A Comprehensive Assessment of XGBoost Algorithm for Landslide Susceptibility Mapping in the Upper Basin of Ataturk Dam, Turkey

The success rate in landslide susceptibility mapping efforts increased with the advancements in machine learning algorithms and the availability of geospatial data with high spatial and temporal resolutions. Existing data-driven susceptibility mapping models are not globally applicable due to the high variability of landslide conditioning parameters and the limitations in the availability of up-to-date and accurate data. Among numerous applications, landslide susceptibility maps are essential for site selection and health monitoring of engineering structures, such as dams, for increasing their lifetime and to prevent from disastrous events caused by the damages. In this study, landslide susceptibility mapping performance of XGBoost algorithm was evaluated in a landslide-prone area in the upper basin of Ataturk Dam, which is a prime investment located in the southeast of Turkey. The study area has a size of 2718.7 km(2) with an elevation difference of ca. 2000 m and contains 27 lithological units. EU-DEM v1.1 from the Copernicus Programme was used to derive the geomorphological features. High classification accuracy with area under curve value of 0.96 could be obtained from the XGBoost algorithm. According to the results, the main factors controlling the landslides in the study area are the lithology, altitude and topographic wetness index.

Automated summary

Landslide susceptibility mapping efforts have seen increased success with advancements in machine learning algorithms and the availability of high-resolution geospatial data. The XGBoost algorithm showed high classification accuracy in a landslide-prone area in southeastern Turkey, highlighting the significance of landslide susceptibility mapping for site selection and health monitoring of engineering structures. The main controlling factors for landslides in the study area were identified as lithology, altitude, and topographic wetness index.