Assessing the relationship between landslide susceptibility and land cover change using machine learning

Abstract

Landslides are natural disasters most frequent in the mountain region of Vietnam, producing critical damage to human lives and assets. Therefore, precisely identifying the landslide occurrence probability within the region is essential in supporting decision-makers or developers in establishing effective strategies for reducing the damage. This study is aimed at developing a methodology based on machine learning, namely Xgboost (XGB), lightGBM, K-Nearest Neighbors (KNN), and Bagging (BA)  for assessing the connection of land cover change to landslide susceptibility in Da Lat City, Vietnam. 202 landslide locations and 13 potential drivers became input data for the model. Various statistical indices, namely the root mean square error (RMSE), the area under the curve (AUC), and mean absolute error (MAE), were used to evaluate the proposed models. Our findings indicate that the Xgboost model was better than other models, as shown by the AUC value of 0.94, followed by LightGBM (AUC=0.91), KNN (AUC=0.87), and Bagging (AUC=0.81). In addition, urban areas increased during 2017-2023 from 25 km² to 30 km² in very high landslide susceptibility areas. Our approach can be applied to test the other regions in Vietnam. Our findings might represent a necessary tool for land use planning strategies to reduce damage from natural disasters and landslides.