the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
| 29 Aug 2022
HIDRA2: deep-learning ensemble storm surge forecasting in the presence of seiches – the case of Northern Adriatic
Marko Rus
Anja Fettich
Matej Kristan
Matjaž Ličer
Abstract. We propose a new deep-learning architecture HIDRA2 for sea level and storm surge modeling, which is extremely fast to train and apply, and outperforms both our previous network design HIDRA1 and the state-of-the-art numerical ocean model (a NEMO engine with sea level data assimilation), over all sea level bins and all forecast lead times. The architecture of HIDRA2 employs novel atmospheric, tidal and SSH feature encoders, as well as a novel feature fusion and SSH regression block. HIDRA2 was trained on surface wind and pressure fields from a single member of ECMWF atmospheric ensemble and on Koper tide gauge observations during years 2006–2018, and evaluated on the data from June 2019 to December 2020. Compared to HIDRA1, the overall mean absolute forecast error is reduced by 13.9 %, while on storm surge events it is lower by even a larger margin of 25.1 %. Consistent superior performance over HIDRA1 as well as NEMO is observed in both tails of the sea level distribution. Power spectrum analysis indicates that HIDRA2 most accurately represents the energy density peaks centered on the two lowest Adriatic wind-induced free oscillation eigenmodes (seiches) among all tested models. To assign model errors to specific frequency bands covering diurnal and semi-diurnal tides and the lowest two basin seiches, sea level band-pass filtering of several historic storm surge events is applied. HIDRA2 performs well across all frequency bands and most accurately predicts amplitudes and temporal phases of the Adriatic basin seiches. This is shown to be an important forecasting benefit due to the high sensitivity of total Adriatic storm surge sea level to the phase lag between peak tide and peak seiche.
-
Notice on discussion status
The requested preprint has a corresponding peer-reviewed final revised paper. You are encouraged to refer to the final revised version.
-
Preprint
(2861 KB)
-
The requested preprint has a corresponding peer-reviewed final revised paper. You are encouraged to refer to the final revised version.
- Preprint
(2861 KB) - BibTeX
- EndNote
- Final revised paper
Journal article(s) based on this preprint
Marko Rus et al.
Interactive discussion
Status: closed
-
CEC1: 'Comment on egusphere-2022-618', Juan Antonio Añel, 21 Sep 2022
Dear authors,
Unfortunately, after checking your manuscript, it has come to our attention that it does not comply with our "Code and Data Policy".
https://www.geoscientific-model-development.net/policies/code_and_data_policy.htmlYour manuscript fails to comply because of several issues. I list them below and expect that you address and fix them as soon as possible.
- First, regarding code: the Hidra 2 model does not have a license listed. If you do not include a license, despite you publishing it, the code is not available to use by anyone; it continues to be your property. Therefore, add a license to your code in Zenodo. You could want to choose a free software/open-source (FLOSS) license. We recommend the GPLv3. You only need to include the file 'https://www.gnu.org/licenses/gpl-3.0.txt' as LICENSE.txt with your code. Also, you can choose other options that Zenodo provides: GPLv2, Apache License, MIT License, etc.
- Secondly, you use the UTIDE package. However, this package is stored on GitHub, as you mention in the list of References. UTIDE is released under the MIT license so that you can copy it. Therefore, as GitHub is not a suitable repository (GitHub itself instructs authors to use other alternatives for long-term archival and publishing, such as Zenodo), please, publish UTIDE (maintaining the MIT license) in one of the appropriate repositories, and reply to this comment with the relevant information (link and DOI).
- Also, your manuscript is about a learning method. As this technique heavily depends on the input data, and the reproducibility of the work is compromised without it, we request that you publish in the repositories for your paper the input and output files used in your work. In the Code and Data Availability section, you mention in a generic way the MARS retrieval system. This is not enough. You must publish the specific data used as input. If variables are taken from a larger file, you can post simply the input data taken from them and used. For outputs, nothing prevents you from publishing them.
Finally, you use the NEMO model. However, you do not provide the NEMO code. You simply cite a pdf file, listed in the references, stored in a webpage that is not a trustable repository. Also, you do not identify the NEMO version used for your work. All these issues must be fixed. First, you must clearly state in your manuscript the NEMO version that you use. Then you must provide in the Code and Data Availability section a link to a trustable repository containing it. Many papers on the development of NEMO have been published in our journal, and in this way many NEMO versions are already stored in Zenodo. You could want to check if it is the case of the version you have used and simply cite its current Zenodo repository. If not, please, create a new one.
Please, reply as soon as possible to this comment with all the information requested above, so it is available for the Discussions process as it should be. Note that your manuscript should have never been accepted for Discussions with all the mentioned flaws, this was an oversight from the Topical Editor, and we are trying to fix it now. Also, please, be aware that failing to comply with this request could result in rejecting your manuscript for publication. Moreover, you must include in any reviewed version of your manuscript the modified 'Code and Data Availability' section with all the new information requested.
Juan A. AñelGeosci. Model Dev. Exec. EditorCitation: https://doi.org/10.5194/egusphere-2022-618-CEC1 -
CC1: 'Reply on CEC1', Matjaz Licer, 22 Sep 2022
Dear Editor,
thank you for bringing these issues to our attention - we will gladly comply with stated request as soon as possible. Unfortunately some of the authors needed for a full response are unavailable/unreachable until the end of next week so we will not be able to finalize our amendments until then. This will however be our first and top priority. I hope this delay is not an issue, otherwise we are open to further suggestions.
Best regards,
Matjaz Licer
Citation: https://doi.org/10.5194/egusphere-2022-618-CC1 -
CC2: 'Reply on Editor comment. License and Input Training/Testing datasets.', Matjaz Licer, 30 Sep 2022
Point-by-point reply to issues raised by the GMD editor:
GMD: - First, regarding code: the Hidra 2 model does not have a license listed. If you do not include a license, despite you publishing it, the code is not available to use by anyone; it continues to be your property. Therefore, add a license to your code in Zenodo. You could want to choose a free software/open-source (FLOSS) license. We recommend the GPLv3. You only need to include the file 'https://www.gnu.org/licenses/gpl-3.0.txt' as LICENSE.txt with your code. Also, you can choose other options that Zenodo provides: GPLv2, Apache License, MIT License, etc.
Authors’ reply:
We have added a licence file to the repository.
GMD: - Secondly, you use the UTIDE package. However, this package is stored on GitHub, as you mention in the list of References. UTIDE is released under the MIT license so that you can copy it. Therefore, as GitHub is not a suitable repository (GitHub itself instructs authors to use other alternatives for long-term archival and publishing, such as Zenodo), please, publish UTIDE (maintaining the MIT license) in one of the appropriate repositories, and reply to this comment with the relevant information (link and DOI).
Authors’ reply:
Utide package, used in the manuscript, is now uploaded to Zenodo under MIT license.
link: https://zenodo.org/record/7103894
DOI: https://doi.org/10.5281/zenodo.7103894
- Also, your manuscript is about a learning method. As this technique heavily depends on the input data, and the reproducibility of the work is compromised without it, we request that you publish in the repositories for your paper the input and output files used in your work. In the Code and Data Availability section, you mention in a generic way the MARS retrieval system. This is not enough. You must publish the specific data used as input. If variables are taken from a larger file, you can post simply the input data taken from them and used. For outputs, nothing prevents you from publishing them.
Authors ‘reply:
We have published the entire processed input training and test datasets for HIDRA2 at the following location:
link: https://zenodo.org/record/7123911
DOI: https://doi.org/10.5281/zenodo.7123910
Note these are not the original ECMWF ensemble fields but rather a substantially coarsened and processed fields - original fields are only available via MARS system request specifications AREA="46./5./35./21.", GRID="0.125/0.125", STEP="00/to/72/by/1", PARAMS="165.128/166.128/167.128/151.128", NUMBER="1/to/50", TIMES="00".
We have also updated the repository to include HIDRA2 predictions on the test set, and refined instructions on how to train and evaluate HIDRA2 on the published data. The repository is available here:
link: https://github.com/rusmarko/HIDRA2
DOI: https://doi.org/10.5281/zenodo.6784842
We will add this information to the revised version of the manuscript.
Finally, you use the NEMO model. However, you do not provide the NEMO code. You simply cite a pdf file, listed in the references, stored in a webpage that is not a trustable repository. Also, you do not identify the NEMO version used for your work. All these issues must be fixed. First, you must clearly state in your manuscript the NEMO version that you use. Then you must provide in the Code and Data Availability section a link to a trustable repository containing it. Many papers on the development of NEMO have been published in our journal, and in this way many NEMO versions are already stored in Zenodo. You could want to check if it is the case of the version you have used and simply cite its current Zenodo repository. If not, please, create a new one.
Authors’ reply:
We are using the Copernicus Marine Environment and Monitoring Service (CMEMS) operational forecasting product which is publicly available and based on NEMO v3.6 (https://doi.org/10.25423/CMCC/MEDSEA_ANALYSISFORECAST_PHY_006_013_EAS6). We are not running the NEMO model ourselves for this particular study. However, a regional setup of NEMO v3.6, which officially ships with NEMOGCM code (https://www.nemo-ocean.eu/), is available at the following repository:
Link: https://zenodo.org/record/4022310
Doi: https://doi.org/10.5281/zenodo.4022309
We will include the version number in the revised manuscript and we will remove the untrusted documentation pdf address and replace it by the official Copernicus documentation doi for the used sea level product: https://doi.org/10.25423/CMCC/MEDSEA_ANALYSISFORECAST_PHY_006_013_EAS6 .
Please, reply as soon as possible to this comment with all the information requested above, so it is available for the Discussions process as it should be. Note that your manuscript should have never been accepted for Discussions with all the mentioned flaws, this was an oversight from the Topical Editor, and we are trying to fix it now. Also, please, be aware that failing to comply with this request could result in rejecting your manuscript for publication. Moreover, you must include in any reviewed version of your manuscript the modified 'Code and Data Availability' section with all the new information requested.
Authors’ reply: Thank you, we will include this information in any revised version of the manuscript.
Citation: https://doi.org/10.5194/egusphere-2022-618-CC2
-
CC1: 'Reply on CEC1', Matjaz Licer, 22 Sep 2022
-
RC1: 'Comment on egusphere-2022-618', Anonymous Referee #1, 25 Sep 2022
The manuscript is great in its approach and compares with previous models. The application of the work is also in a major area of concern. Adding a bit more technical details to the manuscript will be good for the readership of the article.
Citation: https://doi.org/10.5194/egusphere-2022-618-RC1 -
AC1: 'Reply on RC1', Marko Rus, 14 Nov 2022
The comment was uploaded in the form of a supplement: https://egusphere.copernicus.org/preprints/2022/egusphere-2022-618/egusphere-2022-618-AC1-supplement.pdf
-
AC1: 'Reply on RC1', Marko Rus, 14 Nov 2022
-
RC2: 'Comment on egusphere-2022-618', Anonymous Referee #2, 10 Oct 2022
This manuscript presents a new deep-learning storm surge forecasting (HIDRA2) for the Northern Adriatic which is an “updated” version of a previous deep learning architecture HIDRA1. The authors show that HIDRA2 outperforms its previous version HIDRA1 and it also performs better that the Copernicus Mediterranean Reanalysis. The paper is well written, and I think it must be published after some minor changes.
Major comment:
The authors compare their new HIDRA2 with CMEMS Reanalysis, that is a 3D model in a regular horizontal grid. I recommend to the authors to compare the performance of HIDRA2 against numerical simulations specifically design to determine the sea surface elevation. As examples, the authors may use the global simulation by Muis et al. (2020) which has, in the Mediterranean, a 1.25 km of coastal resolution; or they can use the newest available simulation performed by Toomey et al. (2022) specifically designed for the Mediterranean Sea with a coastal resolution of 200 m. The latest hindcast includes the wave setup component that maybe relevant when computing the total elevation in the studied area.
Minor comments:
- The authors use the term storm surge to refer to the combined effect of atmospheric pressure, winds, and astronomic tides. I strongly recommend the authors to follow the terminology detailed in Gregory et al. (2019). In that paper, they write: “N9 Storm surge: The elevation or depression of the sea surface with respect to the predicted tide during a storm.” And they also write: “Sea-surface height (SSH) can be greatly elevated during a storm by a storm surge, and the consequent extreme sea level is sometimes called a storm tide”. So, the combination of storm surge + astronomical tide should be referred as storm tide, if we decide to follow the definitions in Gregory et al. (2019).
- Line 17: this line needs, at least, two references where I have included (Ref. XXXX): “Global mean sea level rise, related to anthropogenic climate change (Ref. XXXX), is causing a worldwide increase in coastal flooding frequency and is leading to a myriad of negative consequences for coastal communities, civil safety and economies (Ref. XXXX).”
- Fig. 1: Please change the title of the figure to “Adriatic Sea topo-bathymetry”.
- Line 35-36: put the citation to Medvedev between parentheses.
- Line 48: “HIDRA1 ensemble (Žust et al., 2021) is a million times faster than the operational numerical ocean model ensemble based on NEMO engine”. Although it maybe true, it is not fair to compare the computational time of a 3D model that computes water dynamics (currents, temperatures, salinities, …) in several vertical layers with HIDRA1 or HIDRA2 that gives SSH information only and in a single point. The authors should compare the computational time with, for example Muis et al. (2020) or Toomey et al. (2022), and multiply their computational time by the number of nodes that the other two studies are computing.
-Fig. 10: it is difficult to appreciate the differences between the different datasets. I would recommend the authors to apply a filter to the spectrum. There may be a newer reference but I usually do it following the Chapter 5- Time-series Analysis Methods (https://www.sciencedirect.com/science/article/pii/B978044450756350006X) from Data Analysis Methods in Physical Oceanography by Emery and Thomson.
Some thoughts:
1) Could this system be scaled up and applied to estimate SSH values at a Mediterranean scale?
2) How does the predictability change if the system is fed with the first predicted day?
References:
Gregory, J.M., Griffies, S.M., Hughes, C.W. et al. Concepts and Terminology for Sea Level: Mean, Variability and Change, Both Local and Global. Surv Geophys 40, 1251–1289 (2019). https://doi.org/10.1007/s10712-019-09525-z
Muis S., Apecechea M. I., Dullaart J., de Lima Rego J., Madsen K. S., Su J., et al. (2020). A high-resolution global dataset of extreme sea levels, tides, and storm surges, including future projections. Front. Mar. Sci. 7. doi: 10.3389/fmars.2020.00263
Toomey, T., Amores, A., Marcos, M., & Orfila, A. Coastal sea levels and wind-waves in the Mediterranean Sea since 1950 from a high-resolution ocean reanalysis. Frontiers in Marine Science, 1873. doi: 10.3389/fmars.2022.991504
Citation: https://doi.org/10.5194/egusphere-2022-618-RC2 -
AC2: 'Reply on RC2', Marko Rus, 14 Nov 2022
The comment was uploaded in the form of a supplement: https://egusphere.copernicus.org/preprints/2022/egusphere-2022-618/egusphere-2022-618-AC2-supplement.pdf
-
AC2: 'Reply on RC2', Marko Rus, 14 Nov 2022
-
RC3: 'Comment on egusphere-2022-618', Anonymous Referee #3, 31 Oct 2022
This manuscript shows an implementation of a neural network (HYDRA2) to predict sea level at the Koper tidal station. This neural network is an improvement over HIDRA1 and it is compared to its predecessor and to a numerical ocean model NEMO. Particularly notable in this manuscript is the detailed validation of the performance of the model. I can recommend publishing this manuscript after minor changes.
To facilitate the reading of the manuscript and the interpretation of the figures and table I would recommend the captions clarify if the authors show an independent validation (data not used during training and not used for the optimization of hyperparameters, if this is the case) or validation with dependent data. Likewise I think it would be useful to mention this also with the skill scores mentioned in the abstract (starting at line 7) whether these error reductions are obtained from the independent test data or not.
I don’t not have any doubts about the scientific soundness of the results, but adding this information would help readers understand the results of the manuscript more quickly.
Minor comments:
Line 5: “single member of ECMWF atmospheric ensemble”: is this the central forecast or any single member (chosen at random)?
Line 47: “HIDRA1 ensemble (Žust et al., 2021) is a million times faster than the operational numerical ocean model ensemble based on NEMO engine (Madec, 2016) at Slovenian Environment Agency”: There is not a lot of context to understand this comparison. NEMO will provide you with a sea level estimate over the whole domain. Is this also the case for HIDRA1 or would it provide the sea-level for a single location?
Line 99: “HIDRA2 does not require explicit annotation of whether a location point belongs to land or sea, thus land masks are not generated.”
I am wondering if the land-sea mask would still be a useful feature to provide to the neural network as a wind over land would not generate seiches. I guess that the neural network compensates for this by learning the land-sea mask internally.
Line 103: “three-days prediction lead time” I think that your ML model will give in one application the full 3-day time series. Can you confirm? Or do you rather need to apply the ML model iteratively to obtain the 3-day time series? Can you also clarify this in the manuscript?
104: “full ECMWF three-day forecast” -> “full” refers to the full ensemble (i.e. all ensemble members)?
143: “prototype matching layer” Can you provide more information and a reference ?
section 4.1.1: this is an interesting and surprising result. Can the authors speculate why this is the case? (predicting full SSH leads to better results for extreme events). Could it be that the neural network internally limits its output range when working on anomalies? Do you expect this outcome to remain should one have more training data?
Section 4.1.2 “Ablation study”: can you clarify that you retrained the network for the different test cases (without tides encoder, without atmospheric encoder,..) or you do rather zero-out the output of the corresponding encoder without re-training.
Typo:
Line 205: 1°/24 -> 1/24 °
Citation: https://doi.org/10.5194/egusphere-2022-618-RC3 -
AC3: 'Reply on RC3', Marko Rus, 14 Nov 2022
The comment was uploaded in the form of a supplement: https://egusphere.copernicus.org/preprints/2022/egusphere-2022-618/egusphere-2022-618-AC3-supplement.pdf
-
AC3: 'Reply on RC3', Marko Rus, 14 Nov 2022
Interactive discussion
Status: closed
-
CEC1: 'Comment on egusphere-2022-618', Juan Antonio Añel, 21 Sep 2022
Dear authors,
Unfortunately, after checking your manuscript, it has come to our attention that it does not comply with our "Code and Data Policy".
https://www.geoscientific-model-development.net/policies/code_and_data_policy.htmlYour manuscript fails to comply because of several issues. I list them below and expect that you address and fix them as soon as possible.
- First, regarding code: the Hidra 2 model does not have a license listed. If you do not include a license, despite you publishing it, the code is not available to use by anyone; it continues to be your property. Therefore, add a license to your code in Zenodo. You could want to choose a free software/open-source (FLOSS) license. We recommend the GPLv3. You only need to include the file 'https://www.gnu.org/licenses/gpl-3.0.txt' as LICENSE.txt with your code. Also, you can choose other options that Zenodo provides: GPLv2, Apache License, MIT License, etc.
- Secondly, you use the UTIDE package. However, this package is stored on GitHub, as you mention in the list of References. UTIDE is released under the MIT license so that you can copy it. Therefore, as GitHub is not a suitable repository (GitHub itself instructs authors to use other alternatives for long-term archival and publishing, such as Zenodo), please, publish UTIDE (maintaining the MIT license) in one of the appropriate repositories, and reply to this comment with the relevant information (link and DOI).
- Also, your manuscript is about a learning method. As this technique heavily depends on the input data, and the reproducibility of the work is compromised without it, we request that you publish in the repositories for your paper the input and output files used in your work. In the Code and Data Availability section, you mention in a generic way the MARS retrieval system. This is not enough. You must publish the specific data used as input. If variables are taken from a larger file, you can post simply the input data taken from them and used. For outputs, nothing prevents you from publishing them.
Finally, you use the NEMO model. However, you do not provide the NEMO code. You simply cite a pdf file, listed in the references, stored in a webpage that is not a trustable repository. Also, you do not identify the NEMO version used for your work. All these issues must be fixed. First, you must clearly state in your manuscript the NEMO version that you use. Then you must provide in the Code and Data Availability section a link to a trustable repository containing it. Many papers on the development of NEMO have been published in our journal, and in this way many NEMO versions are already stored in Zenodo. You could want to check if it is the case of the version you have used and simply cite its current Zenodo repository. If not, please, create a new one.
Please, reply as soon as possible to this comment with all the information requested above, so it is available for the Discussions process as it should be. Note that your manuscript should have never been accepted for Discussions with all the mentioned flaws, this was an oversight from the Topical Editor, and we are trying to fix it now. Also, please, be aware that failing to comply with this request could result in rejecting your manuscript for publication. Moreover, you must include in any reviewed version of your manuscript the modified 'Code and Data Availability' section with all the new information requested.
Juan A. AñelGeosci. Model Dev. Exec. EditorCitation: https://doi.org/10.5194/egusphere-2022-618-CEC1 -
CC1: 'Reply on CEC1', Matjaz Licer, 22 Sep 2022
Dear Editor,
thank you for bringing these issues to our attention - we will gladly comply with stated request as soon as possible. Unfortunately some of the authors needed for a full response are unavailable/unreachable until the end of next week so we will not be able to finalize our amendments until then. This will however be our first and top priority. I hope this delay is not an issue, otherwise we are open to further suggestions.
Best regards,
Matjaz Licer
Citation: https://doi.org/10.5194/egusphere-2022-618-CC1 -
CC2: 'Reply on Editor comment. License and Input Training/Testing datasets.', Matjaz Licer, 30 Sep 2022
Point-by-point reply to issues raised by the GMD editor:
GMD: - First, regarding code: the Hidra 2 model does not have a license listed. If you do not include a license, despite you publishing it, the code is not available to use by anyone; it continues to be your property. Therefore, add a license to your code in Zenodo. You could want to choose a free software/open-source (FLOSS) license. We recommend the GPLv3. You only need to include the file 'https://www.gnu.org/licenses/gpl-3.0.txt' as LICENSE.txt with your code. Also, you can choose other options that Zenodo provides: GPLv2, Apache License, MIT License, etc.
Authors’ reply:
We have added a licence file to the repository.
GMD: - Secondly, you use the UTIDE package. However, this package is stored on GitHub, as you mention in the list of References. UTIDE is released under the MIT license so that you can copy it. Therefore, as GitHub is not a suitable repository (GitHub itself instructs authors to use other alternatives for long-term archival and publishing, such as Zenodo), please, publish UTIDE (maintaining the MIT license) in one of the appropriate repositories, and reply to this comment with the relevant information (link and DOI).
Authors’ reply:
Utide package, used in the manuscript, is now uploaded to Zenodo under MIT license.
link: https://zenodo.org/record/7103894
DOI: https://doi.org/10.5281/zenodo.7103894
- Also, your manuscript is about a learning method. As this technique heavily depends on the input data, and the reproducibility of the work is compromised without it, we request that you publish in the repositories for your paper the input and output files used in your work. In the Code and Data Availability section, you mention in a generic way the MARS retrieval system. This is not enough. You must publish the specific data used as input. If variables are taken from a larger file, you can post simply the input data taken from them and used. For outputs, nothing prevents you from publishing them.
Authors ‘reply:
We have published the entire processed input training and test datasets for HIDRA2 at the following location:
link: https://zenodo.org/record/7123911
DOI: https://doi.org/10.5281/zenodo.7123910
Note these are not the original ECMWF ensemble fields but rather a substantially coarsened and processed fields - original fields are only available via MARS system request specifications AREA="46./5./35./21.", GRID="0.125/0.125", STEP="00/to/72/by/1", PARAMS="165.128/166.128/167.128/151.128", NUMBER="1/to/50", TIMES="00".
We have also updated the repository to include HIDRA2 predictions on the test set, and refined instructions on how to train and evaluate HIDRA2 on the published data. The repository is available here:
link: https://github.com/rusmarko/HIDRA2
DOI: https://doi.org/10.5281/zenodo.6784842
We will add this information to the revised version of the manuscript.
Finally, you use the NEMO model. However, you do not provide the NEMO code. You simply cite a pdf file, listed in the references, stored in a webpage that is not a trustable repository. Also, you do not identify the NEMO version used for your work. All these issues must be fixed. First, you must clearly state in your manuscript the NEMO version that you use. Then you must provide in the Code and Data Availability section a link to a trustable repository containing it. Many papers on the development of NEMO have been published in our journal, and in this way many NEMO versions are already stored in Zenodo. You could want to check if it is the case of the version you have used and simply cite its current Zenodo repository. If not, please, create a new one.
Authors’ reply:
We are using the Copernicus Marine Environment and Monitoring Service (CMEMS) operational forecasting product which is publicly available and based on NEMO v3.6 (https://doi.org/10.25423/CMCC/MEDSEA_ANALYSISFORECAST_PHY_006_013_EAS6). We are not running the NEMO model ourselves for this particular study. However, a regional setup of NEMO v3.6, which officially ships with NEMOGCM code (https://www.nemo-ocean.eu/), is available at the following repository:
Link: https://zenodo.org/record/4022310
Doi: https://doi.org/10.5281/zenodo.4022309
We will include the version number in the revised manuscript and we will remove the untrusted documentation pdf address and replace it by the official Copernicus documentation doi for the used sea level product: https://doi.org/10.25423/CMCC/MEDSEA_ANALYSISFORECAST_PHY_006_013_EAS6 .
Please, reply as soon as possible to this comment with all the information requested above, so it is available for the Discussions process as it should be. Note that your manuscript should have never been accepted for Discussions with all the mentioned flaws, this was an oversight from the Topical Editor, and we are trying to fix it now. Also, please, be aware that failing to comply with this request could result in rejecting your manuscript for publication. Moreover, you must include in any reviewed version of your manuscript the modified 'Code and Data Availability' section with all the new information requested.
Authors’ reply: Thank you, we will include this information in any revised version of the manuscript.
Citation: https://doi.org/10.5194/egusphere-2022-618-CC2
-
CC1: 'Reply on CEC1', Matjaz Licer, 22 Sep 2022
-
RC1: 'Comment on egusphere-2022-618', Anonymous Referee #1, 25 Sep 2022
The manuscript is great in its approach and compares with previous models. The application of the work is also in a major area of concern. Adding a bit more technical details to the manuscript will be good for the readership of the article.
Citation: https://doi.org/10.5194/egusphere-2022-618-RC1 -
AC1: 'Reply on RC1', Marko Rus, 14 Nov 2022
The comment was uploaded in the form of a supplement: https://egusphere.copernicus.org/preprints/2022/egusphere-2022-618/egusphere-2022-618-AC1-supplement.pdf
-
AC1: 'Reply on RC1', Marko Rus, 14 Nov 2022
-
RC2: 'Comment on egusphere-2022-618', Anonymous Referee #2, 10 Oct 2022
This manuscript presents a new deep-learning storm surge forecasting (HIDRA2) for the Northern Adriatic which is an “updated” version of a previous deep learning architecture HIDRA1. The authors show that HIDRA2 outperforms its previous version HIDRA1 and it also performs better that the Copernicus Mediterranean Reanalysis. The paper is well written, and I think it must be published after some minor changes.
Major comment:
The authors compare their new HIDRA2 with CMEMS Reanalysis, that is a 3D model in a regular horizontal grid. I recommend to the authors to compare the performance of HIDRA2 against numerical simulations specifically design to determine the sea surface elevation. As examples, the authors may use the global simulation by Muis et al. (2020) which has, in the Mediterranean, a 1.25 km of coastal resolution; or they can use the newest available simulation performed by Toomey et al. (2022) specifically designed for the Mediterranean Sea with a coastal resolution of 200 m. The latest hindcast includes the wave setup component that maybe relevant when computing the total elevation in the studied area.
Minor comments:
- The authors use the term storm surge to refer to the combined effect of atmospheric pressure, winds, and astronomic tides. I strongly recommend the authors to follow the terminology detailed in Gregory et al. (2019). In that paper, they write: “N9 Storm surge: The elevation or depression of the sea surface with respect to the predicted tide during a storm.” And they also write: “Sea-surface height (SSH) can be greatly elevated during a storm by a storm surge, and the consequent extreme sea level is sometimes called a storm tide”. So, the combination of storm surge + astronomical tide should be referred as storm tide, if we decide to follow the definitions in Gregory et al. (2019).
- Line 17: this line needs, at least, two references where I have included (Ref. XXXX): “Global mean sea level rise, related to anthropogenic climate change (Ref. XXXX), is causing a worldwide increase in coastal flooding frequency and is leading to a myriad of negative consequences for coastal communities, civil safety and economies (Ref. XXXX).”
- Fig. 1: Please change the title of the figure to “Adriatic Sea topo-bathymetry”.
- Line 35-36: put the citation to Medvedev between parentheses.
- Line 48: “HIDRA1 ensemble (Žust et al., 2021) is a million times faster than the operational numerical ocean model ensemble based on NEMO engine”. Although it maybe true, it is not fair to compare the computational time of a 3D model that computes water dynamics (currents, temperatures, salinities, …) in several vertical layers with HIDRA1 or HIDRA2 that gives SSH information only and in a single point. The authors should compare the computational time with, for example Muis et al. (2020) or Toomey et al. (2022), and multiply their computational time by the number of nodes that the other two studies are computing.
-Fig. 10: it is difficult to appreciate the differences between the different datasets. I would recommend the authors to apply a filter to the spectrum. There may be a newer reference but I usually do it following the Chapter 5- Time-series Analysis Methods (https://www.sciencedirect.com/science/article/pii/B978044450756350006X) from Data Analysis Methods in Physical Oceanography by Emery and Thomson.
Some thoughts:
1) Could this system be scaled up and applied to estimate SSH values at a Mediterranean scale?
2) How does the predictability change if the system is fed with the first predicted day?
References:
Gregory, J.M., Griffies, S.M., Hughes, C.W. et al. Concepts and Terminology for Sea Level: Mean, Variability and Change, Both Local and Global. Surv Geophys 40, 1251–1289 (2019). https://doi.org/10.1007/s10712-019-09525-z
Muis S., Apecechea M. I., Dullaart J., de Lima Rego J., Madsen K. S., Su J., et al. (2020). A high-resolution global dataset of extreme sea levels, tides, and storm surges, including future projections. Front. Mar. Sci. 7. doi: 10.3389/fmars.2020.00263
Toomey, T., Amores, A., Marcos, M., & Orfila, A. Coastal sea levels and wind-waves in the Mediterranean Sea since 1950 from a high-resolution ocean reanalysis. Frontiers in Marine Science, 1873. doi: 10.3389/fmars.2022.991504
Citation: https://doi.org/10.5194/egusphere-2022-618-RC2 -
AC2: 'Reply on RC2', Marko Rus, 14 Nov 2022
The comment was uploaded in the form of a supplement: https://egusphere.copernicus.org/preprints/2022/egusphere-2022-618/egusphere-2022-618-AC2-supplement.pdf
-
AC2: 'Reply on RC2', Marko Rus, 14 Nov 2022
-
RC3: 'Comment on egusphere-2022-618', Anonymous Referee #3, 31 Oct 2022
This manuscript shows an implementation of a neural network (HYDRA2) to predict sea level at the Koper tidal station. This neural network is an improvement over HIDRA1 and it is compared to its predecessor and to a numerical ocean model NEMO. Particularly notable in this manuscript is the detailed validation of the performance of the model. I can recommend publishing this manuscript after minor changes.
To facilitate the reading of the manuscript and the interpretation of the figures and table I would recommend the captions clarify if the authors show an independent validation (data not used during training and not used for the optimization of hyperparameters, if this is the case) or validation with dependent data. Likewise I think it would be useful to mention this also with the skill scores mentioned in the abstract (starting at line 7) whether these error reductions are obtained from the independent test data or not.
I don’t not have any doubts about the scientific soundness of the results, but adding this information would help readers understand the results of the manuscript more quickly.
Minor comments:
Line 5: “single member of ECMWF atmospheric ensemble”: is this the central forecast or any single member (chosen at random)?
Line 47: “HIDRA1 ensemble (Žust et al., 2021) is a million times faster than the operational numerical ocean model ensemble based on NEMO engine (Madec, 2016) at Slovenian Environment Agency”: There is not a lot of context to understand this comparison. NEMO will provide you with a sea level estimate over the whole domain. Is this also the case for HIDRA1 or would it provide the sea-level for a single location?
Line 99: “HIDRA2 does not require explicit annotation of whether a location point belongs to land or sea, thus land masks are not generated.”
I am wondering if the land-sea mask would still be a useful feature to provide to the neural network as a wind over land would not generate seiches. I guess that the neural network compensates for this by learning the land-sea mask internally.
Line 103: “three-days prediction lead time” I think that your ML model will give in one application the full 3-day time series. Can you confirm? Or do you rather need to apply the ML model iteratively to obtain the 3-day time series? Can you also clarify this in the manuscript?
104: “full ECMWF three-day forecast” -> “full” refers to the full ensemble (i.e. all ensemble members)?
143: “prototype matching layer” Can you provide more information and a reference ?
section 4.1.1: this is an interesting and surprising result. Can the authors speculate why this is the case? (predicting full SSH leads to better results for extreme events). Could it be that the neural network internally limits its output range when working on anomalies? Do you expect this outcome to remain should one have more training data?
Section 4.1.2 “Ablation study”: can you clarify that you retrained the network for the different test cases (without tides encoder, without atmospheric encoder,..) or you do rather zero-out the output of the corresponding encoder without re-training.
Typo:
Line 205: 1°/24 -> 1/24 °
Citation: https://doi.org/10.5194/egusphere-2022-618-RC3 -
AC3: 'Reply on RC3', Marko Rus, 14 Nov 2022
The comment was uploaded in the form of a supplement: https://egusphere.copernicus.org/preprints/2022/egusphere-2022-618/egusphere-2022-618-AC3-supplement.pdf
-
AC3: 'Reply on RC3', Marko Rus, 14 Nov 2022
Peer review completion
Journal article(s) based on this preprint
Marko Rus et al.
Marko Rus et al.
Viewed
| HTML | XML | Total | BibTeX | EndNote | |
|---|---|---|---|---|---|
| 322 | 122 | 23 | 467 | 6 | 3 |
- HTML: 322
- PDF: 122
- XML: 23
- Total: 467
- BibTeX: 6
- EndNote: 3
Viewed (geographical distribution)
| Country | # | Views | % |
|---|
| Total: | 0 |
| HTML: | 0 |
| PDF: | 0 |
| XML: | 0 |
- 1
The requested preprint has a corresponding peer-reviewed final revised paper. You are encouraged to refer to the final revised version.
- Preprint
(2861 KB) - Metadata XML