the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
| 20 Aug 2025
A High-Precision Satellite XCH4 Inversion Method Using CBAM-ResNet18
Abstract. Amid global climate change, rising atmospheric methane (CH4) concentrations significantly influence the climate system, contributing to temperature increases and atmospheric chemistry changes. Accurate monitoring of these concentrations is essential to support global methane emission reduction goals, such as those outlined in the Global Methane Pledge targeting a 30 % reduction by 2030. Satellite remote sensing, offering high precision and extensive spatial coverage, has become a critical tool for measuring large-scale atmospheric methane concentrations. However, traditional physical inversion models face challenges, including high computational complexity, low processing efficiency, and inadequate incorporation of spatial distribution information, limiting their effectiveness. To address these shortcomings, this study proposes a high-precision XCH4 inversion method that integrates the Convolutional Block Attention Module (CBAM) with the ResNet18 neural network (CBAM-ResNet18). By leveraging shortwave infrared spectral data from the Sentinel-5P satellite and the CAMS reanalysis dataset, this approach achieves rapid and accurate XCH4 inversion. Experimental results demonstrate that the method outperforms both conventional physical models and existing mainstream techniques in terms of inversion accuracy and computational efficiency. It achieves an error of less than 2 %, meeting the stringent precision requirements for XCH4 in atmospheric remote sensing and providing a robust tool for methane monitoring.
- Preprint
(1016 KB) - Metadata XML
- BibTeX
- EndNote
Interactive discussion
Status: closed
-
RC1: 'Comment on egusphere-2025-3885', Anonymous Referee #1, 22 Sep 2025
-
AC1: 'Reply on RC1', Yong Wan, 25 Sep 2025
Dear Reviewer,
Thank you for your careful review and constructive feedback on our manuscript. We greatly appreciate your expertise and the time you invested in providing detailed comments. Your observations highlight important aspects of our work that will help enhance the scientific rigor of the paper. Below, we address each point raised in your overall comments and major concerns. We have carefully considered your suggestions and outlined planned revisions where appropriate, providing clarifications where necessary:
1. Training Strategy:
We appreciate the reviewer raising this critical point regarding our use of interpolated coarse-resolution CAMS reanalysis data as the training target, while the model input consists of high-resolution TROPOMI spectral data. To further clarify the necessity and rationale of our approach: The primary objective of our CBAM-ResNet18 model is not to fully replace CAMS, but to develop an efficient, data-driven simulator that bridges raw TROPOMI L1B spectral observations with reliable XCH₄ estimates while incorporating the spatial context of high-resolution inputs. Several compelling reasons based on data quality, bias mitigation, and methodological advantages justify selecting CAMS reanalysis data as the training target:
(1) CAMS integrates a comprehensive collection of global observations (including satellite, ground-based, and in-situ data) with advanced chemical transport modeling, providing a more robust and bias-corrected XCH₄ representation than the standalone TROPOMI L2 product. Existing studies indicate that TROPOMI L2 XCH₄ may exhibit regional biases due to errors in prior conditions within the inversion algorithm, such as surface reflectance priors and aerosol corrections. By training on CAMS, our model learns a more accurate target, focusing on spectral features relevant to real atmospheric variability. Our experiments comparing results against TCCON ground data also validate that this approach yields more accurate results than TROPOMI L2 XCH4.
(2) Although CAMS has coarse resolution, our input preprocessing explicitly addresses this by cropping TROPOMI L1B data into 3×3 spatial blocks. This enables the model to capture subgrid heterogeneity (e.g., local emission hotspots) smoothed out by CAMS. The CBAM module further amplifies this by selectively focusing on spatial and spectral features within the high-resolution spectrum, allowing the model to “upsample” fine details onto the CAMS grid cells rather than simply reproducing their smoothing.
(3) While our data filtering step utilizes the TROPOMI L2 product XCH4, this is solely for a convenient method to screen high-quality TROPOMI spectral samples during model training. This step is not required for the model's practical application.
We acknowledge that our methodology may warrant more detailed elaboration, but we do not plan significant modifications to the core approach. Our objective is to surpass TROPOMI's L2 product XCH4 in both inversion efficiency and accuracy. Using TROPOMI's L2 product XCH4 as the training target would substantially diminish the research's necessity, and the inversion accuracy would likely not exceed that of the product. Nevertheless, to address your concerns, we will expand our explanation in Section 2, detailing why CAMS was chosen as the training target instead of TROPOMI's L2 product XCH4.
2. Model Performance:
We appreciate the reviewer's emphasis on the need for explicit data coverage details, a larger sample size, and more comprehensive metrics. We also note your observation of “flat” scatter plots in Figures 6 and 7, which may suggest low sensitivity to XCH4 variability. Upon re-examination, this result stems from the narrow dynamic range of XCH4 in our selected validation subset (1840–1850 ppb globally during June 2020), where natural variability was moderate (approximately 10 ppb), leading to y-axis compression. However, RMSE/MAE values (e.g., 9.96 ppb relative to CAMS, 5.68–17.6 ppb relative to TCCON) indicate that relative accuracy within this range is not low, and spatial visualizations of the model (Figure 5) confirm its ability to resolve subtle gradients.
To strengthen the persuasiveness of this section's experiments and enhance the model's generalization capability, we plan to implement the following modifications:
(1) To mitigate the small sample size, we will expand the dataset by incorporating more TROPOMI orbits and extending coverage to a global scale, followed by retraining the model.
(2) To comprehensively evaluate the accuracy of experimental results, we will add correlation coefficients (r) and coefficient of determination (R²) to all scatter plots (Figures 6 and 7).
3. Comparison with Other Methods:
We appreciate the reviewer's feedback and acknowledge that our previous description of the “optimal estimation” method was indeed overly broad. In the revised manuscript, we have provided further details on the method's configuration: Specifically, we employ the SCIATRAN radiative transfer model as the forward model, with CH₄ prior profiles derived from spatiotemporally interpolated CH₄ profiles from the CAMS reanalysis product; Additionally, other key parameters include surface albedo and temperature/humidity profiles provided by the ERA5 reanalysis dataset. All other parameters are configured according to SCIATRAN's default settings. We believe this supplementary information enhances the method's transparency and reproducibility.
We understand the reviewer's concern regarding the citation source for the “improved spatial inversion method.” This method was originally derived from a master's thesis within our team. While the thesis underwent rigorous academic defense and peer review procedures, as you noted, theses may be less accessible and subject to less stringent review compared to formal journal articles. Therefore, in the revised manuscript, we plan to add citations to relevant journal articles on “spatial inversion methods” and provide further clarification on the specific principles of the “improved spatial inversion method.” The forward model, prior data, and other parameters of this method remain consistent with the “optimal estimation” approach.
4. Lack of Discussion Section:
We fully agree with the reviewer's feedback that a dedicated discussion section is essential for contextualizing our contributions, implications, and limitations. While we combined the discussion with experimental analysis in a subsection, the discussion was indeed insufficient. In the revised manuscript, we plan to insert a new subsection before the conclusions to discuss experimental results. This section will include feature importance analysis based on SHAP values to identify which input features most significantly impact model predictions, thereby enhancing model interpretability.Citation: https://doi.org/10.5194/egusphere-2025-3885-AC1
-
AC1: 'Reply on RC1', Yong Wan, 25 Sep 2025
-
AC2: 'Comment on egusphere-2025-3885', Yong Wan, 13 Nov 2025
We are writing to formally request the withdrawal of our manuscript titled “A High-Precision Satellite XCH4 Inversion Method Using CBAM-ResNet18” (submission ID: EGUsphere-2025-3885, submitted on 9 August 2025).
We sincerely appreciate the time and effort that the editorial team have dedicated to handling our manuscript. However, due to unforeseen delays in the review process—particularly the challenges in securing a second reviewer—we feel it is in the best interest of our work to seek alternative opportunities for publication at this time.Citation: https://doi.org/10.5194/egusphere-2025-3885-AC2 -
RC2: 'Comment on egusphere-2025-3885', Anonymous Referee #2, 13 Nov 2025
The comment was uploaded in the form of a supplement: https://egusphere.copernicus.org/preprints/2025/egusphere-2025-3885/egusphere-2025-3885-RC2-supplement.pdf
-
AC3: 'Reply on RC2', Yong Wan, 14 Nov 2025
Thank you very much for handling our submission and for sending us the valuable and detailed comments from the reviewers. We sincerely appreciate the time and effort the reviewers have invested in providing this constructive feedback.
After carefully studying the reports, we realize that the current manuscript has several significant shortcomings that require substantial revision. To properly address the concerns raised and to meet the high standards of the journal, we believe it is necessary to fundamentally redesign parts of the study, including additional experiments and a major restructuring of the paper.
Given the extent of the required changes, we feel it would be inappropriate to proceed with the current version under review. Therefore, we kindly request to withdraw our manuscript EGUSPHERE-2025-3885 from further consideration at this time.
Citation: https://doi.org/10.5194/egusphere-2025-3885-AC3
-
AC3: 'Reply on RC2', Yong Wan, 14 Nov 2025
Interactive discussion
Status: closed
-
RC1: 'Comment on egusphere-2025-3885', Anonymous Referee #1, 22 Sep 2025
[General Comments]
This manuscript introduces a deep learning approach, CBAM-ResNet18, for retrieving column-averaged dry-air mole fraction of methane (XCH4) from TROPOMI satellite spectra. The topic is of considerable interest and falls well within the scope of Atmospheric Measurement Techniques. The goal of developing more efficient retrieval algorithms is an important one for the atmospheric and climate science community.
However, the study has several major issues that undermine its scientific quality. These include the model training strategy, unconvincing validation performance, insufficient detail in comparison between methods, and a lack of discussion on the model's limitations. For these reasons, the work does not meet the scientific standards required for publication in the AMT journal.
Major Concerns:
- Training strategy: The authors train their model, which uses high-resolution (~7 km) TROPOMI spectral data as input, with a coarse-resolution (~80 km) CAMS reanalysis product as the training target. The CAMS data is interpolated to match the TROPOMI grid, and this approach trains the model to emulate the interpolated CAMS reanalysis product, which enables the model to learn and reproduce the smooth, large-scale features of CAMS. This strategy raises significant concerns: 1) The machine learning (ML) model will also learn the inherent CAMS model biases, and cannot capture the fine-scale information that TROPOMI is capable of observing. 2) The importance of the ML model diminishes if its purpose is only to emulate the CAMS, since the CAMS product can already be delivered routinely. This is a critical conceptual issue that undermines the necessity of this ML model. Additionally, it is unclear to me why the authors don't use the existing TROPOMI L2 product XCH4 data as the training target, given that they have utilized this L2 product to assist with data filtration.
- Model performance: The manuscript does not clearly describe the geographic or temporal coverage of the training, validation, and test data. The small sample sizes (2244 for training, 647 for testing) are a concern for developing a generalizable deep learning model. More importantly, the validations against CAMS and TCCON data, shown in Figures 6 and 7, reveal unreliable model performance. Three scatter plots show "flattened" distributions where the model's predictions (y-axis) show little to no response to the actual variations in the CAMS result and TCCON measurements (x-axis). This suggests that the model has very low predictive power and is largely insensitive to XCH4 variability, contradicting the claims of “high precision” suggested by the RMSE and MAE metrics. Additionally, it is an oversight that standard metrics like the correlation coefficient (r) and coefficient of determination (R2) are not included on these plots.
- Comparison with Other Methods: The manuscript claims superiority over several other methods, but this comparison is neither transparent nor reproducible. The "Optimal estimation" method is described without any implementation details, as it is a broad framework, and its performance depends on the specific forward model, a-priori data, and other parameters used, none of which are detailed. Furthermore, the "Improved spatial inversion" method is cited from a Master's thesis, which is not a peer-reviewed source and is difficult for reviewers to access and evaluate. Without a detailed and transparent description of the benchmark methods, the comparative analysis lacks scientific validity, and the claims of superior performance remain unsubstantiated.
- Absence of the discussion section: The manuscript lacks a dedicated discussion section that reflects on the study's implications, despite some results being shown in Section 3. This section is critical to any scientific paper, as it provides a thorough discussion of the advancements that this work can bring to the community, along with an honest assessment of the potential weaknesses and sources of error in the methodology. For example, what is the implication of using the CAMS reanalysis product rather than the TROPOMI L2 product as the training target? What input features most influence the model prediction (i.e., model explainability)? This lack makes the manuscript incomplete for a scientific publication.
Citation: https://doi.org/10.5194/egusphere-2025-3885-RC1 -
AC1: 'Reply on RC1', Yong Wan, 25 Sep 2025
Dear Reviewer,
Thank you for your careful review and constructive feedback on our manuscript. We greatly appreciate your expertise and the time you invested in providing detailed comments. Your observations highlight important aspects of our work that will help enhance the scientific rigor of the paper. Below, we address each point raised in your overall comments and major concerns. We have carefully considered your suggestions and outlined planned revisions where appropriate, providing clarifications where necessary:
1. Training Strategy:
We appreciate the reviewer raising this critical point regarding our use of interpolated coarse-resolution CAMS reanalysis data as the training target, while the model input consists of high-resolution TROPOMI spectral data. To further clarify the necessity and rationale of our approach: The primary objective of our CBAM-ResNet18 model is not to fully replace CAMS, but to develop an efficient, data-driven simulator that bridges raw TROPOMI L1B spectral observations with reliable XCH₄ estimates while incorporating the spatial context of high-resolution inputs. Several compelling reasons based on data quality, bias mitigation, and methodological advantages justify selecting CAMS reanalysis data as the training target:
(1) CAMS integrates a comprehensive collection of global observations (including satellite, ground-based, and in-situ data) with advanced chemical transport modeling, providing a more robust and bias-corrected XCH₄ representation than the standalone TROPOMI L2 product. Existing studies indicate that TROPOMI L2 XCH₄ may exhibit regional biases due to errors in prior conditions within the inversion algorithm, such as surface reflectance priors and aerosol corrections. By training on CAMS, our model learns a more accurate target, focusing on spectral features relevant to real atmospheric variability. Our experiments comparing results against TCCON ground data also validate that this approach yields more accurate results than TROPOMI L2 XCH4.
(2) Although CAMS has coarse resolution, our input preprocessing explicitly addresses this by cropping TROPOMI L1B data into 3×3 spatial blocks. This enables the model to capture subgrid heterogeneity (e.g., local emission hotspots) smoothed out by CAMS. The CBAM module further amplifies this by selectively focusing on spatial and spectral features within the high-resolution spectrum, allowing the model to “upsample” fine details onto the CAMS grid cells rather than simply reproducing their smoothing.
(3) While our data filtering step utilizes the TROPOMI L2 product XCH4, this is solely for a convenient method to screen high-quality TROPOMI spectral samples during model training. This step is not required for the model's practical application.
We acknowledge that our methodology may warrant more detailed elaboration, but we do not plan significant modifications to the core approach. Our objective is to surpass TROPOMI's L2 product XCH4 in both inversion efficiency and accuracy. Using TROPOMI's L2 product XCH4 as the training target would substantially diminish the research's necessity, and the inversion accuracy would likely not exceed that of the product. Nevertheless, to address your concerns, we will expand our explanation in Section 2, detailing why CAMS was chosen as the training target instead of TROPOMI's L2 product XCH4.
2. Model Performance:
We appreciate the reviewer's emphasis on the need for explicit data coverage details, a larger sample size, and more comprehensive metrics. We also note your observation of “flat” scatter plots in Figures 6 and 7, which may suggest low sensitivity to XCH4 variability. Upon re-examination, this result stems from the narrow dynamic range of XCH4 in our selected validation subset (1840–1850 ppb globally during June 2020), where natural variability was moderate (approximately 10 ppb), leading to y-axis compression. However, RMSE/MAE values (e.g., 9.96 ppb relative to CAMS, 5.68–17.6 ppb relative to TCCON) indicate that relative accuracy within this range is not low, and spatial visualizations of the model (Figure 5) confirm its ability to resolve subtle gradients.
To strengthen the persuasiveness of this section's experiments and enhance the model's generalization capability, we plan to implement the following modifications:
(1) To mitigate the small sample size, we will expand the dataset by incorporating more TROPOMI orbits and extending coverage to a global scale, followed by retraining the model.
(2) To comprehensively evaluate the accuracy of experimental results, we will add correlation coefficients (r) and coefficient of determination (R²) to all scatter plots (Figures 6 and 7).
3. Comparison with Other Methods:
We appreciate the reviewer's feedback and acknowledge that our previous description of the “optimal estimation” method was indeed overly broad. In the revised manuscript, we have provided further details on the method's configuration: Specifically, we employ the SCIATRAN radiative transfer model as the forward model, with CH₄ prior profiles derived from spatiotemporally interpolated CH₄ profiles from the CAMS reanalysis product; Additionally, other key parameters include surface albedo and temperature/humidity profiles provided by the ERA5 reanalysis dataset. All other parameters are configured according to SCIATRAN's default settings. We believe this supplementary information enhances the method's transparency and reproducibility.
We understand the reviewer's concern regarding the citation source for the “improved spatial inversion method.” This method was originally derived from a master's thesis within our team. While the thesis underwent rigorous academic defense and peer review procedures, as you noted, theses may be less accessible and subject to less stringent review compared to formal journal articles. Therefore, in the revised manuscript, we plan to add citations to relevant journal articles on “spatial inversion methods” and provide further clarification on the specific principles of the “improved spatial inversion method.” The forward model, prior data, and other parameters of this method remain consistent with the “optimal estimation” approach.
4. Lack of Discussion Section:
We fully agree with the reviewer's feedback that a dedicated discussion section is essential for contextualizing our contributions, implications, and limitations. While we combined the discussion with experimental analysis in a subsection, the discussion was indeed insufficient. In the revised manuscript, we plan to insert a new subsection before the conclusions to discuss experimental results. This section will include feature importance analysis based on SHAP values to identify which input features most significantly impact model predictions, thereby enhancing model interpretability.Citation: https://doi.org/10.5194/egusphere-2025-3885-AC1
-
AC2: 'Comment on egusphere-2025-3885', Yong Wan, 13 Nov 2025
We are writing to formally request the withdrawal of our manuscript titled “A High-Precision Satellite XCH4 Inversion Method Using CBAM-ResNet18” (submission ID: EGUsphere-2025-3885, submitted on 9 August 2025).
We sincerely appreciate the time and effort that the editorial team have dedicated to handling our manuscript. However, due to unforeseen delays in the review process—particularly the challenges in securing a second reviewer—we feel it is in the best interest of our work to seek alternative opportunities for publication at this time.Citation: https://doi.org/10.5194/egusphere-2025-3885-AC2 -
RC2: 'Comment on egusphere-2025-3885', Anonymous Referee #2, 13 Nov 2025
The comment was uploaded in the form of a supplement: https://egusphere.copernicus.org/preprints/2025/egusphere-2025-3885/egusphere-2025-3885-RC2-supplement.pdf
-
AC3: 'Reply on RC2', Yong Wan, 14 Nov 2025
Thank you very much for handling our submission and for sending us the valuable and detailed comments from the reviewers. We sincerely appreciate the time and effort the reviewers have invested in providing this constructive feedback.
After carefully studying the reports, we realize that the current manuscript has several significant shortcomings that require substantial revision. To properly address the concerns raised and to meet the high standards of the journal, we believe it is necessary to fundamentally redesign parts of the study, including additional experiments and a major restructuring of the paper.
Given the extent of the required changes, we feel it would be inappropriate to proceed with the current version under review. Therefore, we kindly request to withdraw our manuscript EGUSPHERE-2025-3885 from further consideration at this time.
Citation: https://doi.org/10.5194/egusphere-2025-3885-AC3
-
AC3: 'Reply on RC2', Yong Wan, 14 Nov 2025
Viewed
| HTML | XML | Total | BibTeX | EndNote | |
|---|---|---|---|---|---|
| 1,670 | 60 | 23 | 1,753 | 33 | 32 |
- HTML: 1,670
- PDF: 60
- XML: 23
- Total: 1,753
- BibTeX: 33
- EndNote: 32
Viewed (geographical distribution)
| Country | # | Views | % |
|---|
| Total: | 0 |
| HTML: | 0 |
| PDF: | 0 |
| XML: | 0 |
- 1
[General Comments]
This manuscript introduces a deep learning approach, CBAM-ResNet18, for retrieving column-averaged dry-air mole fraction of methane (XCH4) from TROPOMI satellite spectra. The topic is of considerable interest and falls well within the scope of Atmospheric Measurement Techniques. The goal of developing more efficient retrieval algorithms is an important one for the atmospheric and climate science community.
However, the study has several major issues that undermine its scientific quality. These include the model training strategy, unconvincing validation performance, insufficient detail in comparison between methods, and a lack of discussion on the model's limitations. For these reasons, the work does not meet the scientific standards required for publication in the AMT journal.
Major Concerns: