Groundwater-Potential Mapping Using a Self-Learning Bayesian Network Model: A Comparison among Metaheuristic Algorithms

Round 1

Reviewer 1 Report

 the input weight of ensemble models: what do you mean ensemble models?

Line 63: what do you mean by “potential of groundwater”?

Please re-write the object of the work in the last section of the introduction.

Line 122: please use the k-fold cross-validation to evaluate the models.

Line 179: it is unclear. Please explain clearly what is its benefit. It is a kind of feature selection?

Line 240: it is unclear. Please explain clearly what is its benefit. It is a kind of feature selection?

Author Response

Dear Editor-in-Chief

Water

Re: water-1072224, entitled: “Mapping of groundwater potential zones using self-learning Bayesian network model: A comparison among metaheuristic algorithms”

We thank both reviewers for providing us highly constructive and insightful comments to improve our manuscript. We have carefully revised the manuscript, following the reviewers’ suggestions, and have responded in detail to each comment. The next section contains our point-by-point responses (in blue) and changes referencing the manuscript (in green), based on the reviewers’ comments (in italic) (Please see the attachment). We believe that our manuscript has substantially improved and is more readable for broader audiences. We would like to thank you and the respected Special Issue Guest Editors for following up this manuscript. We look forward to hearing from you. Also, we would be glad to respond to any further questions and comments that you may have. 

Yours Sincerely,

Nguyen Thi Thuy Linh, 

Author Response File: Author Response.docx

Reviewer 2 Report

1. The objective of the paper was not clearly stated in the Abstract and Introduction section.
2. It seems that groundwater potential might depend on spring discharge which might vary with the location. It is not clear how the discharge from the springs in different location is considered in the analysis. If groundwater potential depends on only the existence or nonexistence of spring, the authors describe and discuss the assumptions or hypotheses in relation to these issues.
3. The authors consider additional analyses using traditional BayesNet model without employing metaheuristic algorithms. With additional analyses, the authors present the comparative results between traditional and metaheuristic approaches. That will demonstrate the strength of the proposed approach in this paper and reinforce the conclusion of this paper.
4. In Table 1,

what is the unit of scale? 30mⅹ30m? What does it mean by 1.100,1000?

what does it mean by ‘manual’ in classification method?

It is not clear how one collects SRTM DM, Landsat-8 image in Table 1. The detailed source should be described.

The 22 meteorological stations in Khuzestan need to be described. This can be described in Supplemental materials that the authors can add. The authors might consider moving Table 1 to Supplemental materials.

5. Explain briefly the meaning of pp_a and pp_s in Equation (2) and how one can estimate pp_a and pp_s in Cf method.
6. What is the meaning of negative and positive values in profile curvature? In Line 295, check the value of 0.0054. In Table 2, it is given as -0.0054.
7. Line 327 needs to be described in 2.9 Ensemble model. Provide sufficient URL information regarding software and program used in this study such that the readers can use to reproduce the results of this study.
8. Explain why TWI>6.1 has the negative CF score in Table 2.
9. Explain why rainfall >550mm has lower CF score than rainfall 500-550mm class in Table 2.
10. The authors might consider moving Figure 5 to Supplemental materials. Use Supplemental materials to reduce the main texts.

11. What is the criteria for dividing GPM into five categories in Figure 6?

Author Response

Dear Editor-in-Chief
Water
January, 2021
Re: water-1072224, entitled: “Mapping of groundwater potential zones using self-learning Bayesian network model: A comparison among metaheuristic algorithms”
We thank both reviewers for providing us highly constructive and insightful comments to improve our manuscript. We have carefully revised the manuscript, following the reviewers’ suggestions, and have responded in detail to each comment. The next section contains our point-by-point responses (in blue) and changes referencing the manuscript (in green), based on the reviewers’ comments (in italic) (Please see the attachment). We believe that our manuscript has substantially improved and is more readable for broader audiences. We would like to thank you and the respected Special Issue Guest Editors for following up this manuscript. We look forward to hearing from you. Also, we would be glad to respond to any further questions and comments that you may have.
Yours Sincerely,
Nguyen Thi Thuy Linh, 

Author Response File: Author Response.docx

Round 2

Reviewer 2 Report

1. The description of objectives in the Introduction and in the Abstract was different. The readers are confusing about the study objective.
2. The response (line 63-67) is still unclear. It’s difficult to understand how it is related to the assumptions and hypotheses regarding groundwater potential.
3. The response (line 364-368) should be described in Section 2.9 because it is not the results and related to the method.

Author Response

Dear Editor-in-Chief

Water

January, 2021

Re: water-1072224, entitled: “Mapping of groundwater potential zones using self-learning Bayesian network model: A comparison among metaheuristic algorithms”

We thank both reviewers for providing us highly constructive and insightful comments to improve our manuscript. We have carefully revised the manuscript, following the reviewers’ suggestions, and have responded in detail to each comment. The next section contains our point-by-point responses (in blue) and changes referencing the manuscript (in green), based on the reviewers’ comments (in italic) (Please see the attachment). We believe that our manuscript has substantially improved and is more readable for broader audiences. We would like to thank you and the respected Special Issue Guest Editors for following up this manuscript. We look forward to hearing from you. Also, we would be glad to respond to any further questions and comments that you may have.

Yours Sincerely,

Nguyen Thi Thuy Linh,

Author Response File: Author Response.docx