CF耦合LR模型的地质灾害易发性评价  

Evaluation of geological hazard susceptibility based on certainty factors coupling logistic regression

作　　者：王璇 师芸[1,2] 陈浩 WANG Xuan;SHI Yun;CHEN Hao(College of Geomatics,Xi'an University of Science and Technology,Xi'an 710054,China;Key Laboratory of Coal Resources Exploration and Comprehensive Utilization,Ministry of Land and Resources,Xi'an University of Science and Technology,Xi'an 710021,China;Shaanxi Key Laboratory of Disasters Monitoring and Mechanism Simulation,Baoji 721013,China)

机构地区：[1]西安科技大学测绘科学与技术学院,陕西西安710054 [2]西安科技大学国土资源部煤炭资源勘查与综合利用重点实验室,陕西西安710021 [3]陕西省灾害监测与机理模拟重点实验室,陕西宝鸡721013

出　　处：《测绘通报》2022年第11期112-117,共6页Bulletin of Surveying and Mapping

基　　金：国家自然科学基金(41674013,41874012)。

摘　　要：为对自然灾害频发的西北地区进行地质灾害易发性研究,本文考虑了高程、坡向等10类因素,利用确定性系数(CF)模型和确定性系数耦合逻辑回归(CF-LR)模型对城固县地质灾害易发性进行评价。结果表明,CF模型和CF-LR模型的灾害比均呈递增状态,高、极高灾害点密度分别为4.75、5.97个/km~2,且两种模型的测试集受试者工作特征(ROC)曲线下面积(AUC)分别为0.812、0.835,验证集ROC和AUC值分别为0.862、0.891。两种模型均能有效评价区域内地质灾害易发性,且CF-LR模型具有更高的评价精度。In order to study the susceptibility of geological disasters in the Northwest region, where natural disasters frequently occur, we consider ten factors, such as elevation and slope aspect, and use the coefficient of certainty(CF) model and the coupled logistic regression(CF-LR) model to evaluate the susceptibility of geological hazards in Chenggu county. The results show that the disaster ratios of the CF model and the CF-LR model are increasing, and the density of high-extremely high disaster points are 4.75/km~2and 5.97/km~2 respectively. In addition, in the test data set, the area under curve(AUC) of the receiver operating characteristic(ROC) of the two models are 0.812 and 0.835 respectively. In the validation dataset, the AUC of the ROC of the two models are 0.862 and 0.891 respectively. Both models can effectively evaluate the susceptibility of geological disasters in the region, and the CF-LR model has higher evaluation accuracy.

关 键 词：地质灾害 易发性评价 逻辑回归模型 相关性系数 确定性系数模型 

分 类 号：P208[天文地球—地图制图学与地理信息工程]