Predicting Groundwater Level Based on Machine Learning: A Case Study of the Hebei Plain

Round 1

Reviewer 1 Report

The present study analyzed the prediction model of groundwater level based on four kinds of machine learning, which provided a basis for groundwater level prediction in Hebei Plain. However, after reviewing the paper, I have several concerns regarding the quality of the paper:

(1) The original data contains the groundwater level data that is not measured. The paper mentions the splicing and interpolation of the data, but does not explain the method used for interpolation.

(2) Chapter 3.5 points out that MLP model is the slowest and GRU model is the fastest, but there are no quantitative indicators to support this argument. It is necessary to express the learning time of each model in the article.

(3) The introduction only describes the ecological and environmental problems of groundwater overdraft in Hebei Plain, but the main research objective of this paper is groundwater level. The existing problems of groundwater level in Hebei Plain should be further elaborated and explained in the article.

(4) In Figure 10, the legend of the scatter diagram drawn by SVM, LSTM, MLP, and GRU models is too small to see which model it represents. It needs to be modified in the article.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

Please see the attached pdf. 

Comments for author File: Comments.pdf

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Round 2

Reviewer 2 Report

I read through the changes in the revised manuscript and the authors' responses to my comments and suggestions. I am happy with the changes and therefore suggest the publication of this manuscript.