Next Article in Journal
Assessing the Environmental Impact of Oasis Agriculture in the Yarkant River Basin: A Comprehensive Study of Water Use, Carbon Footprint, and Decoupling Index
Next Article in Special Issue
Evaluation of the Sensitivity of the Weather Research and Forecasting Model to Changes in Physical Parameterizations During a Torrential Precipitation Event of the El Niño Costero 2017 in Peru
Previous Article in Journal
Defining and Mitigating Flow Instabilities in Open Channels Subjected to Hydropower Operation: Formulations and Experiments
Previous Article in Special Issue
Variability of Dry Days and Sequences of Dry Days in the Polish Carpathians in the Period 1986–2020
 
 
Article
Peer-Review Record

Adapting to Climate Change with Machine Learning: The Robustness of Downscaled Precipitation in Local Impact Analysis

Water 2024, 16(21), 3070; https://doi.org/10.3390/w16213070
by Santiago Mendoza Paz 1,2, Mauricio F. Villazón Gómez 1,* and Patrick Willems 2,*
Reviewer 1:
Reviewer 2: Anonymous
Reviewer 3: Anonymous
Water 2024, 16(21), 3070; https://doi.org/10.3390/w16213070
Submission received: 20 September 2024 / Revised: 19 October 2024 / Accepted: 23 October 2024 / Published: 26 October 2024

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

Manuscript entitled ADAPTING TO CLIMATE CHANGE WITH MACHINE

LEARNING: THE ROBUSTNESS OF DOWNSCALED

PRECIPITATION IN LOCAL IMPACT ANALYSIS is generally well written. It contains interesting analysis and addresses a topic relevant to climate change. The paper adds new knowledge to the current state of knowledge. The manuscript was well consulted. The introductory chapter does an excellent job of introducing the reader to the research topic. The methodology has been described in detail. The results have been analysed correctly and are discussed in depth in the discussion chapter. However, I have a few minor comments that need to be taken into account:

1. please do not use the form 'we' - this is unprofessional. The whole paper should use the impersonal form e.g.  It has been done , counted and not we did , we counted.

2. in line 99 there is a letter ,,y" at the beginning please remove it 

3. the conclusion chapter must be rewritten. The chapter should be significantly shortened. Suggest the authors include the most important conclusions in the form of a bullet point list. Currently the chapter is too large and the authors' important results are difficult to find.

(4) The entire text should be re-checked for editing and the references should be fudged according to the requirements of the journal.

5. in the abstract, please stick to a concise structure. This is the sentence of the introduction, the purpose of the paper, the methodology, the results and the conclusion. The abstract in its current form is poorly written.

With these minor changes, in my opinion the manuscript is suitable for publication.

Author Response

Please see the attachment

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

Please see the attached fileÑŽ. 

Comments for author File: Comments.pdf

Author Response

Please see the attachment

Author Response File: Author Response.pdf

Reviewer 3 Report

Comments and Suggestions for Authors

The authors propose a study analysing the rainfall projections using two machine learning methods that are applied at the country level in Bolivia. As it stands now, the study, although being interesting, is more targeted for a regional journal, since the novelty is not properly justified in the Introduction and the Conclusion does not explain how the methods and results can be extrapolated to other environmental contexts. Therefore, the authors must work much oin these aspects. Moreover, I have found often flaws in the presentation, which I have detailed in the commented ms in attachment.

Comments for author File: Comments.pdf

Author Response

Please see the attachment

Author Response File: Author Response.pdf

Round 2

Reviewer 2 Report

Comments and Suggestions for Authors

Authors' response: "Support Vector Machines (modified to perform quantile mapping) and Random Forest tend to perform better compared to other Machine Learning Techniques in downscaling precipitation. It is a controversial statement." I would not say so unequivocally. Overall, the manuscript is well done, I have no significant comments.

Reviewer 3 Report

Comments and Suggestions for Authors

The authors have replied to all the reviewrs' comments and now the paper is noticeably improved.

Comments on the Quality of English Language

I am not a native English speaker, but I fell that the language is fine.

Back to TopTop