GHGPSE-Net: A method towards spaceborne automated extraction of greenhouse-gas point sources using point-object-detection deep neural network

Pang, Yiguo; Hu, Denghui; Tian, Longfei; Gao, Shuang; Liu, Guohua

doi:10.5194/egusphere-2025-3631

Preprints

https://doi.org/10.5194/egusphere-2025-3631

Preprints

18 Aug 2025

| 18 Aug 2025

GHGPSE-Net: A method towards spaceborne automated extraction of greenhouse-gas point sources using point-object-detection deep neural network

Yiguo Pang, Denghui Hu, Longfei Tian, Shuang Gao, and Guohua Liu

Abstract. Point sources account for a large portion of anthropogenic greenhouse gas (GHG) emissions. Timely detection, localization, and quantification of these emissions are critical for supporting carbon neutrality efforts. Spaceborne monitoring satellites can provide essential concentration data for identifying point sources. However, existing methods often require human intervention and typically detect plume masks instead of source locations, limiting their utility for regulatory applications. In this study, we present GHGPSE-Net, a deep learning method for greenhouse gas point source extraction. GHGPSE-Net simultaneously performs detection, localization, and quantification of emissions, eliminating the need for traditional segmentation steps. To train and evaluate the model, we construct synthetic datasets using an atmospheric transport model and validate its accuracy against radiosonde profiles and satellite observations. GHGPSE-Net demonstrates desirable performance in the simulation data across detection (F₁-score of 0.96), subpixel-level localization and quantification (Pearson's correlation of 0.99, root mean square error of 89.9 tCO₂ hr^-1), tested on ideal instrument of 2 km × 2 km resolution with retrieval noise of 1.5 parts per million (ppm). The results also demonstrate considerable generalization of the proposed model when tested using two independent datasets. On the identified sources from OCO-3 spaceborne observations, GHGPSE-Net achieves a detection precision of 0.60, localization accuracy of 2.47 km, and a Pearson's R of 0.89 for quantification. The proposed method and datasets provide a valuable foundation for future research towards rapid and automated GHG point source extraction, offering critical data to support swift responses to abnormal emission events.

Received: 27 Jul 2025 – Discussion started: 18 Aug 2025

Publisher's note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this paper. While Copernicus Publications makes every effort to include appropriate place names, the final responsibility lies with the authors. Views expressed in the text are those of the authors and do not necessarily reflect the views of the publisher.

Download & links

Preprint (PDF, 7146 KB)

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 (7146 KB)

Supplement (14764 KB)

Download & links

The requested preprint has a corresponding peer-reviewed final revised paper. You are encouraged to refer to the final revised version.

Journal article(s) based on this preprint

27 Feb 2026

GHGPSE-Net: a method towards spaceborne automated extraction of greenhouse-gas point sources using point-object-detection deep neural network

Yiguo Pang, Denghui Hu, Longfei Tian, Shuang Gao, and Guohua Liu

Geosci. Model Dev., 19, 1683–1702, https://doi.org/10.5194/gmd-19-1683-2026,https://doi.org/10.5194/gmd-19-1683-2026, 2026

Short summary

Yiguo Pang, Denghui Hu, Longfei Tian, Shuang Gao, and Guohua Liu

Interactive discussion

Status: closed

RC1:
'Comment on egusphere-2025-3631', Anonymous Referee #1, 28 Sep 2025

The manuscript "GHGPSE-Net: A method towards spaceborne automated extraction of greenhouse-gas point sources using point-object-detection deep neural network" presents a novel deep learning framework and a large dataset for detecting and quantifying greenhouse gas (GHG) point sources from satellite imagery. The authors are the first to introduce the point object detection approach in this domain, which is very valuable and insightful for the GHG point source monitoring community, as it has the potential to integrate and simplify the processing complexity largely. The authors also demonstrate the feasibility of the model by evaluating it on two datasets, including authentic satellite observations. Though I anticipate more evaluations may be required on the upcoming moderate-resolution carbon monitoring satellites (e.g., CO2M and TanSat-2) to fully explore the potential. This work marks an important step towards automated GHG point source monitoring and has the potential to make a significant contribution to the GHG remote sensing community.
Minor suggestions:

(1-1) The dataset construction process, including WRF-GHG simulation, XCO2 construction and data augmentation, involves multiple scenarios, especially it seems that the model is trained on the synthetic dataset and evaluated using independent datasets. It may be better clarified using a diagram.

(1-2) The authors summarized GHGPSE-Net in Figure 3. However, the overall methodology, including simulation, simulation evaluation, training dataset preparation, and deep learning evaluation, is quite complex and somewhat difficult to follow. The authors may consider summarizing the entire methodology in Section 2.

(1-3) In some related GHG plume detection studies, deep learning models usually require wind as an input. Does GHGPSE-Net not require the 2D wind field as input?

(1-4) According to the result (e.g., Table 3), it seems the "2 km × 2 km" in L10 should be 0.5 km × 0.5km.
Technical comments:

(2-1) Typo in L59 and L137.

(2-2) It should be "mean squared error" instead of "mean square error" in L10, L208, and L223.

Citation: https://doi.org/10.5194/egusphere-2025-3631-RC1
- AC3: 'Reply on RC1', Yiguo Pang, 20 Oct 2025
  
  We sincerely thank the editor and reviewers for the valuable comments and suggestions. Our detailed point-by-point responses to reviewer #1 are attached in the PDF file.
  
  Citation: https://doi.org/10.5194/egusphere-2025-3631-AC3
CEC1:
'No compliance with the policy of the journal', Juan Antonio Añel, 11 Oct 2025

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.html
First of all, for the WRF code you link a GitHub site. However, GitHub is not a suitable repository for scientific publication. GitHub itself instructs authors to use other long-term archival and publishing alternatives.
Also, for many of the data sources you cite webpages that are not repositories. It is necessary that you store all the data that you have used in repositories that we can accept, with a DOI. This includes the CarbonTracker, IGRA, OCO3, etc.
Therefore, the current situation with your manuscript is irregular. Please, publish the WRF code and all the data in one of the appropriate repositories and reply to this comment with the relevant information (link and a permanent identifier for it (e.g. DOI)) as soon as possible, as we can not accept manuscripts in Discussions that do not comply with our policy. Also, you must include a modified 'Code and Data Availability' section containing the information of the new repositories, which you must include in a potentially reviewed manuscript too.
I must note that if you do not fix this problem, we cannot accept your manuscript for publication in our journal.
Juan A. Añel

Geosci. Model Dev. Executive Editor

Citation: https://doi.org/10.5194/egusphere-2025-3631-CEC1
- AC1:
  'Reply on CEC1', Yiguo Pang, 11 Oct 2025
  
  The comment was uploaded in the form of a supplement: https://egusphere.copernicus.org/preprints/2025/egusphere-2025-3631/egusphere-2025-3631-AC1-supplement.pdf
  
  Citation: https://doi.org/10.5194/egusphere-2025-3631-AC1
  - CEC2: 'Reply on AC1', Juan Antonio Añel, 11 Oct 2025
    
    Dear authors,
    Unfortunately, your reply does not solve the problems pointed out. You must store all the WRF model, not only the code that you have developed or modified. Also, for the data sources, you continue linking webpages that are not valid repositories (e.g., ucar.edu, European Comisssion webpages, etc.).
    Therefore, the problems remain and we can not consider your manuscript for publication in the journal.
    Juan A. Añel
    Geosci. Model Dev. Executive Editor
    
    Citation: https://doi.org/10.5194/egusphere-2025-3631-CEC2
    
    AC2: 'Reply on CEC2', Yiguo Pang, 16 Oct 2025
    
    Dear Dr. Añel,
    Thank you very much for your comments. I apologize for the delay of reply, as it takes some time to upload the software and data to Zenodo due to network issues.
    The WRF-GHG model, including all source codes, configurations, emission files, initial conditions, and boundary conditions has now been uploaded to a publicly available Zenodo repository:
    
    https://zenodo.org/records/17337441
    
    Anyone can download, compile and reproduce the results.
    All processing scripts have been provided previously in another Zenodo repository:
    
    https://zenodo.org/records/16751293
    External datasets that are not hosted on Zenodo or other acceptable repositories will be removed from the Data Availability section of the manuscript.
    
    The OCO-3 measurements, IGRA profiles and other necessary external datasets are stored in the Zenodo repository.
    Please contact me if any further clarification is needed.
    Best regards,
    
    Yiguo Pang
    
    Citation: https://doi.org/10.5194/egusphere-2025-3631-AC2
RC2:
'Comment on egusphere-2025-3631', Anonymous Referee #2, 14 Oct 2025
This work applies deep learning to satellite snapshots of CO2, performing point source detection, localisation and quantification. As the authors identify, most work in this area focuses on plume identification or source location, without performing quantification directly. The authors present an innovative solution, where a CNN is trained to identify sources as hotspots, which then get detected and quantified using a statistical Gaussian Kernel fitting method. The authors also introduce a greenhouse-specific augmentation method, varying the linear coefficients for each source, that presents a valuable contribution to the area of GHG+deep learning. The authors demonstrate their model on a wide range of observations and instruments, using also independent validation tests for verification. I believe that the work presents a significant contribution to the ML-remote sensing field, with some further clarifications on the method.
Clarifications required:
The datasets used should be summarised more cohesively, as at the moment it is hard to follow 1) what regions, areas and time periods are covered for each dataset, 2) the number of samples in each dataset 3) whether the test datasets were augmented. The number of samples added in the augmentation needs to be specified.

The architecture of the model needs to be outlined more clearly, including how it was tuned, the learning rate, loss functions etc.

It is not clear to me if the resolution of the model was kept constant across the different instruments, or adapted to each instrument.

Is it possible that the significantly lower skill on the SMARTCARB dataset is due to a different transport model?

Would other inputs to the CNN, like the wind direction or the location of known sources, improve predictive skill?

The Gaussian kernel fitting is demonstrated to improve when the kernel size is the same as the instrument pixel size, for the one instrument tested. Do you expect performance to improve for other instruments when the same process is applied? It is not clear what kernel size you applied for evaluation for each instrument.

Typos and minor corrections:
Figure 5 shows, from the text, two days with large absolute errors. Clarify in the caption/figure labelling that these two days are not representative of the usual error distribution.

Line 39 (“and The new generation…”)

Line 151: areas (not area)

L342

Supplement S3.1, title: Definition (not defination)
Citation: https://doi.org/10.5194/egusphere-2025-3631-RC2
- AC4: 'Reply on RC2', Yiguo Pang, 20 Oct 2025
  
  We sincerely thank the editor and reviewers for the valuable comments and suggestions. Our detailed point-by-point responses to reviewer #2 are attached in the PDF file.
  
  Citation: https://doi.org/10.5194/egusphere-2025-3631-AC4

Interactive discussion

Status: closed

RC1:
'Comment on egusphere-2025-3631', Anonymous Referee #1, 28 Sep 2025

The manuscript "GHGPSE-Net: A method towards spaceborne automated extraction of greenhouse-gas point sources using point-object-detection deep neural network" presents a novel deep learning framework and a large dataset for detecting and quantifying greenhouse gas (GHG) point sources from satellite imagery. The authors are the first to introduce the point object detection approach in this domain, which is very valuable and insightful for the GHG point source monitoring community, as it has the potential to integrate and simplify the processing complexity largely. The authors also demonstrate the feasibility of the model by evaluating it on two datasets, including authentic satellite observations. Though I anticipate more evaluations may be required on the upcoming moderate-resolution carbon monitoring satellites (e.g., CO2M and TanSat-2) to fully explore the potential. This work marks an important step towards automated GHG point source monitoring and has the potential to make a significant contribution to the GHG remote sensing community.
Minor suggestions:

(1-1) The dataset construction process, including WRF-GHG simulation, XCO2 construction and data augmentation, involves multiple scenarios, especially it seems that the model is trained on the synthetic dataset and evaluated using independent datasets. It may be better clarified using a diagram.

(1-2) The authors summarized GHGPSE-Net in Figure 3. However, the overall methodology, including simulation, simulation evaluation, training dataset preparation, and deep learning evaluation, is quite complex and somewhat difficult to follow. The authors may consider summarizing the entire methodology in Section 2.

(1-3) In some related GHG plume detection studies, deep learning models usually require wind as an input. Does GHGPSE-Net not require the 2D wind field as input?

(1-4) According to the result (e.g., Table 3), it seems the "2 km × 2 km" in L10 should be 0.5 km × 0.5km.
Technical comments:

(2-1) Typo in L59 and L137.

(2-2) It should be "mean squared error" instead of "mean square error" in L10, L208, and L223.

Citation: https://doi.org/10.5194/egusphere-2025-3631-RC1
- AC3: 'Reply on RC1', Yiguo Pang, 20 Oct 2025
  
  We sincerely thank the editor and reviewers for the valuable comments and suggestions. Our detailed point-by-point responses to reviewer #1 are attached in the PDF file.
  
  Citation: https://doi.org/10.5194/egusphere-2025-3631-AC3
CEC1:
'No compliance with the policy of the journal', Juan Antonio Añel, 11 Oct 2025

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.html
First of all, for the WRF code you link a GitHub site. However, GitHub is not a suitable repository for scientific publication. GitHub itself instructs authors to use other long-term archival and publishing alternatives.
Also, for many of the data sources you cite webpages that are not repositories. It is necessary that you store all the data that you have used in repositories that we can accept, with a DOI. This includes the CarbonTracker, IGRA, OCO3, etc.
Therefore, the current situation with your manuscript is irregular. Please, publish the WRF code and all the data in one of the appropriate repositories and reply to this comment with the relevant information (link and a permanent identifier for it (e.g. DOI)) as soon as possible, as we can not accept manuscripts in Discussions that do not comply with our policy. Also, you must include a modified 'Code and Data Availability' section containing the information of the new repositories, which you must include in a potentially reviewed manuscript too.
I must note that if you do not fix this problem, we cannot accept your manuscript for publication in our journal.
Juan A. Añel

Geosci. Model Dev. Executive Editor

Citation: https://doi.org/10.5194/egusphere-2025-3631-CEC1
- AC1:
  'Reply on CEC1', Yiguo Pang, 11 Oct 2025
  
  The comment was uploaded in the form of a supplement: https://egusphere.copernicus.org/preprints/2025/egusphere-2025-3631/egusphere-2025-3631-AC1-supplement.pdf
  
  Citation: https://doi.org/10.5194/egusphere-2025-3631-AC1
  - CEC2: 'Reply on AC1', Juan Antonio Añel, 11 Oct 2025
    
    Dear authors,
    Unfortunately, your reply does not solve the problems pointed out. You must store all the WRF model, not only the code that you have developed or modified. Also, for the data sources, you continue linking webpages that are not valid repositories (e.g., ucar.edu, European Comisssion webpages, etc.).
    Therefore, the problems remain and we can not consider your manuscript for publication in the journal.
    Juan A. Añel
    Geosci. Model Dev. Executive Editor
    
    Citation: https://doi.org/10.5194/egusphere-2025-3631-CEC2
    
    AC2: 'Reply on CEC2', Yiguo Pang, 16 Oct 2025
    
    Dear Dr. Añel,
    Thank you very much for your comments. I apologize for the delay of reply, as it takes some time to upload the software and data to Zenodo due to network issues.
    The WRF-GHG model, including all source codes, configurations, emission files, initial conditions, and boundary conditions has now been uploaded to a publicly available Zenodo repository:
    
    https://zenodo.org/records/17337441
    
    Anyone can download, compile and reproduce the results.
    All processing scripts have been provided previously in another Zenodo repository:
    
    https://zenodo.org/records/16751293
    External datasets that are not hosted on Zenodo or other acceptable repositories will be removed from the Data Availability section of the manuscript.
    
    The OCO-3 measurements, IGRA profiles and other necessary external datasets are stored in the Zenodo repository.
    Please contact me if any further clarification is needed.
    Best regards,
    
    Yiguo Pang
    
    Citation: https://doi.org/10.5194/egusphere-2025-3631-AC2
RC2:
'Comment on egusphere-2025-3631', Anonymous Referee #2, 14 Oct 2025
This work applies deep learning to satellite snapshots of CO2, performing point source detection, localisation and quantification. As the authors identify, most work in this area focuses on plume identification or source location, without performing quantification directly. The authors present an innovative solution, where a CNN is trained to identify sources as hotspots, which then get detected and quantified using a statistical Gaussian Kernel fitting method. The authors also introduce a greenhouse-specific augmentation method, varying the linear coefficients for each source, that presents a valuable contribution to the area of GHG+deep learning. The authors demonstrate their model on a wide range of observations and instruments, using also independent validation tests for verification. I believe that the work presents a significant contribution to the ML-remote sensing field, with some further clarifications on the method.
Clarifications required:
The datasets used should be summarised more cohesively, as at the moment it is hard to follow 1) what regions, areas and time periods are covered for each dataset, 2) the number of samples in each dataset 3) whether the test datasets were augmented. The number of samples added in the augmentation needs to be specified.

The architecture of the model needs to be outlined more clearly, including how it was tuned, the learning rate, loss functions etc.

It is not clear to me if the resolution of the model was kept constant across the different instruments, or adapted to each instrument.

Is it possible that the significantly lower skill on the SMARTCARB dataset is due to a different transport model?

Would other inputs to the CNN, like the wind direction or the location of known sources, improve predictive skill?

The Gaussian kernel fitting is demonstrated to improve when the kernel size is the same as the instrument pixel size, for the one instrument tested. Do you expect performance to improve for other instruments when the same process is applied? It is not clear what kernel size you applied for evaluation for each instrument.

Typos and minor corrections:
Figure 5 shows, from the text, two days with large absolute errors. Clarify in the caption/figure labelling that these two days are not representative of the usual error distribution.

Line 39 (“and The new generation…”)

Line 151: areas (not area)

L342

Supplement S3.1, title: Definition (not defination)
Citation: https://doi.org/10.5194/egusphere-2025-3631-RC2
- AC4: 'Reply on RC2', Yiguo Pang, 20 Oct 2025
  
  We sincerely thank the editor and reviewers for the valuable comments and suggestions. Our detailed point-by-point responses to reviewer #2 are attached in the PDF file.
  
  Citation: https://doi.org/10.5194/egusphere-2025-3631-AC4

Peer review completion

AR – Author's response | RR – Referee report | ED – Editor decision | EF – Editorial file upload

AR by Yiguo Pang on behalf of the Authors (23 Nov 2025) Author's response Author's tracked changes Manuscript

ED: Reconsider after major revisions (01 Dec 2025) by Luke Western

AR by Yiguo Pang on behalf of the Authors (09 Dec 2025) Author's response Author's tracked changes Manuscript

ED: Referee Nomination & Report Request started (15 Dec 2025) by Luke Western

RR by Anonymous Referee #1 (22 Dec 2025)

Suggestions for revision or reasons for rejection

The authors have adequately addressed the major concerns raised in the previous round of review, and the overall quality of the manuscript has been significantly improved. I have no further major comments on the scientific content or the methodology. However, the manuscript requires a final round of careful proofreading to ensure professional presentation. There are several grammatical inconsistencies and typographical errors that need to be addressed before publication.
1.Line 45: "...equipped with a Onboard intelligent..." should be corrected to "an Onboard".
2.Line 52: "...model referred GHGPSE-Net..." should be corrected to "...model referred to as GHGPSE-Net...".
3.Line 72: "...spatial-temporal limited dataset..." would be better phrased as "spatiotemporally limited dataset" or "spatially and temporally limited dataset".
4.Line 155: "Here, |Ibg| denote the mean concentration..." Subject-verb agreement error. It should be "denotes".
5.Line 190: "Deep neural network is a class..." should be "A deep neural network is a class..." or "Deep neural networks are a class...".
6.Line 252 (Eq. 7): Ensure the formatting of the condition "ai≥0" is consistent with the text.
7.Line 306: "...which is generated..." (Check tense consistency with the rest of the paragraph).
8.Line 363: "...metrics reach maximum with..." suggest changing to "...reach a maximum..." or "...reach their peak...".
9.Line 365 (Figure 6 Caption): "The observation timestamps are provided in UTC." – This is clear, but ensure the x-axis labels in Figure 6 are legible.Line 370: "...extract emission source." should be plural: "...extract emission sources."
10.Line 381: "...increases the localization performance..." – phrasing is acceptable, but "improves" might be more natural than "increases" for performance.
11.Figure 5 (Y-axis label): The label "Temperautre error[K]" contains a spelling error. It should be "Temperature".
12.Line 304: "SMARTCARAB" is a typo. It should be "SMARTCARB".
13.Line 613: "1.2 to 1.6 6 ktCO2 hr-1". There appears to be a stray digit "6" before the unit.
14.ine 776: "...more sptial context..." is a typo. It should be "spatial".
15.Please ensure that the citation style for "et al." is consistent throughout the manuscript (e.g., Line 51 vs Line 136).

Hide

RR by Anonymous Referee #2 (09 Feb 2026)

Suggestions for revision or reasons for rejection

Dear authors and GMD team,
Most of my comments have been addressed satisfactorily. There are a few items that are still left to clarify in my view:
1) According to the authors, the augmented datasets are split "into training, validation, and testing sets in a 3:1:1 ratio". The authors do not specify if this split is random, and if so, any potential consequences of this - i.e. whether the model achieves high scores due to skill, or due to the test samples being very similar to the training ones. Testing on unseen OCO-3 and SmartCarb samples is a significantly better test of skill - for example comparing performance of the model on the test set of synthetic OCO-3 augmented samples, vs true OCO-3 observations shows a decrease in performance. There is no assessment of the skill of the model on the augmented dataset with SMARTCAB specific noise, so this comparison is not possible.

2) I would like clarification on why, from the OCO-3 dataset, only eight observations with a clear background are selected.

3) The distributions you use for data augmentation, described in 2.1.3, are shown in the Supplement, which is very helpful. However this is not mentioned in the text.

4) Kernel size is a parameter investigated through the paper, but it is not defined explicitly. Is it the sigma in equation 5, labelled below "the spatial extent"? Refer to the parameter consistently as "kernel size" for clarity.

5) You evaluate the models with and without GKF, but don't address explicitly how the locations and emissions rate is calculated without GKF.

6) typos and minor corrections:
line 161 - "Each mean e_{ps,i} is sampled [...]" I assume you mean each individual e_{ps,i} is sampled from the inventory, and the mean calculated from this sample
line 314 - remove "on the generalization"
line 322 - SMARTCARB instead of SMARTCARAB

Hide

ED: Publish subject to minor revisions (review by editor) (09 Feb 2026) by Luke Western

AR by Yiguo Pang on behalf of the Authors (18 Feb 2026) Author's response Author's tracked changes Manuscript

ED: Publish subject to technical corrections (18 Feb 2026) by Luke Western

AR by Yiguo Pang on behalf of the Authors (19 Feb 2026) Author's response Manuscript

Post-review adjustments

AA – Author's adjustment | EA – Editor approval

AA by Yiguo Pang on behalf of the Authors (24 Feb 2026) Author's adjustment Manuscript

EA: Adjustments approved (24 Feb 2026) by Luke Western

Journal article(s) based on this preprint

27 Feb 2026

GHGPSE-Net: a method towards spaceborne automated extraction of greenhouse-gas point sources using point-object-detection deep neural network

Yiguo Pang, Denghui Hu, Longfei Tian, Shuang Gao, and Guohua Liu

Geosci. Model Dev., 19, 1683–1702, https://doi.org/10.5194/gmd-19-1683-2026,https://doi.org/10.5194/gmd-19-1683-2026, 2026

Short summary

Yiguo Pang, Denghui Hu, Longfei Tian, Shuang Gao, and Guohua Liu

Supplement

https://doi.org/10.5194/egusphere-2025-3631-supplement

Data sets

Source code for "GHGPSE-Net: A method towards spaceborne automated extraction of greenhouse-gas point sources using point-object-detection deep neural network" Yiguo Pang https://zenodo.org/records/16751293

Model code and software

Yiguo Pang, Denghui Hu, Longfei Tian, Shuang Gao, and Guohua Liu

Viewed

Total article views: 2,267 (including HTML, PDF, and XML)

HTML	PDF	XML	Total	Supplement	BibTeX	EndNote
1,966	249	52	2,267	106	38	35

HTML: 1,966
PDF: 249
XML: 52
Total: 2,267
Supplement: 106
BibTeX: 38
EndNote: 35

Views and downloads (calculated since 18 Aug 2025)

Month	HTML	PDF	XML	Total
Aug 2025	439	13	4	456
Sep 2025	1,249	19	7	1,275
Oct 2025	145	43	18	206
Nov 2025	46	24	7	77
Dec 2025	33	62	6	101
Jan 2026	30	61	6	97
Feb 2026	24	27	4	55

Cumulative views and downloads (calculated since 18 Aug 2025)

Month	HTML	PDF	XML	Total
Aug 2025	439	13	4	456
Sep 2025	1,249	19	7	1,275
Oct 2025	145	43	18	206
Nov 2025	46	24	7	77
Dec 2025	33	62	6	101
Jan 2026	30	61	6	97
Feb 2026	24	27	4	55

Viewed (geographical distribution)

Total article views: 2,220 (including HTML, PDF, and XML) Thereof 2,220 with geography defined and 0 with unknown origin.

Country	#	Views	%

Latest update: 27 Feb 2026

Download

The requested preprint has a corresponding peer-reviewed final revised paper. You are encouraged to refer to the final revised version.

Preprint (7146 KB)
Metadata XML

Short summary

Satellites can reveal greenhouse gas point sources, but current point source extraction methods rely on manual inspection. We developed a point-object-detection-based deep learning method for fast, automated detection and quantification of these sources. The model was trained on a large synthetic dataset and tested for generalization using two independent datasets, including simulations and satellite observations.


Total:	0
HTML:	0
PDF:	0
XML:	0