Landslide susceptibility mapping in three Upazilas of Rangamati hill district Bangladesh: application and comparison of GIS-based machine learning methods. Issue 12 (4th August 2022)

• Record Type: Journal Article
• Authors: Rabby, Yasin Wahid; Hossain, Md Belal; Abedin, Joynal
• Is Part Of: Geocarto international. Volume 37:Issue 12(2022)
• Page Start: 3371
• Page End: 3396
• Publication Date: 2022-08-04
• Subjects: Landslide susceptibility -- Rangamati -- K-nearest neighbour -- random forest -- XGBoost; Remote sensing -- Periodicals; Geographic information systems -- Periodicals; Geology -- Periodicals; Cartography -- Periodicals; 621.3678
• DOI: 10.1080/10106049.2020.1864026
• Languages: English
• ISSNs: 1010-6049

Abstract

Abstract: This study evaluates and compares three machine learning models: K-Nearest Neighbour (KNN), Random Forest (RF) and Extreme Gradient Boosting (XGBoost) for landslide susceptibility mapping for part of areas in Rangamati District, Bangladesh. The performance of these methods has been assessed by employing statistical methods such as the area under the curve (AUC) for success rate (SR) and prediction rate (PR), Kappa index, Qs index and Friedman's test. Results show that XGBoost had the best performance with the highest AUC for both SR (95.27%) and PR (90.63%), followed by RF (SR: 89.26%; PR: 84.74%) and KNN models (SR: 85.54%; PR: 81.02%). This study provides a useful analysis for the selection of the best model for landslide susceptibility mapping and that it will be helpful for disaster planning and risk reduction.