As a destructive geological event,geological disaster often poses a serious threat to human life,property and living environment,and restricts the sustainable development of human society.In particular,a series of disaster chains,such as earthquakes and a series of secondary disasters induced by them,have more and more serious impacts on the ecosystem and the environment,and have become a hot and difficult issue in current geological disaster research.This study takes Maoxian County in Sichuan Province as an example to study the earthquake-geological disaster chain in the region,construct a deep learning model suitable for the earthquake-geological disaster chain,introduce the risk prediction research,and comprehensively analyze the earthquake-geological disaster chain Risk,and its risk has been evaluated.The main results of this research are as follows:(1)A deep neural network model suitable for the earthquake-geological disaster chain is constructed,and an integrated model is constructed on this basis.The sample data extracted from the study area is input into the model to train it,and a variety of verification methods are used to calculate and comparing the accuracy of different models,the results show that the two proposed models have good performance,suitable for the prediction and evaluation of earthquake-induced geological disasters.(2)According to the historical disaster situation,the distribution characteristics of earthquake-geological disasters are analyzed,and the evaluation factors are extracted by combining multi-source data and comprehensive use of GIS spatial analysis and other functions.The susceptibility and risk assessment of the earthquake-geological disaster chain was carried out,and the susceptibility and risk zoning map of the earthquake-geological disaster chain was obtained.(3)A risk assessment index system and a risk assessment model for earthquake-induced geological disasters were constructed,and a comprehensive risk assessment of earthquake-geological disasters in Maoxian was carried out from four aspects: exposure,vulnerability,and disaster prevention and mitigation capabilities.Extremely high-risk areas and high-risk areas accounted for 4.36%,mainly in Nanxin Town in the southwest of Maoxian County,Guangming Township and Yonghe Township in the southeast,and low-altitude areas beside highways and close to faults in the county.The research results obtained in this study can provide better decision support for the prediction and early warning of earthquake-induced geological disaster chain in Maoxian area,disaster rescue and chain-break disaster reduction,and provide a basis for formulating risk prevention measures for earthquake-induced geological disasters in Maoxian County according to local conditions. |