The manuscript “From typhoon rainfall to slope failure: optimising susceptibility models and dynamic thresholds for landslide warnings in Zixing City, China” tackles an important and timely topic with clear potential to contribute to landslide hazard research and early warning practices. The integration of modelling approaches is promising; however, the manuscript in its current form requires substantial revisions. Key issues relate to clarity, consistency, methodological justification, and depth of discussion.

The following are some comments that are intended to be constructive and to help the authors strengthen the manuscript, ensuring it meets NHESS standards and realises its potential contribution.

1. Define all new terms (e.g., IV, CF, FR, SVM, and others) when they first appear in the text, including in the abstract.

2. Why is it necessary to develop a hazard warning system for typhoon-induced landslides in this specific area? Provide a stronger justification. At present, the manuscript only discusses methodological limitations in the introduction. The research gap is unclear, and the rationale for conducting this work specifically in Zixing City is insufficient.

3. The manuscript sometimes uses the term “typhoon-specific hazard monitoring systems” and other times “typhoon rainfall-induced landslide hazard warning system”. It would be better to use consistent terminology throughout. I suggest adopting “typhoon-specific rainfall-induced landslide monitoring systems”, as this best reflects the study’s main objective and reduces confusion for the reader.

4. Provide more information about the study area, including its geographical, geophysical, geological, and hydrological characteristics.

5. Add the units of the factors shown in Figures 2a and 2b.

6. In the text, the authors state that they used 705 landslide points, but Figure 3 (the framework flowchart) refers to 645. Please clarify this inconsistency.

7. There are many machine learning models available for classification tasks. Why did you choose SVM and LightGBM over others? Please justify this choice.

8. Clarify the mechanism for assigning D7 (or other designations) to each landslide point. Specifically, explain how each of the >700 landslide points was linked to one of the 12 rain gauge stations.

9. Provide detailed explanations of all factors with significant results in Table 2. The current explanations are not sufficient.

10. Include the statistical results of the multicollinearity test in the appendix (or supplementary material), and reference them in the main text.

11. Explain how you normalised the resolution of the different factor maps. Since the primary data have different scales, all layers must be resampled to the same resolution to create the susceptibility map.

12. Adjust the font size in Figures 4, 5, and 6. At present, the text appears disproportionately large compared to the maps.

13. Present the AUC values in separate columns for training and testing in Table 3.

14. Avoid the use of unnecessary em dashes (—) throughout the text.

15. Ensure consistency across figures. For example, in Figure 6, landslide points are shown only on the first two maps (SVM and LightGBM), whereas in Figure 7, they are shown on all maps. Standardise this approach.

16. Adjust the sizes of the maps in Figure 8 so that all are presented at the same scale.

17. Why do you describe the final product as a monitoring system? Will it be hosted online for interactive use? If not, it is more accurate to describe it as a hazard zonation map. At times, you also refer to it as a framework. Please avoid such inconsistencies.

18. Consider evaluating the performance of the warning zonation maps (Figures 8d and 8e).

19. In the discussion, you state that the system “can identify regions where slopes are already saturated due to pre-typhoon rainfall and are thus highly susceptible to failure during the typhoon’s high-intensity rainfall phase.” How does it achieve this? Is the system dynamic? The manuscript provides no evidence of using dynamic data; all analyses appear to rely on static datasets. Please clarify.

20. The manuscript lacks a sufficiently scholarly discussion. Strengthen the reasoning behind your findings by incorporating more relevant references.

Manuscript Title: From typhoon rainfall to slope failure: optimizing susceptibility models and dynamic thresholds for landslide warnings in Zixing City, China

General Comments

This manuscript presents an integrated framework that combines landslide susceptibility mapping (SVM and LightGBM models with variable weighting methods) and dynamic rainfall threshold analysis to develop a hazard warning system for typhoon-induced slope failures in Zixing City, China. The topic is timely and relevant, especially given the growing impact of climate change on rainfall extremes in East Asia.

The paper demonstrates novelty by addressing buffer-based negative sampling, variable weighting methods (IV, CF, FR), and machine-learning comparisons in susceptibility mapping along with rainfall-threshold optimization for typhoon-related landslides. However, the manuscript suffers from significant weaknesses: inconsistencies in reported data, missing geological context, limited validation (single-event dependence), overreliance on AUC for model evaluation, and insufficient discussion of applicability to broader settings. Figures also lack clarity, and some equations and references are incomplete.

Overall, while the paper has potential, it requires major revisions to improve methodological transparency, data consistency, and presentation.

Specific Comments

Major Issues:

1. Inconsistency in landslide numbers – The text reports 705 landslides, whereas Figure 3 shows 645. This must be corrected.
2. Geological context missing – Although lithology and faults are considered, the manuscript does not include a geological/lithological map of the study area. This is essential for interpretation.
3. Grid resolution limitations – Landslides are mapped at 60 m resolution. The authors should explain how small landslides (<60 m) were treated and how this may bias the results.
4. Negative sampling buffers – The choice of 0.1–5 km buffer distances lack geomorphic or literature justification. A sensitivity or rationale discussion is required.
5. Single-event validation – The entire framework is based only on Typhoon “Gemei” (2024). This risks overfitting. Authors should at least discuss how thresholds might vary for different typhoons.
6. Evaluation metrics – Reliance solely on AUC is inadequate. Precision, recall, F1-score, and confusion matrices should be added to strengthen model evaluation.
7. Rainfall threshold interpolation – Kriging interpolation is applied, but no error assessment (e.g., RMSE, cross-validation) is reported. This weakens reliability.
8. Climate change context – The discussion does not adequately address how projected changes in typhoon rainfall regimes may affect thresholds and susceptibility.

Minor Issues:

1. Typhoon name is inconsistent, “Gemei (L155)” vs. “Gaemi (L443)”.
2. Figures (e.g., Figs. 4–8) lack scale bars, legends, or are too complex. Improve readability and resolution.
3. Equations (e.g., Eq. 5 for CF) are introduced but poorly explained; variable definitions should be clearer.
4. English expression should be tightened. Phrases like “typhoon rainfall dynamics” are repeated excessively.
5. Abstract is overloaded with technical values (e.g., AUC, buffer sizes). It should be simplified to highlight novelty and findings.