Evaluation on Development Height of Water-Conduted Fractures on Overburden Roof Based on Nonlinear Algorithm
Round 1
Reviewer 1 Report
This subject addressed is within the scope of the journal. However, the manuscript in the present version contains several problems. Appropriate revisions should be undertaken in order to justify recommendation for publication.
1. No decomposition method is used for decomposition to capture data noise. why? How will this affect the results? More details should be furnished.
2. It is mentioned that SVM-PSO is used as main model. What are the advantages of adopting this particular method over others in this case? How will this affect the results? More details should be furnished. Why not tried new advance hybrid models for comparison? For example,ANFIS-GBO,ELM-PSOGWO,LSSVM-IMVO,SVR-SAMOA recently used in the literature of time series modeling. Should add these models recent literature and also explain why not adopted those advanced version?.
3. For readers to quickly catch your contribution, it would be better to highlight major difficulties and challenges, and your original achievements to overcome them, in a clearer way in abstract and introduction.
4. It is mentioned that China is adopted as the case study. What are other feasible alternatives? What are the advantages of adopting this case study over others in this case? How will this affect the results? The authors should provide more details on this.
5. There is a serious concern regarding the novelty of this work. What new has been proposed?
6. Abstract needs to modify and to be revised to be quantitative. You can absorb readers' consideration by having some numerical results in this section.
7. There are some occasional grammatical problems within the text. It may need the attention of someone fluent in English language to enhance the readability.
8. Since the some figures have low-resolution printing, the reviewer cannot recognize them clearly. Please revise them with high resolution.
9. The discussion section in the present form is relatively weak and should be strengthened with more details and justifications.
10. In conclusion section, limitations and recommendations of this research should be highlighted.
11. The authors have to add the state-of-the art references in the manuscripts.
12. Some key parameters are not mentioned. The rationale on the choice of the set of parameters should be explained with more details. Have the authors experimented with other sets of values? What are the sensitivities of these parameters on the results?
13. It is mentioned that three performance indexes were used. What are the advantages of adopting these indexes over others (CC, willimot index) in this case? How will this affect the results? More details should be furnished.
Author Response
Response to reviewers
We gratefully thank the editor and all reviewers for their time spend making their constructive remarks and useful suggestions,which has significantly raised the quality of the manuscript and has enable us to improve the manuscript.Each suggested revision and coment ,brought forward by the reviewers was accurately incorporated and considered.Below the comments of the reviewers are response point by point and the revisions are indicated.
1.Comment:No decomposition method is used for decomposition to capture data noise. why? How will this affect the results? More details should be furnished.
1.Reply:We are appreciative of the reviewer’s suggestion.Regarding data analysis, we used ANP for dimensionality reduction and then collected lower dimensional data to reduce data redundancy. Because there are so few data similar to the hydrogeological background of the study area, it is difficult to collect them. The roof data has the characteristics of small samples and non-linearity, and after careful selection, the volume of the test set and data set is only 16 entries. Some noise reduction methods such as clustering and binning are not applicable, so the manual selection method is chosen to improve the quality of the data.
2.Comment: It is mentioned that SVM-PSO is used as main model. What are the advantages of adopting this particular method over others in this case? How will this affect the results? More details should be furnished. Why not tried new advance hybrid models for comparison? For example, ANFIS-GBO, ELM-PSOGWO, LSSVM-IMVO, SVR-SAMOA recently used in the literature of time series modeling. Should add these models recent literature and also explain why not adopted those advanced version?
2.Reply:Thank you for your comment.The PSO algorithm has the advantages of fast convergence, few parameters and simple implementation (for high dimensional optimisation problems, it converges to the optimal solution faster than genetic algorithms). The combination of particle swarm optimization algorithms and support vector regression machines makes it possible to rapidly and accurately iterate the optimisation search and improve the prediction accuracy and generalisation of the model. The advantages of the optimization search methods over genetic algorithms and grid search have been supplemented in the manuscript. Relevant references have also been added. The roof crack data does not have a time-series character and therefore no time-series model is used. We have studied the relevant models and compared them for analysis and hope that they will meet your requirements.
3.Comment:For readers to quickly catch your contribution, it would be better to highlight major difficulties and challenges, and your original achievements to overcome them, in a clearer way in abstract and introduction.
3.Reply:Thank you for your valuable suggestions. We have made corresponding revisions to the abstract and introduction in response to comments, highlighting the difficulties and challenges in the research process of the study and further demonstrating the innovative and value-oriented nature of this research.
4.Comment:It is mentioned that China is adopted as the case study. What are other feasible alternatives? What are the advantages of adopting this case study over others in this case? How will this affect the results? The authors should provide more details on this.
4.Reply:Thank you for your comments.The setting for the study of this manuscript is the Yingpanhao Mine, a western mining area in China. Coal mines are found in the east and west, and in the southwest, northwest and northeast of China. The geological type of mine in this study area is a weakly cemented seam, which is different from the other areas, and is of research significance as it is highly affected by mining damage and has a high degree of roof development that cannot be accurately predicted using general empirical formulas.We have added an explanation of the background to the selection.
5.Comment:There is a serious concern regarding the novelty of this work. What new has been proposed?
5.Reply:Thanks for your helpful suggestions.We have highlighted the innovations of this research in the abstract and introduction sections.
6.Comment:Abstract needs to modify and to be revised to be quantitative. You can absorb readers' consideration by having some numerical results in this section.
6.Reply:We have revised the abstract consequently and hope that it meets the requirements.
7.Comment:There are some occasional grammatical problems within the text. It may need the attention of someone fluent in English language to enhance the readability.
7.Reply:Thanks for your check.We have double-checked the grammar and revised it to make the manuscript smooth and readable.
8.Comment:Since the some figures have low-resolution printing, the reviewer cannot recognize them clearly. Please revise them with high resolution.
8.Reply:Thanks for your check.We have inspected the images carefully and upgraded the resolution and sharpness.
9.Comment:The discussion section in the present form is relatively weak and should be strengthened with more details and justifications.
9.Reply:Your suggestions have greatly improved the quality of our manuscripts.We have added details and proofs in the conclusion section.
10.Comment:In conclusion section, limitations and recommendations of this research should be highlighted.
10.Reply:We have revised the conclusions based on the valuable comments of the reviewers, with a targeted focus to enhance the quality of the manuscript.
11.Comment:The authors have to add the state-of-the art references in the manuscripts.
11.Reply:Thank you for your comments.We have added recent references.
12.Comment: Some key parameters are not mentioned. The rationale on the choice of the set of parameters should be explained with more details. Have the authors experimented with other sets of values? What are the sensitivities of these parameters on the results?
12.Reply:We have added detailed descriptions of the parameters, and the reasons for their selection, as well as the impact on the results.
13.Comment: It is mentioned that three performance indexes were used. What are the advantages of adopting these indexes over others (CC, willimot index) in this case? How will this affect the results? More details should be furnished.
13.Reply:Thank you for your comments, which will help improve the quality of our manuscripts.The model evaluation indexes selected for this manuscript are widely used and representative in the coal mining field and can be effective in the predictive evaluation of water inrush hazards. We have provided additional details in the new version.
We sincerely hope that this revised manuscript has addressed all your comments and suggestions. We appreciated for reviewers’ warm work earnestly,and hope that the correction will meet with approval.Once again,thank you very much for your comments and suggestions.We would like to thank the referee again for taking the time to review our manuscript.
Author Response File: 
Author Response.doc
Reviewer 2 Report
1 It is suggested that the abstract should be revised appropriately, and the abstract should be revised so that the abstract can explain the purpose of the study, the research methods and the conclusions or results of the study, and the results of the study should be clear and should be briefly summarized.
2 Introduction part could be more comprehensive and in-depth. The authors are advised to add some representative references.
3 Why choose the ANP method for dimensionality reduction? What are the advantages? How does it compare to AHP?
4 Please give the basis for the division of the different thresholds in the legend of Figure 16. How was the range of thresholds determined? What does each colour represent? Why is it divided in this way?
5 Generally speaking, the language expression of this article is not very smooth, so it is suggested to polish and optimize the whole article.
6 It is suggested that the author find and correct the minor errors in the whole article.
Author Response
Response to reviewers
Thank you very much for the excellent suggestions.We sincerely thank the reviewer for thoroughly examining our manuscript and providing very helpful comments to guide our revision.We describe a point-by-point response to the comments from the editor and the reviewers below, and also highlight the revisions in yellow in the manuscript.
Comment 1. It is suggested that the abstract should be revised appropriately, and the abstract should be revised so that the abstract can explain the purpose of the study, the research methods and the conclusions or results of the study, and the results of the study should be clear and should be briefly summarized.
Reply: Thank you for valuable comments.We have focused on revising the abstract to highlight the research mechods, the purpose of the study, and the results of the study.
Comment 2. Introduction part could be more comprehensive and in-depth. The authors are advised to add some representative references.
Reply: We sincerely thank you for comments.We have revised the introduction accordingly, adding updated references and research in response to the reviewers' comments.
Comment 3. Why choose the ANP method for dimensionality reduction? What are the advantages? How does it compare to AHP?
Reply: Your suggestions are very valuable.There are interactions and feedbacks, internal dependencies and external dependencies between and within element sets. Traditional AHP is poorly solved with large errors. ANP solves the problem of distortion of results due to dependencies and feedback of factors at the same level in decision problems
Comment 4. Please give the basis for the division of the different thresholds in the legend of Figure 16. How was the range of thresholds determined? What does each colour represent? Why is it divided in this way?
Reply: We sincerely thank you for comments.In the latest version of the manuscript, we have added a specification of the threshold division of Figure 16 and what the colours of the legend represent.
Comment 5. Generally speaking, the language expression of this article is not very smooth, so it is suggested to polish and optimize the whole article.
Reply: Thank you for your comments.We have re-touched the manuscript and checked the grammatical structure in the hope of meeting the reviewers' requirements.
Comment 6. It is suggested that the author find and correct the minor errors in the whole article.
Reply: Thanks for checking and reviewing. We have carefully checked the full manuscript and made detailed corrections.
Author Response File: Author Response.doc
Round 2
Reviewer 1 Report
The authors revised properly. can accept in present form.
