Integrating predictive modeling techniques with geospatial data for landslide susceptibility assessment in northern Pakistan

作     者：Aamir ASGHAR SU Li-jun ZHAO Bo Nadeem Ahmad USMANI Aamir ASGHAR;SU Li-jun;ZHAO Bo;Nadeem Ahmad USMANI

作者机构：Key Laboratory of Mountain Hazards and Earth Surface ProcessInstitute of Mountain Hazards and EnvironmentChinese Academy of Sciences(CAS)Chengdu 610041China University of Chinese Academy of SciencesBeijing 100049China China-Pakistan Joint Research Center on Earth SciencesCAS-HECIslamabad 45320Pakistan The University of Poonch RawalakotRawalakot 12350Pakistan 

出 版 物：《山地科学学报(英文)》 (Journal of Mountain Science)

年 卷 期：2023年第20卷第9期

页      面：2603-2627页

核心收录：

学科分类：081603[工学-地图制图学与地理信息工程] 081802[工学-地球探测与信息技术] 081803[工学-地质工程] 07[理学] 08[工学] 070503[理学-地图学与地理信息系统] 0818[工学-地质资源与地质工程] 0705[理学-地理学] 0816[工学-测绘科学与技术] 0814[工学-土木工程] 082301[工学-道路与铁道工程] 0823[工学-交通运输工程] 

基　　金：supported by the National Natural Science Foundation of China(Grant No.U22A20603) the Strategic Priority Research Program of the Chinese Academy of Sciences(Grant No.XDA20030301) 

主　　题：Landslides MMMM expressway Machine learning Landslide susceptibility Northern Pakistan 

摘      要：The eastern road section of the ChinaPakistan Economic Corridor(CPEC)traverses the challenging terrain of northern Pakistan,where frequent landslides pose a significant threat to socioeconomic development and ***,the insufficient data on landslide hazards presents a substantial challenge to practical mitigation ***,we conducted an extensive study to gain insight into landslide assessment along the Mansehra-Muzaffarabad-Mirpur and Mangla(MMMM)*** study involved preparing a landslide inventory,analyzing landslide causative factors,and developing landslide susceptibility models(LSMs)using published data,remote sensing interpretations,field excursions and integrated predictive *** first used Pearson s correlation coefficient(PCC),variable importance factors(VIF),and information gain ratio(IGR)to evaluate multicollinearity among the selected landslide causative factors(LCFs).Then,the topographic roughness index(TRI)with VIF5 and PCC0.7 was considered a redundant factor and thus removed before the data ***,we adopted multiple machine-learning methods to analyze landslide *** results indicate that the landslide inventory contains 1,776 events,of which 674 were classified based on geometrical and lithological *** IGR results show that the rainfall,lithology,PGA,drainage density,slope,and distance to fault are the most effective *** AUC values for random forest(RF)(0.901),extreme gradient boosting(XGBoost)(0.884),and K-nearest neighbor(KNN)(0.872)remained higher than evidential belief function(EBF)(0.833),weight of evidence(WoE)(0.820),and certainty factor(CF)(0.810),*** RF model outperformed all other models in terms of ***,these models are accurate but newer in the area;thus,susceptible zones were verified with comprehensive field *** northern and central regions accounted for the high and very high susceptibility classes in th