ABSTRACT

This study evaluates and compares three machine learning models: K-Nearest Neighbor (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.

摘要

这项研究评估和比较了三种机器学习模型：K最近邻（KNN），随机森林（RF）和极端梯度增强（XGBoost），用于孟加拉国Rangamati区部分地区的滑坡敏感性地图。这些方法的性能已通过采用统计方法进行了评估，例如成功率（SR）和预测率（PR）的曲线下面积（AUC），Kappa指数，Qs指数和Friedman检验。结果表明，对于SR（95.27％）和PR（90.63％），XGBoost的性能最佳，AUC最高，其次是RF（SR：89.26％; PR：84.74％）和KNN模型（SR：85.54％; PR ：81.02％）。这项研究为选择滑坡敏感性图的最佳模型提供了有用的分析方法，将有助于灾难规划和降低风险。