Landslide Susceptibility Evaluation Based on a Coupled Informative–Logistic Regression Model—Shuangbai County as an Example
Round 1
Reviewer 1 Report
This article necessitates substantial revisions in the following aspects:
The abstract requires refinement to achieve conciseness and clarity.
The introduction should incorporate a statement emphasizing the novelty of this study, along with pertinent discussions.
The methodology needs to be explicitly and clearly described.
Please include a citation for https://doi.org/10.1016/j.enggeo.2022.106899 in Line 51-52 and https://doi.org/10.1080/10106049.2022.2138566 and https://doi.org/10.1007/s12145-022-00924-2 in 244-245
The conclusion should be presented in a point-wise manner, providing a comprehensive summary of all the major findings of this study.
Wishing you the best of luck with the revision process.
moderate
Author Response
Please see the attachment.
Author Response File: 
Author Response.pdf
Reviewer 2 Report
-The authors must endeavor to accentuate how their paper augments, corroborates, and challenges the existing body of knowledge. The sections devoted to literature review and discussion should encompass more profound insights, elucidating the rationale underpinning this research and its quantitative and methodological contributions to the academic discourse.
-In Table 1, the data sources ought to be presented comprehensively, including scales, spatial resolution, and accurate names of the sources, among other relevant details.
-Concurrently, in Figure 2, it is apparent that the maps lack the corresponding names of the factors, both on the maps themselves and in the figure captions. To address this shortfall, the authors are urged to incorporate the names of these factors to enhance clarity.
-Given the utilization of multiple factors with diverse spatial resolutions, the authors are required to specify the final resolution to be resampled and provide a coherent rationale justifying the chosen resolution.
-Regrettably, the paper's principal drawback lies in the failure to present the landslide inventory. Neither a map nor statistical information pertaining to the landslide inventory has been provided. Additionally, essential information concerning negative samples (non-landslides) necessitates inclusion.
-Regarding performance evaluation, it is advisable not to rely solely on the AUC derived from ROC curves. Instead, the authors should incorporate other metrics such as accuracy, precision, recall, and the F-1 score. Furthermore, the materials and methods section should include the formulae for all the metrics employed in the study.
There are some problems related to grammar and word choices in the text.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Reviewer 3 Report
This manuscript presented an interesting study on landslide susceptibility evaluation based on a coupled informative-logistic regression model. In general, the manuscript is well-structured, and some technical issues can be addressed or clarified to improve the quality of the manuscript:
(1) The introduction section is relatively simple and difficult to highlight the contribution or novelty of this study, it is suggested to re-organize this section. Authors can refer to related papers in sustainability, such as ‘Landslide Susceptibility Mapping in Guangdong Province, China, Using Random Forest Model and Considering Sample Type and Balance’ and ‘Landslide Susceptibility Mapping Using DIvisive ANAlysis (DIANA) and RObust Clustering Using linKs (ROCK) Algorithms, and Comparison of Their Performance’.
(2) Lines 124-125: ‘11 influential factors have been chosen as evaluation metrics for assessing landslide susceptibility in Shuangbai County’. Data preprocessing plays a significant role in machine learning. A total of 11 influential factors were considered in this manuscript, it is suggested to provide more details on the data preprocessing process.
(3) It is well recognized that several machine learning methods (e.g., decision trees, artificial neural networks, support vector machines, random forests, and other ensemble strategies) have been successfully applied in landslide susceptibility evaluation. Among them, Logistic regression (LR) was selected in this study. Please explain the reasons underlying this choice.
(4) Table 3 tabulated the correlation coefficients between different factors. It was observed that there exists a positive correlation between factors B and I (i.e., 0.299). In contrast, factor I was negatively correlated with factor E. Please explain the potential mechanisms underlying this observation.
(5) Besides the correlation coefficients between different factors, the relative importance of each input in the output is also a major concern in the application of machine learning, which can be obtained from feature important analysis, such as in ‘Slope stability prediction using ensemble learning techniques: A case study in Yunyang County’ and ‘Prediction of Undrained Shear Strength using Extreme Gradient Boosting and Random Forest Based on Bayesian Optimization’. In this study, the feature important analysis was not presented and the relative importance of the 11 influential factors in the landslide susceptibility evaluation was not investigated. If possible, it is suggested to provide the feature important analysis results.
(6) The conclusion section is relatively lengthy, and it is suggested to focus more on the implications of this study for geotechnical researchers and practitioners in future landslide susceptibility evaluation.
Minor editing of English language required.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Reviewer 4 Report
The manuscript entitled “Landslide Susceptibility Evaluation Based on a Coupled Informative-Logistic Regression Model—Shuangbai County as an Example”, by H. Wang, J. Xu, S. Tan, & J. Zhou, presents an interesting work.
In general, the manuscript should be acceptable for publication but some serious problems must be repaired prior to publication. It needs some significant improvement. Some suggestions are as follows:
- Please follow the journal author instructions. It would be useful for the reader to follow the classical text structure (i.e. Introduction-methodology-results-discussion-conclusions). A better presentation of your results and an extensive discussion would improve your paper.
- I suggest to separate the chapter “6. Conclusion and Discussion”.
- Please use different terms in the “Title” and the “Keywords”.
- It would be useful to be described the aim of this paper.
- The English language usage should be checked by a fluent English speaker. It is suggested to the authors to take the assistance of someone with English as mother tongue.
- You could enrich the scientific literature.
- Please justify convincingly why this manuscript (method, thematology etc) connected with Sustainability’s content and scope. Perhaps the using of proper literature from this journal would be helpful.
- The authors could make discussion about the relationship between landslide susceptibility and planning from the following publications: https://doi.org/10.1016/j.scitotenv.2016.10.025 & https://doi.org/10.3390/land8090128
- The authors could take into account the following publication https://doi.org/10.3390/land7030085
- When you are using coordinates, please do not use “North Arrow”. This is a mistake in cartography.
- Correct references in the text and the reference list according to the journal’s format. Please format the references’ list by using the correct journal abbreviations. See the following link: https://images.webofknowledge.com/images/help/WOS/A_abrvjt.html
- Please be careful with the spaces between the words.
Moderate editing of English language is required
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Round 2
Reviewer 1 Report
Paper can be accepted in its current form.
Minor
Reviewer 2 Report
Although the sources of the DEM and landslide samples remain somewhat elusive, I believe the manuscript is ready for publication. The proposed revisions apart from this are acceptable. The appropriate citation of data sources seems to intersect with the authors' institutional ethical codes, thus falling under their purview.
Reviewer 3 Report
The manuscript has been revised.
Minor editing of English language required
Reviewer 4 Report
The manuscript entitled “Landslide Susceptibility Evaluation Based on a Coupled Informative-Logistic Regression Model —Shuangbai County as an Example” presents an improved and good work.
The manuscript should be acceptable for publication in the present form.
Minor editing of English language is required
