Short-Term Climate Prediction over China Mainland: An Attempt Using Machine Learning, Considering Natural and Anthropic Factors
Round 1
Reviewer 1 Report (Previous Reviewer 1)
Generally, this is an interesting study about short-term climate predictions using Random forest, but the authors' inaccurate concept or their bad selection of words for this concept makes it hard to understand. The article is about short-term climate predictions, which use climate variables in previous season to train and to predict variables in the present season. However, the authors somehow decided to call it "short-term climate trends (STCT)". So confusing! A (linear) trend model is to find the slope and intercept that give the best average fit to all the past data. It is clearly not what the authors meant in the article.
Detailed comments:
L50: "However" just came out of the blue. I don't see any contradiction mentioned here.
L57: "seasonal" -> a season.
L75: "early warning weather" -> early warnings of weather.
L88: "physical-based" -> physically based.
L173: "China.2.2.3 Anthropogenic Factors".
Equation 5: Please provide a reference for this equation.
L233: Normally, descriptions about the method should be presented in the Methods, which makes it more comfortable to read.
This article is not about "short-term climate trends (STCT)". Please choose your words conscientiously.
Author Response
Please see the attachment.
Author Response File: 
Author Response.pdf
Reviewer 2 Report (Previous Reviewer 2)
Please see the attached file
Comments for author File: Comments.pdf
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Round 2
Reviewer 1 Report (Previous Reviewer 1)
I have no more comments.
Author Response
Dear Reviewer,
Thank you for your time and effort in reviewing our manuscript. We appreciate your feedback and constructive comments, which have helped to improve the quality of our paper. We are pleased to confirm that we have addressed all your concerns and suggestions in the revised version of the manuscript.
We have carefully considered all your comments, and we are happy to inform you that we have made the necessary changes to the manuscript. We have uploaded the revised version as requested.
Once again, we thank you for your invaluable assistance, and we hope that the revised manuscript meets your expectations and requirements for publication.
Best regards,
Ruolin Li Ph.D., co-authors
Reviewer 2 Report (Previous Reviewer 2)
Please see the attached file
Comments for author File: Comments.pdf
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
This manuscript is a resubmission of an earlier submission. The following is a list of the peer review reports and author responses from that submission.
Round 1
Reviewer 1 Report
Review of sustainability-1624358
This article uses a machine learning algorithm to improve climate predictability over China. However, there are some shortcomings in this work, which cast doubts on the results presented in this article. Honestly, the introduction needs great improvement. The introduction starts with a concept “short-term climate trend”, but the purpose of this study shown in the end has nothing to do with this short-term climate trend. A lot of efforts have been put to highlight the devastating socioeconomic losses caused by climate extremes, but authors have barely mentioned how this Random Forests method may improve the predictability of climate extremes.
Further, authors should pay more attention to the writing in the manuscript. For example, in the abstract, there is a term “short-range climate trend change (SCTC)”; however, this term has been mysteriously turned into “short-term climate trend (STCT)” in the main text. A period is missing at the end of the first sentence in the main text. In the second sentence “The STCT includes hindcasting and forecasting climatological features…”. How can a trend involve forecasting some sorts of features? Do you mean the STCT prediction? Besides, all the figures are shown without indicating the unit.
Given the flaws presented above, I expect authors to rewrite the introduction and solve all these issues. I, therefore, won’t provide detailed comments this time.
Reviewer 2 Report
Please the attached file
Comments for author File: Comments.pdf
Reviewer 3 Report
Review Comments
[Title]
Short-range climate prediction over China mainland: An attempt using machine learning, considering natural and anthropic factors
[Summary]
The authors investigated the performance of STCT model with RF method.
[Broad Comments]
The contents of the introduction are fine. But the figures with more than one panels are disordered, and I cannot evaluate the explanation and discussion are appropriate in this time, sorry. So, I recommend you to recheck and remake the figures, and then submit the manuscript.
[Specific Comments]
Line 38: For example, the STC …
Is it “STCT”?
Line 55: … reported to vary between …
… reported vary between … (remove “to”)
Line 78: … than precipitation [23] In the past …
… than precipitation [23]. In the past … (put a period between the two sentences)
Line 82: … computational cost [24] These model …
… computational cost [24]. These model … (put a period between the two sentences)
Line 88: application of the ML and …
The abbreviated word “ML” (maybe, machine learning) appears firstly here without formal nomenclature.
Line 97: … components [32,33]
Put a period at the end of the sentence.
Line 101: … phenomenon, IOD, Pacific …
The abbreviated word “IOD” appears firstly here without formal nomenclature.
Line 174: … predictions Moreover, …
… predictions. Moreover, … (put a period between the two sentences)
Line 178: … different applications, the majority …
… different applications, and the majority … (Some conjunctive is needed)
Line 200: percentage error (PE)
Figs. 2, 5, 6, 7, 8, 9…
The figure panels are disordered. Please remake the figure with sector names.
