COMPREHENSIVE LANDSLIDE HAZARD ASSESSMENT IN KYRGYZSTAN BASED ON SATELLITE DATA AND MACHINE LEARNING APPROACHES
Keywords:
landslide susceptibility mapping, geographic information systems (GIS), machine learning, Random Forest, SRTM, digital elevation model (DEM), Topographic Wetness Index (TWI)Abstract
This study examines the application of geographic information systems (GIS) and machine learning methods for landslide susceptibility mapping in the southern regions of Kyrgyzstan. The analysis is based on the SRTM digital elevation model and statistical data on previously recorded landslides. Morphometric terrain characteristics, including slope, aspect, curvature, and the Topographic Wetness Index (TWI), were derived and used as input features for model training. A Random Forest algorithm was employed to assess landslide susceptibility. As a result, a landslide probability map was generated, enabling the identification of the most vulnerable and potentially hazardous areas within the study region. The results confirm the effectiveness of integrating geospatial analysis and machine learning techniques for regional-scale natural hazard assessment.
References
1. Breiman L. Random Forests Breiman L. Random Forests // Machine Learning. - 2001. - Vol. 45, № 1. - С. 5–32.
2. Moore I.D. Digital terrain modelling review Moore I.D., Grayson R.B., Ladson A.R. Digital terrain modelling: A review of hydrological, geomorphological, and biological applications // Hydrological Processes. - 1991. - Vol. 5. - С. 3–30.
3. Reichenbach P. Landslide susceptibility models review Reichenbach P., Rossi M., Malamud B.D., Mihir M., Guzzetti F. A review of statistically-based landslide susceptibility models // Earth-Science Reviews. - 2018. - Vol. 180. - С. 60–91.
4. Tarboton D.G. Flow direction method Tarboton D.G. A new method for the determination of flow directions and upslope areas in grid digital elevation models // Water Resources Research. - 1997. - Vol. 33, №2. - С. 309– 319.
