Susceptibility evaluation of geological disasters in the alpine and canyon areas:A case study of Nujiang Prefecture
FENG Xianjie
LI Yimin
DENG Xuanlun
ZHAO Juanzhen
YANG Yiming
Abstract：Geological disasters are frequent in alpine and canyon areas.Objectives The aim of this study is to investigate the spatial distribution of geological disaster susceptibility.Methods It selected Nujiang Pre-fecture as the research area.By considering geological conditions,meteorological hydrology,vegetation cover,and other factors,a total of 12 evaluation factors with low collinearity,including elevation,slope,as-pect,curvature,relief,etc.,were selected to construct a regional geological hazard susceptibility evaluation index system.Then,the susceptibility of geological disasters was evaluated at grid units using three models:the information value(IV)model,information value-back propagation neural networks(IV-BPNN)coupled model,and information value-support vector machine(IV-SVM)coupled model.Results(1)The suscepti-bility results are validated by using actual geological disaster points,showing good spatial distribution con-sistency between disaster points and the three susceptibility results.(2)The susceptibility index is catego-rized into four levels:low,moderate,high,and extremely high susceptibility areas.The corresponding area proportions of high and extremely high susceptibility classes for the IV model,IV-BPNN model,and IV-SVM model are 37.12%,32.36%,and 23.08%,respectively.High and extremely high susceptibility areas exhibit a linear distribution and are mainly concentrated along coastal watercourses such as the Nujiang River,Lancang River,and Dulong River,near roads,and in areas with active geological structures.(3)The areas under the curve(AUC)of the receiver operating characteristic(ROC)curves for the IV model,IV-BPNN model,and IV-SVM model are 0.884,0.889,and 0.901,respectively.Conclusions All three geologi-cal disasters susceptibility evaluation models demonstrate high prediction accuracy,among which the IV-SVM model shows the highest accuracy and reliable zoning results,which provide valuable reference for lo-cal governments in formulating measures for geological disaster prevention and control.
Keywords：alpine and canyon areasgeological disastersinformation modelBP neural networksupport vec-tor machinesusceptibility evaluationNujiang Prefecture
Publication Date：2024-06-28
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：11( 70-80 )