Font Size: a A A

Based On Support Vector Machines. Gis Landslide Hazard Evaluation Study

Posted on:2009-02-21Degree:MasterType:Thesis
Country:ChinaCandidate:L X TanFull Text:PDF
GTID:2190360245982615Subject:Cartography and Geographic Information System
Abstract/Summary:PDF Full Text Request
China is a country in which the disasters of frequently landslide happen, the landslide posed the enormous threat to people's life, property safety and the economic development. It has the importantly theoretical and practical significance that how to carry on the landslide disaster risk analysis and the appraisal effectively, and realizes the landslide forecast and the risk management.The development of Geographic Information System (GIS) technology provides a new technical method with the evaluation of landslide risk. Support Vector Machine (SVM) is the hotspot of machine-learning industry research, and in many areas have obtained successful application.Therefore, in the background of the Office of the Fujian Provincial Science and Technology Fund projects "based on support vector machines Geological Hazard Evaluation GIS system" [2006 F3111], this paper tries to combine the GIS technology and the SVM theory in the hazard evaluation of the landslide, and conducted a preliminary research about it.In the paper, the landslide disaster hazard evaluation and the present situation of the SVM research is introduced firstly, and then it is be researched systemically including the establishment of the spatial database of geological disasters, the selection of evaluation indicators, the division of evaluation modules and the application of SVM method in the landslide disaster hazard evaluation. The main research can be summarized as follows:Based on VB+MAPGIS ,in Xian You County the management system of the geological disaster has been developed, the spatial database of the geological disaster,that is, the graph database, the attribute database and seamless connection between them, has established ,which play a role in the browser, query, update and efficient management of geological disasters.According to the actual situation of the research area, the quantification method has been stipulated separately for each of six selected appraisal indexes including the elevation, the gradient, the slope, the gneiss, the rainfall and the vegetation. The system of landslide geology disaster risk appraisal has been established, the special chart of each appraisal index has been obtained by the use of the geographic information system spatial analysis function.From the results of the appraisal, the extremely high-risk danger and the high-risk danger areas are basically located in the central and northwestern parts of the study area, a north-east distribution; the secondary risk in both sides of its distribution, and the low-risk are generally along North West distribution. This distribution result basically has reflected the geological disaster growth present situation in the research area.
Keywords/Search Tags:Support Vector Machine, GIS, landslides, hazard evaluation, geological disasters
PDF Full Text Request
Related items