Landslide Susceptibility Mapping of Chikkamagaluru District, Karnataka Using Ensemble of Frequency Ratio and Evidential Belief Function Models with Geospatial Techniques

This study developed and validated an ensemble GIS-based landslide susceptibility mapping framework for Chikkamagaluru district, Karnataka, using Frequency Ratio and Evidential Belief Function models across eight combination scenarios. The key conclusions are as follows:   • The best-performing ensemble (Scenario 4: EBF + FR) achieved an AUC of 0.919 (success rate) and 0.899 (predictive rate), demonstrating excellent spatial predictive accuracy. • Distance to road, slope gradient, and terrain ruggedness index (TRI) are the dominant conditioning factors for landslide occurrence in the district, highlighting the critical role of anthropogenic activity alongside natural slope conditions. • Highly dissected hills and valleys, predominantly in the central and southern Western Ghats portions of the district, carry the highest geomorphic susceptibility. • The susceptibility zone maps produced can directly support land-use planning, road development guidelines, and early warning system placement in Chikkamagaluru district. • Future research should explore machine learning integration (Random Forest, CNN) and field-verified 3D slope stability models to further improve predictive precision and capture non-linear factor interactions.

[1] A. K. Batar and T. Watanabe, “Landslide Susceptibility Mapping and Assessment Using Geospatial Platforms and Weights of Evidence (WoE) Method in the Indian Himalayan Region: Recent Developments, Gaps, and Future Directions,” ISPRS International Journal of Geo-Information, vol. 10, no. 3, p. 28, 2021. [2] A. D. Regmi et al., “Application of frequency ratio, statistical index, and weights-of-evidence models and their comparison in landslide susceptibility mapping in Central Nepal Himalaya,” Arabian Journal of Geosciences, vol. 6, no. 7, pp. 725–742, 2013. [3] S. Sarkar and D. P. Kanungo, “An Integrated Approach for Landslide Susceptibility Mapping Using Remote Sensing and GIS,” Photogrammetric Engineering & Remote Sensing, vol. 70, no. 5, pp. 617–625, 2004. [4] P. Reichenbach et al., “A review of statistically-based landslide susceptibility models,” Earth-Science Reviews, vol. 180, pp. 60–91, 2018. [5] N. Tengtrairat et al., “Automated Landslide-Risk Prediction Using Web GIS and Machine Learning Models,” ISPRS International Journal of Geo-Information, vol. 10, no. 13, p. 32, 2021. [6] S. R. Meena et al., “Landslide detection in Himalayas using machine learning algorithms and U-Net,” Landslides, vol. 19, pp. 1209–1229, 2022. [7] S. Mondal and S. Mandal, “Data-driven evidential belief function (EBF) model in exploring landslide susceptibility zones for the Darjeeling Himalaya, India,” Geocarto International, vol. 35, no. 8, pp. 818–856, 2020. [8] D. Q. Thanh et al., “GIS based Frequency Ratio Method for Landslide Susceptibility Mapping at Da Lat city, Lam Dong Province, Vietnam,” Vietnam Journal of Earth Sciences, vol. 42, no. 1, pp. 55–66, 2020.