Mapping landslide susceptibility at the Three Gorges Reservoir, China, using gradient boosting decision tree, random forest and information value models Mapping landslide susceptibility at the Three Gorges Reservoir, China, using gradient boosting decision tree, random forest and information value models

最小化 最大化

Vol17 No.3: 670-685

Title】Mapping landslide susceptibility at the Three Gorges Reservoir, China, using gradient boosting decision tree, random forest and information value models

Author】CHEN Tao1,2*; ZHU Li1; NIU Rui-qing1; TRINDER C John3; PENG Ling4; LEI Tao5

Addresses】1 Institute of Geophysics and Geomatics, China University of Geosciences, Wuhan 430074, China; 2 Geomatics Technology and Application key Laboratory of Qinghai Province, Xining 810001, China; 3 School of Civil and Environmental Engineering, The University of New South Wales, Sydney, NSW 2052, Australia; 4 China Institute of Geo-Environment Monitoring, Beijing 100081, China; 5 School of Electronical and Information Engineering, Shaanxi University of Science and Technology, Xi'an 710021, China

Corresponding author】CHEN Tao

Citation】Chen T, Zhu L, Niu RQ, et al. (2020) Mapping landslide susceptibility at the Three Gorges Reservoir, China, using gradient boosting decision tree, random forest and information value models. Journal of Mountain Science 17(3). https://doi.org/10.1007/s11629-019-5839-3

DOI】https://doi.org/10.1007/s11629-019-5839-3

Abstract】This work was to generate landslide susceptibility maps for the Three Gorges Reservoir (TGR) area, China by using different machine learning models. Three advanced machine learning methods, namely,gradient boosting decision tree (GBDT), random forest (RF) and information value (InV) models, were used,and the performances were assessedand compared. In total, 202 landslides were mapped by using a series of field surveys, aerial photographs, and reviews of historical and bibliographical data. Nine causative factors were then considered in landslide susceptibility mapgenerationby using the GBDT, RF and InV models. All of the maps of the causative factors were resampled to a resolution of 28.5 m. Of the 486289 pixels in the area, 28526 pixels were landslidepixels, and 457763 pixels werenon-landslidepixels. Finally, landslide susceptibility maps were generated by using the three machine learning models, and their performances were assessed through receiver operating characteristic (ROC) curves, the sensitivity, the specificity, the overall accuracy (OA) and the kappa coefficient. The results showed that the GBDT, RF and InV models in overall produced reasonable accurate landslide susceptibility maps. Among these three methods, the GBDT method outperforms the other two machine learning methods, which can provide strong technical support for producing landslide susceptibility maps in TGR.

Keywords】Mapping landslide susceptibility; Gradient boosting decision tree; Random forest; Information value model; Three Gorges Reservoir