模糊支持向量机在滑坡危险性评价中的应用

为了将模糊支持向量机应用于滑坡灾害危险性评价工作,并进行验证,进行了研究区滑坡现状的调查,评价指标的选取,隶属函数的确定和基于FSVM的滑坡灾害危险性评价.选取了高程指标、坡度指标、岩土体指标、地表湿度指标及植被覆盖指标等5个指标作为滑坡灾害危险性评价指标,最后以莆田市为例,结合Rs和GIS技术,进行了滑坡危险性评价的研究.评价结果与实地验证和莆田市国土局提供的地质灾害现状图基本吻合.

Application of fuzzy support vector machine to landslide risk assessment

The aim of this study is to apply and verify the use of fuzzy support vector machine ( FSVM) approach for risk assessment of landslide hazard. The study includes four main stages, they are the preparation of a landslide investigation of the study area, the extraction of influence factor of landslide, the determination of fuzzy membership function, the assessment of landslide hazard based on FSVM. The developed approach was tested in the Putian City, southeast of China. Geological data and satellite images were collected, processed, and constructed into a spatial database using GIS and image processing. The factors chosen that influence landslide occurrence are: slope angle, elevation, all from the topographic database; lithologic character taken from the geologic database; vegetation index value and wetness index value from TM satellite images. Each of the above-listed factors was classified and coded using a numerical scale corresponding to the physical conditions of the region. Using those factors, landslide hazard risk was assessed by FSVM methods, and the fuzzy membership values were calculated by combining frequency rati-o and fuzzy operator. The results of the landslide hazard risk assessment were verified using landslide location data. The assessment results show satisfactory agreement with the landslide hazard status map and the existing data on landslide location.