Use of Evolutionary Computation to Improve Rock Slope Back Analysis
Round 1
Reviewer 1 Report
In this study, the Genetic Algorithm and Particle Swarm Optimization were utilized to facilitate back analyses based on the upper bound finite element limit analysis method. The results obtained from the two case studies are reasonable, indicating the applicability of the described method. The paper is also well written, organized, and easy to follow. In my opinion, the paper could be accepted for publication with minor revisions, and I would be happy to review the revised manuscript. My specific comments are as follows:
1. The introduction of the manuscript could be improved by discussing the major advances in back analyses.
2. Figure 8, it is hard to comprehend the figure since the color scale is missing. Also, there is some formatting issue.
3. Page 11, Lines 9-10; not really true, especially for four uncertainty parameters back calculations.
4. Page 12, why the range of 0.4-1 was considered?
5. Figure 3 and 10; it is recommended to clarify that the figures present the cross-section.
6. Figures 11 and 12, some formatting issues. Pasting figures optimize quality. It is recommended to provide color figures, suitable for greyscale printing.
7. There are 24 tables in the manuscript. Tables are hard to follow compared to figures. It is recommended to consolidate the tables.
Author Response
Please see the attachment
Author Response File: 
Author Response.docx
Reviewer 2 Report
This paper addresses the topic of a rock slope back analysis. The authors studied the use of PSO and GA algorithms to tackle the mentioned problem. Studied techniques with analysis UB-FELLA was examed in the scope of two case studies.
The topic is worth researching and relevant to the field of the Applied Sciences Journal, but the quality of English could be improved to meet the journal's standard.
Some things must be addressed before publication.
- Move Table 1 to the Case study section.
- Provide more in-depth literature review.
- What are parameter settings for the PSO algorithm?
- How were the parameters of the GA and PSO defined? Did the authors conduct some parameter tuning?
- Fix equation 3 - > min(delta) - add brackets
- Fix all of the tables. Now there are breaking lines in the table and the readability of such tables is very bad.
- All of the variables in the paper must be written in the italics mode.
- page 8, line 21: "The parameters D, GSI..." and page 9, line 12, are the same. Remove it from one page.
- Fix figures 8, 11 and 12, because the title of the figures is not visible.
- Letter D is used for two different parameters. Please, change that throughout the paper.
Since the authors are talking about evolutionary computation, especially PSO and GA, it would be very useful to provide some in-depth comparison of the results. A comparison of the fundamentals of the mentioned two algorithms is carried out in the latest review on this field: "Swarm Intelligence Algorithms for Feature Selection: A Review" (https://www.mdpi.com/2076-3417/8/9/1521).
Author Response
Please see the attachment
Author Response File: Author Response.docx
Round 2
Reviewer 2 Report
After addressing the comments, the manuscript has improved from the previous version. The paper can now be accepted.
Author Response
Please see the attachment.
Author Response File: Author Response.docx
