Tuesday 18 July 5:30 p.m. - 6:30 p.m. (Canada/Eastern)
Abstract
Landslide susceptibility analysis (LSA) is a popular and effective way to determine the possibility of landslide occurrence in a specific area, and further reduces the losses. This study sims to improve the landslide spatial prediction in Penang, Malaysia using gradient boosting models, eXtreme Gradient Boosting (XGBoost) model and Light Gradient Boosting Machine (LightGBM), combined with the oversampling techniques. The results are analyzed and discussed mainly based on receiver operating characteristic (ROC) curves as well as the area under the curves (AUC). The results show that the highest AUC value of 0.9525 is obtained from the combination of XGBoost and SMOTE. The landslide susceptibility maps (LSMs) produced by XGBoost and LightGBM can provide valuable information in landslide management and mitigation in Penang Island, Malaysia.
aSchool of Sciences, Changzhou Institute of Technology, Changzhou City, Jiangsu Province, P.R. China, 213032
bSchool of Mathematical Sciences, Universiti Sains Malaysia, 11800 USM, Penang, Malaysia
cSchool of Electrical and Electronic Engineering, USM, Engineering Campus, Seberang Perai Selatan Nibong Tebal, Penang, 14300, Malaysia
