The Application of Remote Sensing Technology to the Construction of Risk Assessment Model for Rainfall-Induced Landslides
In this study,the Genetic Adaptive Neural Networks with texture analysis is employed for the classification of satellite images after 2009 Typhoon Morakot to obtain digital records of the ground and disaster.Ten landslide hazard potential factors are included: slope,geology,elevation,distance from the fault,distance from water,terrain roughness,slope roughness,effective accumulated rainfall and developing situation.To study satellite images before and after typhoon,the image subtraction and normalized vegetation are used to calculate index for disaster information.A long interview with the local residents,review of the relevant literature,and setting out the conditions for the preservation of objects of the probability of victimization are carried out to calculate the spatiotemporal impact of the study area,vulnerable area to flooding and resistance level of disaster probability of exposure of the population.The regional risk map is plotted with the help of GIS and the landslide assessment model.The results show that the landslides predicted by this study is consistent with the information provided on the website of Soil and Water Conservation Bureau.
Image classification Landslide risk assessment Genetic Adaptive Neural Network Dangerous Value Method GIS
CHEN Yie-Ruey HSIEH Shun-Chieh TSAI Kuang-Jung MAI Wan-Ju LIN Wei-Chung CHANG Yun-Yue
Department of Land Management and Development, Chang Jung Christian University, 396 Chang Jung Road, Tainan,Chinese Taipei
国际会议
成都
英文
48-68
2012-10-15（万方平台首次上网日期，不代表论文的发表时间）