire susceptibility, widely used for forest fire susceptibility mapping (Kolden and Abatzoglou, 2018; Lautenberger, 2017). For example, the slope factor is essential due to its impact on fire spread, with steeper slopes leading to faster fire propagation (Ghorbanzadeh et al., 2018). Additionally, the difference in temperature and moisture between north- and south-facing slopes contributes to a higher risk of forest fires on south-facing slopes (Sayad et al., 2019). Altitude also plays a significant role, with higher moisture levels at greater altitudes (Ganteaume et al., 2013). The wind effect factor encompasses the degree of wind direction, wind speed, and altitude layer (Pourtaghi et al., 2015). Human-made factors include various distance measures, classified based on their relevance to forest fires, human activity radius, literature, and expert insights (Pourghasemi et al., 2016)."
- Intro Line 2: Could a more relevant study perhaps be cited here? For example, one of the studies cited in Pourtaghi et al., 2016 in which the ecosystem services and carbon balance of forests are considered?
In response to your comment regarding the need for a more relevant study to be cited in Intro Line 2, we have made the following changes:
We have added two additional references to support the discussion on ecosystem services and carbon balance of forests. The references added are as follows:
Manisalidis, I., Stavropoulou, E., Stavropoulos, A., and Bezirtzoglou, E.: Environmental and Health Impacts of Air Pollution: A Review, Front. Public Health, 8, 14.
Badea, O.: Climate Change and Air Pollution Effect on Forest Ecosystems, Forests, 12, 1642, https://doi.org/10.3390/f12121642, 2021
- Intro Lines 4-6: ‘Therefore, most forest fires, whether natural or induced by humans, cause many negative ecological, social, and economic impacts on forest restoration’ Can this be reworded to allow for or acknowledge the increasingly important role of prescribed fire in many regions and the potential benefits. And similarly the beneficial historical role of fire in many regions. Perhaps rewording to ‘forest fires, whether natural or induced by humans, can cause many negative..’ Or this could be moved to appear after your definition of a forest fire (a citation for this definition could also be added if applicable).
We have revised the specified section as per your suggestion. The revised content now appears after the definition of a forest fire. The revised section reads as follows: "Forest fires, whether natural or induced by humans, can have significant ecological, social, and economic impacts on forest restoration. However, it is important to acknowledge the increasingly important role of prescribed fire in many regions and the potential benefits it can bring. Similarly, historical fire regimes have played a beneficial role in many regions. Therefore, it is essential to consider the potential positive impacts of controlled or prescribed fires alongside the negative impacts of forest fires."
- Intro Lines 7-8: As above it would be good to acknowledge that ‘Fires in forests can lead to significant environmental damage’ rather than ‘Fires in forests lead to a lot of environmental destruction due to the presence of highly combustible trees’ as this is not necessarily always the case.
We have revised the sentence as per your suggestion. The revised sentence now reads: "Fires in forests can lead to significant environmental damage."
- Intro Lines 25-26: Can you clarify what is meant by ‘It is important to take precautions and predict fire facilities in fire-prone areas to prevent forest fires.’. Is this referring to firefighting resources in a given area? Are these efforts actually targeted towards preventing forest fires (i.e. preventing ignition) or reducing risk/hazard mapping etc.?
We have revised the sentence as per your suggestion. The revised sentence now reads: "It is important to take precautions and predict fire facilities in fire-prone areas to prevent forest fires, referring to the proactive measures and predictive strategies aimed at preventing the ignition of forest fires, rather than firefighting resources in a given area. These efforts are focused on reducing the risk of forest fires through preventive measures, such as hazard mapping, fire risk assessment, and implementing measures to minimize the likelihood of fire ignition in fire-prone areas."
- Intro Lines 68-70: Could you clarify what is meant by ‘and this causes the impact of several characteristics to be ignored by putting together the occurrence of fire.’
We have revised the paragraph in question based on your feedback. The revised paragraph now includes a specific source for the information provided about the potential disadvantage of the Boruta algorithm. Thank you for your guidance, and I hope this meets your expectations.
" One potential disadvantage of the Boruta algorithm is that it can be computationally intensive, especially when dealing with a large number of input features. Since Boruta works by creating shadow features and comparing their importance to the original features, this process can become time-consuming and resource-intensive when dealing with high-dimensional datasets. Additionally, the algorithm's performance may be sensitive to its parameters, requiring careful tuning for optimal results (Kursa and Rudnicki, 2010)."
- Section 3.2 Line 8: Citation required for Aster Dem
Thank you for your valuable feedback. In response to your comment regarding the need for a citation for Aster Dem in Section 3.2, we have added the appropriate citation as per your suggestion.
- Section 3.2 Line 9: Can you clarify what is meant by wind effect? What is the actual continuous variable considered here?
In response to your comment regarding the clarification of the wind effect in Section 3.2, we have added the following information: "The factor of wind effect was generated by three different factors, including the degree of wind direction, wind speed (m/s), and altitude layer (Pourtaghi et al., 2015)."
- Methods: Could you add more details/description of the fire susceptibility mapping methods used?
Thank you for your valuable feedback. In response to your request for additional details on the fire susceptibility mapping methods used, we have expanded the description of our approach to provide a more comprehensive overview of the techniques and methodologies employed in our research. We believe that these enhancements will address your concerns and provide a clearer understanding of the methods utilized in our study.
- Table 2: See earlier comments on Table 1. Providing more details on how these features are specifically defined (i.e. what are the categorical or continuous variables used) will provide greater context here. This would aid the discussion and may also help to address existing reviewer comments around the need to discuss the exclusion of factors known to affect flame spread e.g. slope. Similarly, an additional description of the fire susceptibility mapping approach may also aid this discussion by explaining the extent to which this study focuses on ignition (fire occurrence).
In section 3.2, We have included the paragraphs you suggested, which provide detailed insights into the factors influencing fire occurrence and spread. The references have been incorporated to support the information provided. These additions aim to enhance the comprehensiveness of the study and address the specific points raised. Thank you for your valuable feedback.
" Height is one of the main factors affecting the size and intensity of fire and is one of the most important spatial layers used in many fields. Accordingly, higher elevations are generally more dangerous than lower elevations when a fire occurs (Rothermel, 1972). In this regard, elevated areas are usually more dangerous than low-lying areas when a fire occurs, especially if the access roads are unpaved or unsuitable for the movement of firefighting teams and their large equipment. If the area in front of the fire is steep, the situation is worse.
The slope of the land is important in the spread of fire and its control, because areas with steep slopes require complex methods of fire control (Estes et al., 2017). Slope controls fire progress, whether it moves uphill or downhill. The direction of the slope affects the amount of solar radiation received by the earth and the amount of soil moisture. In addition, it has an indirect effect on the prevalence of fire because it determines the type and density of vegetation present in a particular location.
Land use is an important factor in determining where wildfires occur, as places with abundant weeds and crops are more vulnerable to fire than others, especially in summer when daytime temperatures are at their maximum. Meanwhile, the possibility of fire in residential areas and forests is less.
Normalized Vegetation Index (NDVI) maps are important maps for analyzing the vegetation cover of each area and identifying the fire vulnerable spots, especially in the presence of seasonal crops, weeds and pastures in each area. are. While the difference of NDVI values in areas with evergreen trees such as oak forests and olive groves is not much. NDVI maps are very different between summer and spring.
Temperature is the most important factor in fire occurrence in the study area. All fires occurred in the summer when the grass had dried and the crops were ready for harvest (MARTÍN and DÍEZ, 2010). No fire has occurred in winter or in low temperature conditions or its occurrence rate is very low. Temperature in the study area can vary from place to place, even in the same season. Wind speed has an effective role in the spread of fire after ignition and may make it impossible to control the spread of fire in some cases. Solar radiation is positively correlated with temperature and associated with fire occurrence (MARTÍN and DÍEZ, 2010), especially in areas dominated by dry grass and fields. Radiation usually varies from place to place due to many factors such as soil texture and moisture content. The topographic moisture index (TWI) is a morphological factor that describes the topography of an area and other related conditions that affect the spatial patterns of soil texture and soil moisture.
Distance from recreation centers is an important factor in fires because many fires are directly or indirectly caused by human activities and activities that allow flames to reach flammable woody biomass. Fires and the number of fires that occur in a given location are positively correlated with population density. Human presence and activity in forest areas increases the possibility of forest fires. As a result, forests are predicted to be always at risk of fire due to nearby human settlements."
- Discussion Lines 12-13: ‘According to previous studies conducted in this specific study area, 17 forest fire conditional factors have been selected for this study.’ Could you discuss this more in the introduction to help explain your choice of the initial 17 factors? The discussion could perhaps also address any study limitations based on factors not considered in the 17 original factors which may merit consideration in future studies.
In response to your suggestion, we have expanded the introduction to provide a more comprehensive discussion regarding the selection of the initial 17 forest fire conditional factors. This includes an explanation of the rationale behind their selection, drawing from previous studies conducted in the specific study area. Furthermore, we have addressed potential limitations based on factors not considered in the original 17, highlighting areas that may merit consideration in future studies. We believe that these additions contribute to a more thorough understanding of our research methodology and its implications.
- Discussion Lines 38-40: Can you clarify if you are referring here to the other 7 factors selected in your study? Or if these are an additional 7 factors that you did not consider? ‘Several studies have identified seven other factors as effective factors in forest fires. (Bjånes et al., 2021; Eskandari et al., 2021; Mohajane et al., 2021; Naderpour et al., 2021; Tavakkoli Piralilou et al., 2022; Valdez et al., 2017).
Thank you for your feedback. In the sentence "In Table 2, one of the outcomes of this study is identifying the distance from power transmission lines as one of eight factors affecting fire occurrence that is less discussed in other studies. Several studies have identified seven other factors as effective factors in forest fires," we are indeed referring to the other seven factors selected in our study, not additional factors that were not considered.
Technical Comments
- Abstract Line 9: ‘and the second on those derived from RFE model’ could be reworded for clarity e.g. ‘and secondly on those derived from the RFE model’.
In response to your suggestion, We have revised the sentence as follows: "The SVM and RF models were applied once on all factors and secondly on those derived from the RFE model as the key factors in FSM."
- Abstract Line 14: ‘and not include unnecessary factors, could be reworded for clarity e.g. ‘and to exclude unnecessary factors’.
Thank you for your feedback, We have revised the sentence as follows: "The assessments demonstrate that leveraging RFE models enhances the FSM results by identifying key factors and excluding unnecessary ones."
- Intro Line 11: This probably requires a full citation ‘According to Copernicus (https://effis.jrc.ec.europa.eu)’
The revised text now includes a citation to the United Nations Environment Programme (2022) report "Spreading like Wildfire – The Rising Threat of Extraordinary Landscape Fires" to support the information provided about the EFFIS - European Forest Fire Information System.
- Intro Lines 52-53: ‘any evaluation if they play a significant role in their selected case study area.’ Typo should be ‘any evaluation of if they play a significant…’
Thank you for pointing out the typo. We have revised the sentence as per your suggestion. The revised sentence now reads: 'The literature review clearly shows that most methodologies employed conditional wildfire criteria without any evaluation of if they play a significant role in their selected case study area.'
- Intro Line 56: Typo ‘accuracies of the resulting FSMs caused’ should be ‘accuracies of the resulting FSMs are caused’
Thank you for pointing out the typo. We have revised the sentence as per your suggestion. The revised sentence now reads: 'While some studies have used several fire conditional factors, it is unclear whether the limited derived accuracies of the resulting FSMs are caused by the model limitations or the adverse impact of some not fully related factors.'
- Study Area Line 1: province does not need to be capitalized.
Thank you for your feedback. We have made the necessary adjustments to the manuscript by removing the capitalization of "province" in the study area section.
- Section 4.4 Line 7 – Missing full stop ‘We also weighed the weak classifier based on the classification effect of the sample set’
Section 4.4 Line 7 – Missing full stop ‘We also weighed the weak classifier based on the classification effect of the sample set’
- Correction of references
We are pleased to inform you that all mentioned references have been thoroughly reviewed and corrected as per your feedback. Thank you for your guidance in ensuring the accuracy and completeness of the reference details.
Citation: https://doi.org/10.5194/egusphere-2022-1294-AC4 -
AC5: 'Reply on RC2', Parham Pahlavani, 05 Dec 2023
Dear Reviewer,
I would like to express my sincere gratitude for the time and effort you dedicated to reviewing my manuscript. Your insightful comments and constructive feedback have significantly contributed to the improvement of the paper. I am thankful for the thoughtfulness of your review.
I am pleased to inform you that I have carefully addressed each of the comments and suggestions you provided. Your input has been invaluable in enhancing the quality and clarity of the manuscript. I believe that the revisions made have strengthened the overall content and presentation of the paper.
Once again, I extend my appreciation for your valuable contribution to this process. Your expertise and attention to detail have been instrumental in refining the manuscript, and I am truly grateful for your support.
Thank you for your time and consideration.
Sincerely,
Authors
- I agree with previous comments that it should be clarified from the outset (and in the title) that it is forest fire susceptibility that is being modeled rather than the wildfire itself (i.e. behavior, spread etc.).
Thank you for your valuable feedback. We have revised the title of the paper to better reflect the focus of our study. The new title, "Modeling Relative Wildfire Susceptibility in a Specific Area: A Study of Recursive Feature Elimination's Impact on SVM and RF—A Case Study in Iran," aims to clearly convey that our study is centered on modeling relative wildfire susceptibility and the impact of recursive feature elimination on SVM and RF in a specific area. We believe this revision effectively addresses your concern about clarifying the modeled factors in the title. We appreciate your input and hope that this change aligns with your expectations.
- How were the 17 factors identified (i.e. what process was involved). Is it worth separating out those that apply to ignition (‘triggering’) vs. spreading or both. Subsequently, RFE is used to select features from these initial 17 but the initial assessment and selection of a ‘longlist’ of factors would seem to be a very important part of any feature selection process to prevent the risk of optimizing for the wrong set of factors.
Thank you for your insightful comments and suggestions. We have carefully reviewed your feedback and have made the necessary revisions to address your concerns. The 17 factors were identified through a comprehensive review of existing literature and empirical studies in the field. These factors were selected based on their documented relevance to forest fire behavior and susceptibility. While the initial identification of these factors was not explicitly categorized into those that apply to ignition versus spreading, the subsequent use of Recursive Feature Elimination (RFE) allowed for the selection of the most influential factors for modeling. The RFE process involved iteratively fitting the model and identifying the most relevant features, thereby addressing the concern of optimizing for the wrong set of factors. This iterative approach ensured that the final set of features used in the analysis was well-suited for the specific objectives of the study, mitigating the risk of suboptimal feature selection. Additionally, the consideration of factors that specifically apply to ignition versus spreading could be a valuable avenue for further research, potentially enhancing the precision and applicability of the model. This distinction may offer insights into the distinct mechanisms driving the initiation and propagation of forest fires, thereby contributing to a more nuanced understanding of fire behavior and risk assessment. In summary, while the initial assessment and selection of the factors were crucial, the subsequent application of RFE provided a robust mechanism for refining the feature set and mitigating the risk of suboptimal feature selection. Further exploration of factors related to ignition and spreading could offer valuable insights for future research in this domain.
- Abstract Lines 11-12: Could you clarify what the difference between accuracy (in both uses below is) ‘Different metrics were used to measure accuracy, including recall, precision, F1, accuracy, the area under the curve (AUC), Matthews correlation coefficient (MCC), and Kappa’. Perhaps by defining accuracy in the subsequent list? This will also help the interpretation of your overall conclusions presented in the final lines of the abstract ‘The greatest improvement is for SVM, with more than 10.97% and 8.61% in the accuracy and AUC metrics, respectively.’
We have revised the sentence as per your suggestion. The updated version now reads: "Various metrics, including recall, precision, F1 score, accuracy, area under the curve (AUC), Matthews correlation coefficient (MCC), and Kappa, were employed to measure the performance of the models. The assessments demonstrate that leveraging RFE models enhances the FSM results by identifying key factors and excluding unnecessary ones. Notably, the SVM model exhibits significant improvement, achieving an increase of over 10.97% in accuracy and 8.61% in AUC metrics. This improvement underscores the effectiveness of the RFE approach in enhancing the predictive performance of the SVM model." We believe this modification aligns with your feedback and provides a clearer description of the assessment process and its implications. Thank you for your input, and we hope this change meets your expectations.
- Intro: The early sections of the introduction could perhaps benefit from a more specific selection of cited references, particularly where the effects of forest fires are discussed. For example, in several cases, it may be worth referring directly to one of the studies cited in the actual source cited. Additionally, a brief discussion of factors known to influence fire susceptibility (aided by the existing literature) may help the discussion of why the initial 17 factors were selected, and subsequently aid the discussion of excluded and selected factors.
In response to your suggestion to provide more specific references, especially when discussing the effects of forest fires and to discuss factors known to influence fire susceptibility based on existing literature, we have made the following changes:
In paragraph 55, we have added the following sentences to address the specific selection of cited references and to discuss factors known to influence fire susceptibility based on existing literature:
"Related topographic factors are crucial in forest fire susceptibility, widely used for forest fire susceptibility mapping (Kolden and Abatzoglou, 2018; Lautenberger, 2017). For example, the slope factor is essential due to its impact on fire spread, with steeper slopes leading to faster fire propagation (Ghorbanzadeh et al., 2018). Additionally, the difference in temperature and moisture between north- and south-facing slopes contributes to a higher risk of forest fires on south-facing slopes (Sayad et al., 2019). Altitude also plays a significant role, with higher moisture levels at greater altitudes (Ganteaume et al., 2013). The wind effect factor encompasses the degree of wind direction, wind speed, and altitude layer (Pourtaghi et al., 2015). Human-made factors include various distance measures, classified based on their relevance to forest fires, human activity radius, literature, and expert insights (Pourghasemi et al., 2016)."
- Intro Line 2: Could a more relevant study perhaps be cited here? For example, one of the studies cited in Pourtaghi et al., 2016 in which the ecosystem services and carbon balance of forests are considered?
In response to your comment regarding the need for a more relevant study to be cited in Intro Line 2, we have made the following changes:
We have added two additional references to support the discussion on ecosystem services and carbon balance of forests. The references added are as follows:
Manisalidis, I., Stavropoulou, E., Stavropoulos, A., and Bezirtzoglou, E.: Environmental and Health Impacts of Air Pollution: A Review, Front. Public Health, 8, 14.
Badea, O.: Climate Change and Air Pollution Effect on Forest Ecosystems, Forests, 12, 1642, https://doi.org/10.3390/f12121642, 2021
- Intro Lines 4-6: ‘Therefore, most forest fires, whether natural or induced by humans, cause many negative ecological, social, and economic impacts on forest restoration’ Can this be reworded to allow for or acknowledge the increasingly important role of prescribed fire in many regions and the potential benefits. And similarly the beneficial historical role of fire in many regions. Perhaps rewording to ‘forest fires, whether natural or induced by humans, can cause many negative..’ Or this could be moved to appear after your definition of a forest fire (a citation for this definition could also be added if applicable).
We have revised the specified section as per your suggestion. The revised content now appears after the definition of a forest fire. The revised section reads as follows: "Forest fires, whether natural or induced by humans, can have significant ecological, social, and economic impacts on forest restoration. However, it is important to acknowledge the increasingly important role of prescribed fire in many regions and the potential benefits it can bring. Similarly, historical fire regimes have played a beneficial role in many regions. Therefore, it is essential to consider the potential positive impacts of controlled or prescribed fires alongside the negative impacts of forest fires."
- Intro Lines 7-8: As above it would be good to acknowledge that ‘Fires in forests can lead to significant environmental damage’ rather than ‘Fires in forests lead to a lot of environmental destruction due to the presence of highly combustible trees’ as this is not necessarily always the case.
We have revised the sentence as per your suggestion. The revised sentence now reads: "Fires in forests can lead to significant environmental damage."
- Intro Lines 25-26: Can you clarify what is meant by ‘It is important to take precautions and predict fire facilities in fire-prone areas to prevent forest fires.’. Is this referring to firefighting resources in a given area? Are these efforts actually targeted towards preventing forest fires (i.e. preventing ignition) or reducing risk/hazard mapping etc.?
We have revised the sentence as per your suggestion. The revised sentence now reads: "It is important to take precautions and predict fire facilities in fire-prone areas to prevent forest fires, referring to the proactive measures and predictive strategies aimed at preventing the ignition of forest fires, rather than firefighting resources in a given area. These efforts are focused on reducing the risk of forest fires through preventive measures, such as hazard mapping, fire risk assessment, and implementing measures to minimize the likelihood of fire ignition in fire-prone areas."
- Intro Lines 68-70: Could you clarify what is meant by ‘and this causes the impact of several characteristics to be ignored by putting together the occurrence of fire.’
We have revised the paragraph in question based on your feedback. The revised paragraph now includes a specific source for the information provided about the potential disadvantage of the Boruta algorithm. Thank you for your guidance, and I hope this meets your expectations.
" One potential disadvantage of the Boruta algorithm is that it can be computationally intensive, especially when dealing with a large number of input features. Since Boruta works by creating shadow features and comparing their importance to the original features, this process can become time-consuming and resource-intensive when dealing with high-dimensional datasets. Additionally, the algorithm's performance may be sensitive to its parameters, requiring careful tuning for optimal results (Kursa and Rudnicki, 2010)."
- Section 3.2 Line 8: Citation required for Aster Dem
Thank you for your valuable feedback. In response to your comment regarding the need for a citation for Aster Dem in Section 3.2, we have added the appropriate citation as per your suggestion.
- Section 3.2 Line 9: Can you clarify what is meant by wind effect? What is the actual continuous variable considered here?
In response to your comment regarding the clarification of the wind effect in Section 3.2, we have added the following information: "The factor of wind effect was generated by three different factors, including the degree of wind direction, wind speed (m/s), and altitude layer (Pourtaghi et al., 2015)."
- Methods: Could you add more details/description of the fire susceptibility mapping methods used?
Thank you for your valuable feedback. In response to your request for additional details on the fire susceptibility mapping methods used, we have expanded the description of our approach to provide a more comprehensive overview of the techniques and methodologies employed in our research. We believe that these enhancements will address your concerns and provide a clearer understanding of the methods utilized in our study.
- Table 2: See earlier comments on Table 1. Providing more details on how these features are specifically defined (i.e. what are the categorical or continuous variables used) will provide greater context here. This would aid the discussion and may also help to address existing reviewer comments around the need to discuss the exclusion of factors known to affect flame spread e.g. slope. Similarly, an additional description of the fire susceptibility mapping approach may also aid this discussion by explaining the extent to which this study focuses on ignition (fire occurrence).
In section 3.2, We have included the paragraphs you suggested, which provide detailed insights into the factors influencing fire occurrence and spread. The references have been incorporated to support the information provided. These additions aim to enhance the comprehensiveness of the study and address the specific points raised. Thank you for your valuable feedback.
" Height is one of the main factors affecting the size and intensity of fire and is one of the most important spatial layers used in many fields. Accordingly, higher elevations are generally more dangerous than lower elevations when a fire occurs (Rothermel, 1972). In this regard, elevated areas are usually more dangerous than low-lying areas when a fire occurs, especially if the access roads are unpaved or unsuitable for the movement of firefighting teams and their large equipment. If the area in front of the fire is steep, the situation is worse.
The slope of the land is important in the spread of fire and its control, because areas with steep slopes require complex methods of fire control (Estes et al., 2017). Slope controls fire progress, whether it moves uphill or downhill. The direction of the slope affects the amount of solar radiation received by the earth and the amount of soil moisture. In addition, it has an indirect effect on the prevalence of fire because it determines the type and density of vegetation present in a particular location.
Land use is an important factor in determining where wildfires occur, as places with abundant weeds and crops are more vulnerable to fire than others, especially in summer when daytime temperatures are at their maximum. Meanwhile, the possibility of fire in residential areas and forests is less.
Normalized Vegetation Index (NDVI) maps are important maps for analyzing the vegetation cover of each area and identifying the fire vulnerable spots, especially in the presence of seasonal crops, weeds and pastures in each area. are. While the difference of NDVI values in areas with evergreen trees such as oak forests and olive groves is not much. NDVI maps are very different between summer and spring.
Temperature is the most important factor in fire occurrence in the study area. All fires occurred in the summer when the grass had dried and the crops were ready for harvest (MARTÍN and DÍEZ, 2010). No fire has occurred in winter or in low temperature conditions or its occurrence rate is very low. Temperature in the study area can vary from place to place, even in the same season. Wind speed has an effective role in the spread of fire after ignition and may make it impossible to control the spread of fire in some cases. Solar radiation is positively correlated with temperature and associated with fire occurrence (MARTÍN and DÍEZ, 2010), especially in areas dominated by dry grass and fields. Radiation usually varies from place to place due to many factors such as soil texture and moisture content. The topographic moisture index (TWI) is a morphological factor that describes the topography of an area and other related conditions that affect the spatial patterns of soil texture and soil moisture.
Distance from recreation centers is an important factor in fires because many fires are directly or indirectly caused by human activities and activities that allow flames to reach flammable woody biomass. Fires and the number of fires that occur in a given location are positively correlated with population density. Human presence and activity in forest areas increases the possibility of forest fires. As a result, forests are predicted to be always at risk of fire due to nearby human settlements."
- Discussion Lines 12-13: ‘According to previous studies conducted in this specific study area, 17 forest fire conditional factors have been selected for this study.’ Could you discuss this more in the introduction to help explain your choice of the initial 17 factors? The discussion could perhaps also address any study limitations based on factors not considered in the 17 original factors which may merit consideration in future studies.
In response to your suggestion, we have expanded the introduction to provide a more comprehensive discussion regarding the selection of the initial 17 forest fire conditional factors. This includes an explanation of the rationale behind their selection, drawing from previous studies conducted in the specific study area. Furthermore, we have addressed potential limitations based on factors not considered in the original 17, highlighting areas that may merit consideration in future studies. We believe that these additions contribute to a more thorough understanding of our research methodology and its implications.
- Discussion Lines 38-40: Can you clarify if you are referring here to the other 7 factors selected in your study? Or if these are an additional 7 factors that you did not consider? ‘Several studies have identified seven other factors as effective factors in forest fires. (Bjånes et al., 2021; Eskandari et al., 2021; Mohajane et al., 2021; Naderpour et al., 2021; Tavakkoli Piralilou et al., 2022; Valdez et al., 2017).
Thank you for your feedback. In the sentence "In Table 2, one of the outcomes of this study is identifying the distance from power transmission lines as one of eight factors affecting fire occurrence that is less discussed in other studies. Several studies have identified seven other factors as effective factors in forest fires," we are indeed referring to the other seven factors selected in our study, not additional factors that were not considered.
Technical Comments
- Abstract Line 9: ‘and the second on those derived from RFE model’ could be reworded for clarity e.g. ‘and secondly on those derived from the RFE model’.
In response to your suggestion, We have revised the sentence as follows: "The SVM and RF models were applied once on all factors and secondly on those derived from the RFE model as the key factors in FSM."
- Abstract Line 14: ‘and not include unnecessary factors, could be reworded for clarity e.g. ‘and to exclude unnecessary factors’.
Thank you for your feedback, We have revised the sentence as follows: "The assessments demonstrate that leveraging RFE models enhances the FSM results by identifying key factors and excluding unnecessary ones."
- Intro Line 11: This probably requires a full citation ‘According to Copernicus (https://effis.jrc.ec.europa.eu)’
The revised text now includes a citation to the United Nations Environment Programme (2022) report "Spreading like Wildfire – The Rising Threat of Extraordinary Landscape Fires" to support the information provided about the EFFIS - European Forest Fire Information System.
- Intro Lines 52-53: ‘any evaluation if they play a significant role in their selected case study area.’ Typo should be ‘any evaluation of if they play a significant…’
Thank you for pointing out the typo. We have revised the sentence as per your suggestion. The revised sentence now reads: 'The literature review clearly shows that most methodologies employed conditional wildfire criteria without any evaluation of if they play a significant role in their selected case study area.'
- Intro Line 56: Typo ‘accuracies of the resulting FSMs caused’ should be ‘accuracies of the resulting FSMs are caused’
Thank you for pointing out the typo. We have revised the sentence as per your suggestion. The revised sentence now reads: 'While some studies have used several fire conditional factors, it is unclear whether the limited derived accuracies of the resulting FSMs are caused by the model limitations or the adverse impact of some not fully related factors.'
- Study Area Line 1: province does not need to be capitalized.
Thank you for your feedback. We have made the necessary adjustments to the manuscript by removing the capitalization of "province" in the study area section.
- Section 4.4 Line 7 – Missing full stop ‘We also weighed the weak classifier based on the classification effect of the sample set’
Section 4.4 Line 7 – Missing full stop ‘We also weighed the weak classifier based on the classification effect of the sample set’
- Correction of references
We are pleased to inform you that all mentioned references have been thoroughly reviewed and corrected as per your feedback. Thank you for your guidance in ensuring the accuracy and completeness of the reference details.
Citation: https://doi.org/10.5194/egusphere-2022-1294-AC5
-
AC4: 'Reply on RC2', Parham Pahlavani, 05 Dec 2023
Viewed
| HTML | XML | Total | BibTeX | EndNote | |
|---|---|---|---|---|---|
| 567 | 259 | 50 | 876 | 16 | 17 |
- HTML: 567
- PDF: 259
- XML: 50
- Total: 876
- BibTeX: 16
- EndNote: 17
Viewed (geographical distribution)
| Country | # | Views | % |
|---|
| Total: | 0 |
| HTML: | 0 |
| PDF: | 0 |
| XML: | 0 |
- 1