Spatial Analysis on the Variances of Landslide Factors Using Geographically Weighted Logistic Regression in Penang Island, Malaysia

Round 1

Reviewer 1 Report

In this study, the author(s) examine the likelihood of landslide in relation to a variety of factors such as distance to road, distance to river, distance to fault, slope angle, slope aspect, curvature, rainfall annual average, lithology, soil series, and land use. In general, the article is well organized and the results are presented in a logical order. However, I suggest the authors make extensive revisions to the current version before it can be considered for publication.

Firstly, in addition to better model performance, the GWLR method has advantages in analyzing spatially varying effects of these factors. The discussion on spatial heterogeneity in the discussion section should be rewritten to reflect this. This may help justify the usage of the GWLR model. Some diagnostic statistics in spatial analysis and modeling such as Moran's I of residuals should also be included in Table 3.

Secondly, the study concludes with the statement that the maps generated can be useful for authorities to make decisions. I suggest the authors give some examples to support this argument. Are there any management strategies that may need to be altered in the future? Overall, the study is presented in a very technical way. The discussion and conclusion sections should be rewritten to address more meaningful findings and the implications of the regression analysis presented. 

Author Response

Please see the attachment

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments for author File: Comments.pdf

Author Response

Please see the attachment

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

I have no other comments.

Reviewer 2 Report

Dear Authors,

The manuscript is sufficiently improved. Thank you for addressing my concerns.

Best wishes