Dear Dr. Kariminejad,

Thank you for submitting your manuscript to PLOS ONE. After careful consideration, we feel that it has merit but does not fully meet PLOS ONE’s publication criteria as it currently stands. Therefore, we invite you to submit a revised version of the manuscript that addresses the points raised during the review process.

Please submit your revised manuscript by Jan 10 2026 11:59PM. If you will need more time than this to complete your revisions, please reply to this message or contact the journal office at plosone@plos.org. When you're ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file.. When you're ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file.. When you're ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file.. When you're ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file.

• A rebuttal letter that responds to each point raised by the academic editor and reviewer(s). You should upload this letter as a separate file labeled 'Response to Reviewers'.
• A marked-up copy of your manuscript that highlights changes made to the original version. You should upload this as a separate file labeled 'Revised Manuscript with Track Changes'.
• An unmarked version of your revised paper without tracked changes. You should upload this as a separate file labeled 'Manuscript'.

If you would like to make changes to your financial disclosure, please include your updated statement in your cover letter. Guidelines for resubmitting your figure files are available below the reviewer comments at the end of this letter.

If applicable, we recommend that you deposit your laboratory protocols in protocols.io to enhance the reproducibility of your results. Protocols.io assigns your protocol its own identifier (DOI) so that it can be cited independently in the future. For instructions see: https://journals.plos.org/plosone/s/submission-guidelines#loc-laboratory-protocols. Additionally, PLOS ONE offers an option for publishing peer-reviewed Lab Protocol articles, which describe protocols hosted on protocols.io. Read more information on sharing protocols at . Additionally, PLOS ONE offers an option for publishing peer-reviewed Lab Protocol articles, which describe protocols hosted on protocols.io. Read more information on sharing protocols at . Additionally, PLOS ONE offers an option for publishing peer-reviewed Lab Protocol articles, which describe protocols hosted on protocols.io. Read more information on sharing protocols at . Additionally, PLOS ONE offers an option for publishing peer-reviewed Lab Protocol articles, which describe protocols hosted on protocols.io. Read more information on sharing protocols at https://plos.org/protocols?utm_medium=editorial-email&utm_source=authorletters&utm_campaign=protocols....

We look forward to receiving your revised manuscript.

Kind regards,

Babak Mohammadi

Academic Editor

PLOS ONE

Journal Requirements:

When submitting your revision, we need you to address these additional requirements.

1. Please ensure that your manuscript meets PLOS ONE's style requirements, including those for file naming. The PLOS ONE style templates can be found at

https://journals.plos.org/plosone/s/file?id=wjVg/PLOSOne_formatting_sample_main_body.pdf and https://journals.plos.org/plosone/s/file?id=ba62/PLOSOne_formatting_sample_title_authors_affiliations.pdf

2. Please note that PLOS One has specific guidelines on code sharing for submissions in which author-generated code underpins the findings in the manuscript. In these cases, we expect all author-generated code to be made available without restrictions upon publication of the work. Please review our guidelines at https://journals.plos.org/plosone/s/materials-and-software-sharing#loc-sharing-code and ensure that your code is shared in a way that follows best practice and facilitates reproducibility and reuse.

3. Thank you for stating the following in your Competing Interests section:

[NO authors have competing interests].

Please complete your Competing Interests on the online submission form to state any Competing Interests. If you have no competing interests, please state "The authors have declared that no competing interests exist.", as detailed online in our guide for authors at http://journals.plos.org/plosone/s/submit-now

This information should be included in your cover letter; we will change the online submission form on your behalf.

4. We note that your Data Availability Statement is currently as follows: [All relevant data are within the manuscript and its Supporting Information files.]

Please confirm at this time whether or not your submission contains all raw data required to replicate the results of your study. Authors must share the “minimal data set” for their submission. PLOS defines the minimal data set to consist of the data required to replicate all study findings reported in the article, as well as related metadata and methods (https://journals.plos.org/plosone/s/data-availability#loc-minimal-data-set-definition).

For example, authors should submit the following data:

- The values behind the means, standard deviations and other measures reported;

- The values used to build graphs;

- The points extracted from images for analysis.

Authors do not need to submit their entire data set if only a portion of the data was used in the reported study.

If your submission does not contain these data, please either upload them as Supporting Information files or deposit them to a stable, public repository and provide us with the relevant URLs, DOIs, or accession numbers. For a list of recommended repositories, please see https://journals.plos.org/plosone/s/recommended-repositories.

If there are ethical or legal restrictions on sharing a de-identified data set, please explain them in detail (e.g., data contain potentially sensitive information, data are owned by a third-party organization, etc.) and who has imposed them (e.g., an ethics committee). Please also provide contact information for a data access committee, ethics committee, or other institutional body to which data requests may be sent. If data are owned by a third party, please indicate how others may request data access.

5. When completing the data availability statement of the submission form, you indicated that you will make your data available on acceptance. We strongly recommend all authors decide on a data sharing plan before acceptance, as the process can be lengthy and hold up publication timelines. Please note that, though access restrictions are acceptable now, your entire data will need to be made freely accessible if your manuscript is accepted for publication. This policy applies to all data except where public deposition would breach compliance with the protocol approved by your research ethics board. If you are unable to adhere to our open data policy, please kindly revise your statement to explain your reasoning and we will seek the editor's input on an exemption. Please be assured that, once you have provided your new statement, the assessment of your exemption will not hold up the peer review process.

6. We note that Figures 1 and 15 in your submission contain map and satellite images which may be copyrighted. All PLOS content is published under the Creative Commons Attribution License (CC BY 4.0), which means that the manuscript, images, and Supporting Information files will be freely available online, and any third party is permitted to access, download, copy, distribute, and use these materials in any way, even commercially, with proper attribution. For these reasons, we cannot publish previously copyrighted maps or satellite images created using proprietary data, such as Google software (Google Maps, Street View, and Earth). For more information, see our copyright guidelines: http://journals.plos.org/plosone/s/licenses-and-copyright.

We require you to either (1) present written permission from the copyright holder to publish these figures specifically under the CC BY 4.0 license, or (2) remove the figures from your submission:

1. You may seek permission from the original copyright holder of Figures 1 and 15 to publish the content specifically under the CC BY 4.0 license.

We recommend that you contact the original copyright holder with the Content Permission Form (http://journals.plos.org/plosone/s/file?id=7c09/content-permission-form.pdf) and the following text:

“I request permission for the open-access journal PLOS ONE to publish XXX under the Creative Commons Attribution License (CCAL) CC BY 4.0 (http://creativecommons.org/licenses/by/4.0/). Please be aware that this license allows unrestricted use and distribution, even commercially, by third parties. Please reply and provide explicit written permission to publish XXX under a CC BY license and complete the attached form.”

Please upload the completed Content Permission Form or other proof of granted permissions as an "Other" file with your submission.

In the figure caption of the copyrighted figure, please include the following text: “Reprinted from [ref] under a CC BY license, with permission from [name of publisher], original copyright [original copyright year].”

2. If you are unable to obtain permission from the original copyright holder to publish these figures under the CC BY 4.0 license or if the copyright holder’s requirements are incompatible with the CC BY 4.0 license, please either i) remove the figure or ii) supply a replacement figure that complies with the CC BY 4.0 license. Please check copyright information on all replacement figures and update the figure caption with source information. If applicable, please specify in the figure caption text when a figure is similar but not identical to the original image and is therefore for illustrative purposes only.

The following resources for replacing copyrighted map figures may be helpful:

USGS National Map Viewer (public domain): http://viewer.nationalmap.gov/viewer/

The Gateway to Astronaut Photography of Earth (public domain): http://eol.jsc.nasa.gov/sseop/clickmap/

Maps at the CIA (public domain): https://www.cia.gov/library/publications/the-world-factbook/index.html and https://www.cia.gov/library/publications/cia-maps-publications/index.html

NASA Earth Observatory (public domain): http://earthobservatory.nasa.gov/

Landsat: http://landsat.visibleearth.nasa.gov/

USGS EROS (Earth Resources Observatory and Science (EROS) Center) (public domain): http://eros.usgs.gov/#

Natural Earth (public domain): http://www.naturalearthdata.com/

7. We note that Figures 2 and 5 in your submission contain copyrighted images. All PLOS content is published under the Creative Commons Attribution License (CC BY 4.0), which means that the manuscript, images, and Supporting Information files will be freely available online, and any third party is permitted to access, download, copy, distribute, and use these materials in any way, even commercially, with proper attribution. For more information, see our copyright guidelines: http://journals.plos.org/plosone/s/licenses-and-copyright.

We require you to either (1) present written permission from the copyright holder to publish these figures specifically under the CC BY 4.0 license, or (2) remove the figures from your submission:

1. You may seek permission from the original copyright holder of Figures 2 and 5 to publish the content specifically under the CC BY 4.0 license.

We recommend that you contact the original copyright holder with the Content Permission Form (http://journals.plos.org/plosone/s/file?id=7c09/content-permission-form.pdf) and the following text:

“I request permission for the open-access journal PLOS ONE to publish XXX under the Creative Commons Attribution License (CCAL) CC BY 4.0 (http://creativecommons.org/licenses/by/4.0/). Please be aware that this license allows unrestricted use and distribution, even commercially, by third parties. Please reply and provide explicit written permission to publish XXX under a CC BY license and complete the attached form.

Please upload the completed Content Permission Form or other proof of granted permissions as an "Other" file with your submission.

In the figure caption of the copyrighted figure, please include the following text: “Reprinted from [ref] under a CC BY license, with permission from [name of publisher], original copyright [original copyright year].”

2. If you are unable to obtain permission from the original copyright holder to publish these figures under the CC BY 4.0 license or if the copyright holder’s requirements are incompatible with the CC BY 4.0 license, please either i) remove the figure or ii) supply a replacement figure that complies with the CC BY 4.0 license. Please check copyright information on all replacement figures and update the figure caption with source information. If applicable, please specify in the figure caption text when a figure is similar but not identical to the original image and is therefore for illustrative purposes only.

If the reviewer comments include a recommendation to cite specific previously published works, please review and evaluate these publications to determine whether they are relevant and should be cited. There is no requirement to cite these works unless the editor has indicated otherwise.

Additional Editor Comments:

1. The introduction needs improvement. Please provide a literature review, clearly identify the research gaps based on the reviewed studies, and then state how this manuscript aims to address those gaps.

2. For the LSTM model and each algorithm in the methodology section, please present their main equations and introduce all related components. More detailed explanations are required for each algorithm, including additional references, information about the software packages used, and the inputs and outputs involved.

3. Clarify whether the hyperparameters of the LSTM were tuned using the optimization algorithms. More details are needed on how the hyperparameters were configured and optimized.

4. List the parameters of each algorithm in a table, and explain how you set them.

5. Ensure that each equation is supported with relevant references.

6. Section 2.3 (Model Evaluation and Validation Methods) can be summarized. You may simply present each equation and introduce the components within those equations.

7. Explain and discuss the values in Tables 2 to 9 within the main text. Provide interpretation and context for the results presented.

8. Each figure needs more explanation in the text. Please discuss the details illustrated in every figure.

9. Add more hydrological interpretation when explaining each figure.

10. Please make all revisions using a different font color or by track changes mode.

[Note: HTML markup is below. Please do not edit.]

Reviewers' comments:

Reviewer's Responses to Questions

Comments to the Author

1. Is the manuscript technically sound, and do the data support the conclusions?

Reviewer #1: Yes

Reviewer #2: Yes

Reviewer #3: Partly

Reviewer #4: Partly

**********

2. Has the statistical analysis been performed appropriately and rigorously? -->?>

Reviewer #1: Yes

Reviewer #2: Yes

Reviewer #3: No

Reviewer #4: Yes

**********

3. Have the authors made all data underlying the findings in their manuscript fully available??>

The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified.requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified.-->

Reviewer #1: Yes

Reviewer #2: Yes

Reviewer #3: No

Reviewer #4: Yes

**********

4. Is the manuscript presented in an intelligible fashion and written in standard English??>

Reviewer #1: Yes

Reviewer #2: Yes

Reviewer #3: No

Reviewer #4: No

**********

Reviewer #1: This study proposes a framework for flood susceptibility mapping (FSMs) that integrates feature selection with meta-heuristic optimisation of LSTM networks. Nineteen environmental factors were obtained via Generalised Estimating Equations (GEE), with nine feature selection methods employed to screen key variables and identify core predictors. Subsequently, five meta-heuristic algorithms (WOA, GWO, OOA, etc.) optimised the LSTM network's hyperparameters. Validation through multiple metrics including ROC curves, F1-Score, and Kappa revealed the LSTM-WOA model delivered optimal performance, providing a tool for flood management in arid and semi-arid regions. The study holds significance but requires necessary revisions to meet publication standards.

Major comments:

1. Abstract

- The abstract lacks research background and a concise overview of previous shortcomings; furthermore, innovation should be introduced within the abstract.

Suggested improvement: This section should supplement the core consensus rules for feature selection (e.g., ‘frequency screening based on nine methods’).

2. Introduction

- The research gap is stated too broadly, merely noting ‘the lack of a unified framework integrating feature selection and meta-heuristic optimisation’ without specifying shortcomings in existing studies regarding ‘comparisons of multiple meta-heuristic algorithms’ or ‘the targeted integration of feature selection with LSTM’.

- The representativeness of the study area is not explained (e.g., the specific causes of frequent flooding in the region and their connection to existing prevention and control challenges).

3. Literature Review

- The review of studies concerning ‘application of meta-heuristic algorithms to optimise LSTM in hydrological forecasting’ and ‘consensus strategies for integrated feature selection’ is incomplete, failing to cover analogous research on multi-algorithm fusion and multi-feature screening;

- Key studies on ‘meta-heuristic optimisation of hydrological models’ and ‘multi-source data-driven flood forecasting modelling’ were not cited (j.jhydrol.2025.132998; j.envsoft.2023.105766).

4. Innovation

- The novelty of ‘integrating nine feature selection methods’ and ‘comparing five meta-heuristic algorithms’ remains unclear. Existing studies have applied similar multi-feature selection or multi-optimisation algorithms, failing to highlight the uniqueness of this research in ‘consensus screening rules’ and ‘algorithm adaptability validation’;

- The innovative distinctions between this framework and traditional FSMs approaches (e.g., machine learning models, single deep learning models) remain unexplained.

5. Methodology

- The feature selection integration strategy lacks transparency, with no detailed explanation of the ‘variable selection frequency’ threshold (e.g., rationale for including variables selected 6 times or more as core variables);

- The foundational structure of the LSTM network (e.g., neuron count, number of layers, initial learning rate range) remains undefined, and the specific dimensions of hyperparameters optimised by the meta-heuristic algorithm are not listed; the hardware environment for model training and convergence criteria are not specified.

6. Experimental Details

- No assessment of multicollinearity among variables during feature selection.

7. Results

- Feature selection outcomes merely list selected variables per method without comparing the impact of different feature subsets on model performance (e.g., accuracy differences between core variable subsets, full variable sets, and single-method-selected subsets);

- Stability analysis of models optimised by different meta-heuristic algorithms is absent (e.g., accuracy fluctuations after multiple training iterations).

8. Discussion

- The underlying mechanism for ‘LSTM-WOA achieving optimal model performance’ was not thoroughly analysed (e.g., how WOA's bubble-net search strategy adapts to LSTM hyperparameter optimisation requirements).

- Model limitations were not discussed (e.g., impacts of data timeliness and terrain adaptability).

Minor comments:

- Equations should be sequentially numbered.

- Section numbering error: should be 4. Discussion.

Reviewer #2: The study employs nine feature selection techniques to identify the most influential flood-related variables from a dataset of 19 environmental factors, and uses five optimization algorithms to adjust the hyperparameters of the LSTM model for forecasting tasks. While the process and experimental details are thorough, there are several issues that the authors need to address.

Specific Comments:

1. Present the innovations of this study in a point-by-point format.

2. The paper is too long; reduce the description of methods (such as the introduction to algorithms), and remove generic figures like Figures 4 and 5. Focus on emphasizing the optimization process of the algorithm’s hyperparameters.

3. Some conclusions in the paper, which are not derived from this study, need to be supported by key references. For instance, the paper frequently mentions “the performance of the LSTM model in handling complex nonlinear systems.”

4. In Figure 8, the text overlaps. Please address this issue and improve the clarity of Figures 12, 16, 17, 18, etc., in accordance with the journal’s guidelines.

5. Avoid terms like “a significant research gap.”

General Comments:

1. Currently, the use of different feature selection methods does not seem to have a clear optimization logic. The authors are advised to consider the logical progression between these methods. For example, begin with Elastic-Net for preliminary regularization, then use Boruta to eliminate features with weak relationships to the target variable, and finally apply Boruta-SHAP to ensure that the retained features have significant contributions to the actual predictions.

2. Multiple evaluation metrics are used to assess model performance in the paper. What is the relationship between these metrics? Is there a significant correlation between the AUC value of the ROC curve and F1-Score, accuracy, and recall? Do high accuracy and recall always correspond to a higher AUC value?

3. In the study of feature correlations, both positive and negative correlations between features appear. The authors should explain how they select features in such cases and whether negatively correlated features produce negative feedback on prediction results.

4. Clarify the core research goal of this paper: does it emphasize process explanation or result description? While the use of method stacking allows for a comprehensive analysis of feature correlations and hyperparameter optimization results, the purpose of the process should still be emphasized.

5. In many studies, SHAP analysis is mostly used after completing prediction experiments to assess the positive or negative feedback of hydrological features on the prediction results. However, this study applies it during the initial data selection. Can this ensure that the selected features will have the appropriate level of feedback on the results?

Reviewer #3: 1. The manuscript needs substantially more methodological detail, particularly for the LSTM architecture (layers, units, activation functions, batch size, epochs, learning rate, optimizer, loss function, regularization, input window length).

2. The metaheuristic optimization procedures (WOA, GWO, OOA, CSA, HOA) lack implementation details such as population size, number of iterations, search bounds, objective functions, and the specific hyperparameters optimized.

3. The process of creating the flood inventory dataset is insufficiently described; the manuscript must report the number of flood points, data sources, sampling strategy for non-flood points, temporal alignment with predictors, and spatial distribution.

4. The final feature-selection decision rule is not explained. With nine methods producing conflicting results, the manuscript needs a clear, justified rule for choosing the final feature set (e.g., majority voting, frequency threshold).

5. Some variables included in the final model were selected only weakly or infrequently; their inclusion requires justification or removal.

6. Performance reporting is incomplete; key metrics mentioned in the Methods (precision, recall, F1-score, RMSE, MAE, Kappa, AUC, confusion matrices, Friedman test results) are missing or only partially presented.

7. A complete comparison table for all models with all evaluation metrics must be added for transparency.

8. The manuscript lacks a dedicated Discussion section. The authors must interpret results, compare them with previous studies, explain why certain variables/methods dominate, and acknowledge limitations.

9. The flood susceptibility maps need improved clarity, description of classification thresholds, mapping resolution, and area statistics for each susceptibility class.

10. Figures throughout the manuscript have small or unreadable fonts, and some are overly cluttered; they need redesign for clarity.

11. Tables contain inconsistent formatting and in some cases broken or confusing layouts; uniform formatting is required.

12. Algorithm description sections are overly long and read like textbook content; they should be shortened and focused on implementation relevant to this study.

13. The Introduction is lengthy but does not clearly outline the specific research gap, the novelty of combining nine feature-selection methods, or the motivation for using five metaheuristic optimizers.

14. Reproducibility is insufficient: the manuscript states that all data are available but does not provide supporting files, GEE code, or model scripts. These must be added to comply with PLOS ONE requirements.

15. Abbreviations are not always defined consistently; the manuscript needs standardization of variable names, units, and terminology.

16. Spatial variables such as slope, aspect, land cover, and soil bulk density were rarely selected; the manuscript should discuss their limited role and potential reasons.

17. The manuscript contains many grammatical errors, awkward phrasing, and typos and requires thorough English language editing.

18. Several scientific statements lack citations or use incomplete references; the reference list must be added and brought into PLOS ONE format.

19. Some units in tables appear inconsistent or unclear (e.g., soil moisture in mm, slope in “1”); unit definitions should be checked for correctness.

20. The visual presentation of results (maps, charts, diagrams) should follow PLOS ONE figure quality standards.

21. The results section should more clearly connect performance outcomes (e.g., WOA superiority) to the methodological choices.

22. Limitations of the study (e.g., static predictors, potential overfitting, reliance on GEE temporal products) should be explicitly stated.

23. The manuscript should outline potential policy or practical implications of the findings, especially given the importance of Khuzestan Province.

24. Many metrics described in Methods (full confusion matrices, RMSE, MAE, AUC values, Friedman test p-values, model ranking) are not presented in the Results section.

This makes it impossible to verify the strength or consistency of model performance.

Reviewer #4: Introduction

1. The term “Natural Disasters” is incorrect. Consider replacing it with a more appropriate term such as “disasters caused by natural hazards.”

2. Add references where necessary. Many statements in the introduction lack supporting literature. In particular, Paragraphs 2 and 3 require additional citations.

3. A more comprehensive literature review on previous studies is needed. The current version provides minimal discussion of existing work on the use of LSTM for flood susceptibility mapping, the research gaps, and how the present study addresses them. The discussion should explicitly highlight gaps and clarify the study’s contribution. Refine the last sentence of Paragraph 4 (“Furthermore, an ensemble feature selection approach was adopted…”) since it describes your method rather than a research gap.

Materials and Methods – Study Area

4. No references were provided to support the information presented in Section 2.1.

5. Indicate the reason for selecting the case-study area. Clarify whether the selected region is flood-prone or previously identified as highly susceptible. Provide details on flood history and associated damages where available; if not, describe the flood susceptibility of the region using appropriate sources.

Materials and Methods – Model Description

6. Clarify how the parameters listed in Table 1 were selected. Provide relevant literature or scientific justification showing that these parameters influence flood susceptibility, supported by previous studies.

7. The use of abbreviations is unclear. Ensure consistent and conscious use of abbreviations throughout the manuscript.

8. Explain how the parameters were obtained and inlcude the sources for each variable. Although the introduction notes that data were acquired from GEE, the methodology must clearly specify each parameter, its source, the time frame for any time-series data, data reliability (supported by previous applications of the datasets), spatial resolution, and any known limitations.

9. Figure 2 is comprehensive, but the accompanying narrative does not sufficiently describe the methodology. Section 2.2 would benefit from clearer methodological explanations, including workflow, step-by-step processes, input/output descriptions, software or tools used, and connections to the technical details provided later.

10. Several abbreviations are not defined in the main text. Ensure that each abbreviation is defined at its first appearance (preferably in the main text rather than the abstract).

11. The models and methods used in the feature-selection stage (e.g., Boruta, Boruta-SHAP) are not introduced in the methodology. Include brief explanations of each method and clarify how they operate within your workflow.

12. The introduction to optimisation algorithms is good, but more technical detail is recommended. Include explanations of how each algorithm works (equations or schematic plots where appropriate) and how they were applied (e.g., for hyperparameter tuning).

13. The rationale for using multiple feature-selection methods requires stronger justification. Begin by emphasising why multiple methods are necessary for identifying critical parameters, how each method differs conceptually, and how some can capture relationships better than others. Selecting parameters that consistently appear across methods is acceptable, but this requires clearer scientific reasoning and justification.

14. The methodology does not explain how flood susceptibility was calculated or defined. Clarify whether susceptibility is based on simulated flood extents, observed flood events, or other criteria. Given that this is the model’s target variable, a detailed explanation is essential.

15. The manuscript does not clearly explain how LSTM is utilised in the model. Specify whether the model was trained using sequential time-series data and how changes in each parameter relate to flood susceptibility over time. This should be clarified before discussing optimisation.

16. The target variable requires a clearer definition. Indicate whether it represents flooded/not-flooded classes, flood context, susceptibility scores, or another metric.

Results

17. There is no need to provide multiple figures and tables for each feature-selection model, as most of them yield similar conclusions. Include only the most relevant figures and provide a consolidated summary of results.

Overall Comments

18. The manuscript lacks several essential details. Consider explicitly defining flood susceptibility and the approach used to calculate or evaluate it; explaining how LSTM was applied, including the structure of sequential data; and clearly defining the target variable.

19. The manuscript would benefit from substantial language improvement. Abbreviations are inconsistently defined, and several incorrect terms (e.g., “Natural Disasters”) remain. Some grammatical errors are also present. Reviewers strongly discourage relying solely on generative AI for language refinement.

**********

what does this mean?). If published, this will include your full peer review and any attached files.). If published, this will include your full peer review and any attached files.). If published, this will include your full peer review and any attached files.). If published, this will include your full peer review and any attached files.

If you choose “no”, your identity will remain anonymous but your review may still be made public.

Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our For information about this choice, including consent withdrawal, please see our For information about this choice, including consent withdrawal, please see our For information about this choice, including consent withdrawal, please see our Privacy Policy..-->

Reviewer #1: No

Reviewer #2: No

Reviewer #3: No

Reviewer #4: No

**********

[NOTE: If reviewer comments were submitted as an attachment file, they will be attached to this email and accessible via the submission site. Please log into your account, locate the manuscript record, and check for the action link "View Attachments". If this link does not appear, there are no attachment files.]

To ensure your figures meet our technical requirements, please review our figure guidelines: https://journals.plos.org/plosone/s/figures

You may also use PLOS’s free figure tool, NAAS, to help you prepare publication quality figures: https://journals.plos.org/plosone/s/figures#loc-tools-for-figure-preparation.

NAAS will assess whether your figures meet our technical requirements by comparing each figure against our figure specifications.

Dear Dr. Kariminejad,

Thank you for submitting your manuscript to PLOS ONE. After careful consideration, we feel that it has merit but does not fully meet PLOS ONE’s publication criteria as it currently stands. Therefore, we invite you to submit a revised version of the manuscript that addresses the points raised during the review process.

Please submit your revised manuscript by Mar 25 2026 11:59PM. If you will need more time than this to complete your revisions, please reply to this message or contact the journal office at plosone@plos.org. When you're ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file.. When you're ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file.. When you're ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file.. When you're ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file.

• A letter that responds to each point raised by the academic editor and reviewer(s). You should upload this letter as a separate file labeled 'Response to Reviewers'.
• A marked-up copy of your manuscript that highlights changes made to the original version. You should upload this as a separate file labeled 'Revised Manuscript with Track Changes'.
• An unmarked version of your revised paper without tracked changes. You should upload this as a separate file labeled 'Manuscript'.

If you would like to make changes to your financial disclosure, please include your updated statement in your cover letter. Guidelines for resubmitting your figure files are available below the reviewer comments at the end of this letter.

If applicable, we recommend that you deposit your laboratory protocols in protocols.io to enhance the reproducibility of your results. Protocols.io assigns your protocol its own identifier (DOI) so that it can be cited independently in the future. For instructions see: https://journals.plos.org/plosone/s/submission-guidelines#loc-laboratory-protocols. Additionally, PLOS ONE offers an option for publishing peer-reviewed Lab Protocol articles, which describe protocols hosted on protocols.io. Read more information on sharing protocols at . Additionally, PLOS ONE offers an option for publishing peer-reviewed Lab Protocol articles, which describe protocols hosted on protocols.io. Read more information on sharing protocols at . Additionally, PLOS ONE offers an option for publishing peer-reviewed Lab Protocol articles, which describe protocols hosted on protocols.io. Read more information on sharing protocols at . Additionally, PLOS ONE offers an option for publishing peer-reviewed Lab Protocol articles, which describe protocols hosted on protocols.io. Read more information on sharing protocols at https://plos.org/protocols?utm_medium=editorial-email&utm_source=authorletters&utm_campaign=protocols....

We look forward to receiving your revised manuscript.

Kind regards,

Babak Mohammadi

Academic Editor

PLOS One

Journal Requirements:

If the reviewer comments include a recommendation to cite specific previously published works, please review and evaluate these publications to determine whether they are relevant and should be cited. There is no requirement to cite these works unless the editor has indicated otherwise.

Additional Editor Comments:

1. The introduction section still needs improvement. Please provide a comprehensive literature review and clearly identify the research gaps based on the reviewed studies. Additionally, include more detailed content in the introduction regarding flood susceptibility mapping.

2. Please add the main equations of the LSTM model in the methodology section.

3. Please include more hydrological interpretation when explaining each figure. You may choose to incorporate this discussion in the main text or provide it as supplementary material. Each figure in the results section should be accompanied by a clear hydrological interpretation in the text. Therefore, add a more in-depth hydrological discussion for Figures 3, 4, 6, 7, 8, 11, and 12–15.

4. The conclusion needs more key findings.

[Note: HTML markup is below. Please do not edit.]

Reviewers' comments:

Reviewer's Responses to Questions

Comments to the Author

Reviewer #1: (No Response)

Reviewer #2: (No Response)

Reviewer #3: (No Response)

**********

2. Is the manuscript technically sound, and do the data support the conclusions??>

Reviewer #1: (No Response)

Reviewer #2: Yes

Reviewer #3: Partly

**********

3. Has the statistical analysis been performed appropriately and rigorously? -->?>

Reviewer #1: (No Response)

Reviewer #2: Yes

Reviewer #3: No

**********

4. Have the authors made all data underlying the findings in their manuscript fully available??>

The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified.requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified.-->

Reviewer #1: (No Response)

Reviewer #2: Yes

Reviewer #3: No

**********

5. Is the manuscript presented in an intelligible fashion and written in standard English??>

Reviewer #1: (No Response)

Reviewer #2: Yes

Reviewer #3: No

**********

Reviewer #1: I think the authors have responded and revised accordingly to the issues raised by the previous round of reviewers. Therefore, I accept this paper for publication in its present format.

Reviewer #2: The author has made careful adjustments to the previous requirements, and in order to further improve the quality of the manuscript, the following additional suggestions are proposed:

1 How to handle spatial features such as elevation in the construction of LSTM as a temporal prediction model for simulation applications. The mechanism of the model should be detailed, easy to read, and reproducible.

2 Please provide an analysis that combines the results of the selected features with hydrological laws.

3 Due to the black box characteristics of machine learning models, the credibility of simulation results is more important. Therefore, the limitations of the model or the effective range of simulation results are worth discussing, which can help improve the persuasiveness of the results.

Reviewer #3: The following core reviewer requirements remain unmet:

- Stability analysis and rigorous replication

- Clear, consistent reporting of experimental settings

- Reproducible data/code availability (PLOS policy)

- Proper spatial validation

- Fully specified LSTM architecture and temporal logic

- Resolution of dataset size vs confusion-matrix inconsistency

- Full hydrological interpretation in the main manuscript

- Substantial language editing

**********

what does this mean?). If published, this will include your full peer review and any attached files.). If published, this will include your full peer review and any attached files.). If published, this will include your full peer review and any attached files.). If published, this will include your full peer review and any attached files.

If you choose “no”, your identity will remain anonymous but your review may still be made public.

Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our For information about this choice, including consent withdrawal, please see our For information about this choice, including consent withdrawal, please see our For information about this choice, including consent withdrawal, please see our Privacy Policy..-->

Reviewer #1: No

Reviewer #2: No

Reviewer #3: No

**********

[NOTE: If reviewer comments were submitted as an attachment file, they will be attached to this email and accessible via the submission site. Please log into your account, locate the manuscript record, and check for the action link "View Attachments". If this link does not appear, there are no attachment files.]

To ensure your figures meet our technical requirements, please review our figure guidelines: https://journals.plos.org/plosone/s/figures

You may also use PLOS’s free figure tool, NAAS, to help you prepare publication quality figures: https://journals.plos.org/plosone/s/figures#loc-tools-for-figure-preparation.

NAAS will assess whether your figures meet our technical requirements by comparing each figure against our figure specifications.

Dear Dr. Kariminejad,

Thank you for submitting your manuscript to PLOS ONE. After careful consideration, we feel that it has merit but does not fully meet PLOS ONE’s publication criteria as it currently stands. Therefore, we invite you to submit a revised version of the manuscript that addresses the points raised during the review process.

Please submit your revised manuscript by Apr 11 2026 11:59PM. If you will need more time than this to complete your revisions, please reply to this message or contact the journal office at plosone@plos.org. When you're ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file.. When you're ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file.. When you're ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file.. When you're ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file.

• A letter that responds to each point raised by the academic editor and reviewer(s). You should upload this letter as a separate file labeled 'Response to Reviewers'.
• A marked-up copy of your manuscript that highlights changes made to the original version. You should upload this as a separate file labeled 'Revised Manuscript with Track Changes'.
• An unmarked version of your revised paper without tracked changes. You should upload this as a separate file labeled 'Manuscript'.

If applicable, we recommend that you deposit your laboratory protocols in protocols.io to enhance the reproducibility of your results. Protocols.io assigns your protocol its own identifier (DOI) so that it can be cited independently in the future. For instructions see: https://journals.plos.org/plosone/s/submission-guidelines#loc-laboratory-protocols. Additionally, PLOS ONE offers an option for publishing peer-reviewed Lab Protocol articles, which describe protocols hosted on protocols.io. Read more information on sharing protocols at . Additionally, PLOS ONE offers an option for publishing peer-reviewed Lab Protocol articles, which describe protocols hosted on protocols.io. Read more information on sharing protocols at . Additionally, PLOS ONE offers an option for publishing peer-reviewed Lab Protocol articles, which describe protocols hosted on protocols.io. Read more information on sharing protocols at . Additionally, PLOS ONE offers an option for publishing peer-reviewed Lab Protocol articles, which describe protocols hosted on protocols.io. Read more information on sharing protocols at https://plos.org/protocols?utm_medium=editorial-email&utm_source=authorletters&utm_campaign=protocols....

We look forward to receiving your revised manuscript.

Kind regards,

Babak Mohammadi

Academic Editor

PLOS One

Journal Requirements:

If the reviewer comments include a recommendation to cite specific previously published works, please review and evaluate these publications to determine whether they are relevant and should be cited. There is no requirement to cite these works unless the editor has indicated otherwise.

Please review your reference list to ensure that it is complete and correct. If you have cited papers that have been retracted, please include the rationale for doing so in the manuscript text, or remove these references and replace them with relevant current references. Any changes to the reference list should be mentioned in the rebuttal letter that accompanies your revised manuscript. If you need to cite a retracted article, indicate the article’s retracted status in the References list and also include a citation and full reference for the retraction notice.

[Note: HTML markup is below. Please do not edit.]

Reviewers' comments:

Reviewer's Responses to Questions

Comments to the Author

Reviewer #3: (No Response)

**********

2. Is the manuscript technically sound, and do the data support the conclusions??>

Reviewer #3: Partly

**********

3. Has the statistical analysis been performed appropriately and rigorously? -->?>

Reviewer #3: No

**********

4. Have the authors made all data underlying the findings in their manuscript fully available??>

The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified.requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified.-->

Reviewer #3: No

**********

5. Is the manuscript presented in an intelligible fashion and written in standard English??>

Reviewer #3: (No Response)

**********

Reviewer #3: The revised manuscript does not fully address the core reviewer comments. While additional explanations have been added, several fundamental issues remain unresolved.

Specifically:

Stability and replication are insufficiently demonstrated, as performance variability and statistical robustness across runs are not fully reported.

Experimental settings are not clearly or consistently specified, particularly regarding the full LSTM configuration.

Reproducibility requirements are unmet, with no publicly available data or code repository provided.

Proper spatial validation is lacking, as only random data splitting is used.

The justification and full specification of the LSTM architecture and its temporal logic remain unclear.

There are inconsistencies in dataset size reporting versus confusion matrix results.

Hydrological interpretation is not comprehensively integrated.

Substantial language editing is still required.

Overall, the key methodological, reproducibility, and reporting concerns raised by reviewers have not been adequately resolved.

**********

what does this mean?). If published, this will include your full peer review and any attached files.). If published, this will include your full peer review and any attached files.). If published, this will include your full peer review and any attached files.). If published, this will include your full peer review and any attached files.

If you choose “no”, your identity will remain anonymous but your review may still be made public.

Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our For information about this choice, including consent withdrawal, please see our For information about this choice, including consent withdrawal, please see our For information about this choice, including consent withdrawal, please see our Privacy Policy..-->

Reviewer #3: No

**********

[NOTE: If reviewer comments were submitted as an attachment file, they will be attached to this email and accessible via the submission site. Please log into your account, locate the manuscript record, and check for the action link "View Attachments". If this link does not appear, there are no attachment files.]

To ensure your figures meet our technical requirements, please review our figure guidelines: https://journals.plos.org/plosone/s/figures

You may also use PLOS’s free figure tool, NAAS, to help you prepare publication quality figures: https://journals.plos.org/plosone/s/figures#loc-tools-for-figure-preparation.

NAAS will assess whether your figures meet our technical requirements by comparing each figure against our figure specifications.

Optimizing LSTM Networks and Feature Selection Algorithms Using GEE Data

PONE-D-25-51471R3

Dear Dr. Kariminejad,

We’re pleased to inform you that your manuscript has been judged scientifically suitable for publication and will be formally accepted for publication once it meets all outstanding technical requirements.

Within one week, you’ll receive an e-mail detailing the required amendments. When these have been addressed, you’ll receive a formal acceptance letter and your manuscript will be scheduled for publication.

An invoice will be generated when your article is formally accepted. Please note, if your institution has a publishing partnership with PLOS and your article meets the relevant criteria, all or part of your publication costs will be covered. Please make sure your user information is up-to-date by logging into Editorial Manager at Editorial Manager® and clicking the ‘Update My Information' link at the top of the page. For questions related to billing, please contact  and clicking the ‘Update My Information' link at the top of the page. For questions related to billing, please contact  and clicking the ‘Update My Information' link at the top of the page. For questions related to billing, please contact  and clicking the ‘Update My Information' link at the top of the page. For questions related to billing, please contact billing support....

If your institution or institutions have a press office, please notify them about your upcoming paper to help maximize its impact. If they’ll be preparing press materials, please inform our press team as soon as possible -- no later than 48 hours after receiving the formal acceptance. Your manuscript will remain under strict press embargo until 2 pm Eastern Time on the date of publication. For more information, please contact onepress@plos.org.

Kind regards,

Babak Mohammadi

Academic Editor

PLOS One

Additional Editor Comments (optional):

This manuscript is acceptable.

Reviewers' comments: