新疆天山北坡经济带地质灾害风险评价模型优选对比研究——以昌吉市为例  

Optimization and Comparison Study of Geological Hazard Risk Assessment Model in Changji City,Xinjiang

作　　者：廖世斌[1] 梁玉霞 李正辉 陶金涛 古丽波斯坦·吐逊江 耿新宇 Liao Shibin;Liang Yuxia;Li Zhenghui;Tao Jintao;Gulbostan·Tursun;Geng Xinyu(Xinjiang Institute of Ecology and Geography,Chinese Academy of Sciences,Urumqi,Xinjiang,830011,China;Xinjiang Zijin Gold Co.,Ltd,xinjaing,845450,China;Xinjiang Key Laboratory of Geohazard Prevention,Xinjiang Institute of Engineering,Urumqi,Xinjiang,830023,China)

机构地区：[1]中国科学院新疆生态与地理研究所,新疆乌鲁木齐830011 [2]新疆紫金黄金有限公司,新疆乌恰845450 [3]新疆工程学院新疆地质灾害防治重点实验室,新疆乌鲁木齐830023

出　　处：《新疆地质》2025年第1期139-148,共10页Xinjiang Geology

基　　金：新疆地质灾害防治重点实验室开放基金资助项目(XKLGP2022K06)资助。

摘　　要：在收集昌吉市地质灾害相关数据的基础上,通过地质科学、地理信息技术及统计方法的交叉应用,揭示研究区地质灾害诱发因素、形成特点和分布趋势,以确定评估风险所需关键因子。再对研究区进行地质灾害易发性评价,通过使用证据权重法和支持向量机模型进行分析评价,利用ROC曲线的AUC值对比选择较佳模型。在易损性评估方面,结合研究区基本资料和易损性评价因子的选择标准,识别人口密度、耕地面积和道路网络等易损性因素,应用模糊数学方法得出昌吉市易损性评估结果。风险评估则是通过ArcGIS分析工具,将危险性和易损性的评估结果相乘。使用ArcGIS通过栅格重叠方法将地质灾害危险性等级和易损性等级相结合,编制地质灾害风险评价图。评价图分为极高、高、中、低4个等级,便于识别不同区域地质灾害风险水平。通过对比不同评估模型在该区域的表现,确定最合适的地质灾害风险评价模型。This paper mainly studies the comparative study of geological disaster risk assessment in the economic belt of the northern slope of the Tianshan Mountains in Xinjiang,taking Changji City as the research area.It collects relevant data on geological disasters in Changji City and uses the interdisciplinary application of geological science,Geographic Information System(GIS)technology,and statistical methods to reveal the inducing factors,formation characteristics,and distribution trends of geological disasters in the research area to determine the key factors required for risk assessment.Then,the geological disaster susceptibility evaluation of the research area is carried out.We used the Evidence Weighting Method and the Support Vector Machine(SVM)model for analysis and evaluation,and the Receiver Operating Characteristic(ROC)curve's Area Under the Curve(AUC)value comparison was used to select the better model.In terms of vulnerability assessment,based on the basic information of the research area and the selection criteria of vulnerability assessment factors,vulnerability factors including population density,arable land area,and road network were identified.The vulnerability assessment results of Changji City were obtained using fuzzy mathematics methods.The risk assessment was conducted by multiplying the results of the hazard and vulnerability assessments using ArcGIS analysis tools.Using ArcGIS,the hazard level and vulnerability level of geological disasters were combined through a raster overlay method to compile a geological disaster risk assessment map.This assessment map is divided into four levels:extremely high,high,medium,and low,to facilitate the identification of geological disaster risk levels in different areas.By comparing the performance of different assessment models in this area,the most suitable geological disaster risk assessment model was determined.

关 键 词：地质灾害 易发性评价 风险评价 证据权模型 支持向量机模型 ROC曲线 

分 类 号：P694[天文地球—地质学]