川西芦山县地质灾害易发性评价模型研究  

Study on Susceptibility Assessment Model of Geologic hazard in Lushan County,Western Sichuan Province

作　　者：薛凯伦 刘严松[1,2] 聂诗音 沈杜衡 李会玲 Xue Kailun;Liu Yansong;Nie Shiyin;Shen Duheng;Li Huiling(College of Earth and Planetary Sciences,Chengdu University of Technology,Sichuan Chengdu 610059;Key Laboratory of Earth Exploration and Information Technology,Ministry of Education,Chengdu University of Technology,Sichuan Chengdu 610059)

机构地区：[1]成都理工大学地球与行星科学学院,四川成都610059 [2]地球勘探与信息技术教育部重点实验室成都理工大学,四川成都610059

出　　处：《石化技术》2025年第2期280-282,共3页Petrochemical Industry Technology

摘　　要：为探究地震带的地质灾害易发性评价模型,本文以川西龙门山地震带的芦山县为研究区,基于区域地质背景及地质灾害发育特征的分析,从地形地貌、地质环境、人类活动、植被覆盖、气象水文、地震带发育特征中等方面选取16个地质灾害评价因子,采用信息量法与随机森林(RF)、反向传播神经网络(BPNN)、卷积神经网络(CNN)相结合的方法对区内地质灾害易发性进行评价,并选用ROC曲线对3种易发性评价模型进行精度分析。结果表明:基于信息量的卷积神经网络模型所获得的易发性分区AUC值为0.992,分区准确性最高、效果最好,最适用于研究区。评价结果对位于龙门山地震带的芦山县地质灾害易发性评价工作提供了参考与借鉴。In order to explore the susceptibility assessment model of geologic hazards in seismic belt,this paper takes Lushan County in the Longmenshan seismic belt in western Sichuan province as the study area,and based on the analysis of regional geologic background and developmental characteristics of geologic hazards,16 geologic hazard evaluation factors are selected from the aspects of topography and geomorphology,geologic environment,human activities,vegetation coverage,meteorology and hydrology,and developmental characteristics of seismic belt,etc.The information volume method combined with random forest(RF),back propagation neural network(BPNN)and convolutional neural network(CNN)was used to evaluate the susceptibility of geologic hazards in the area,and the ROC curve was used to analyze the accuracy of the three susceptibility assessment models.The results show that the AUC value of the susceptibility zoning obtained by the information-based convolutional neural network model is 0.992,which has the highest zoning accuracy and the best effect,and is most suitable for the study area.The assessment results provide a reference and reference for the evaluation of geologic hazard susceptibility in Lushan County,which is located in the Longmenshan seismic zone.

关 键 词：地震带 易发性 机器学习 信息量法 

分 类 号：P69[天文地球—地质学]