Research on landslide prediction based on support vector model

The Landslide, which is caused by mining activities, has become an important factor which constrains the sustainable development of mining area. Thus it becomes very important to predict the landslide in order to reduce and even to avoid the loss in hazards. The paper is to address the landslide prediction problem in the environment of GIS by establishing the landslide prediction model based on SVM (support vector machine). Through differentiating the stability, it achieves the prediction of the landslide hazard. In the process of modeling, the impact factors of the landslide are analyzed with the spatial analysis function of GIS. Since the model parameters are determined by cross validation and grid search, and the sample data are trained by LIBSVM, traditional support vector machine will be optimized, and its stability and accuracy will be greatly increased. This gives a strong support to the avoidance and reduction of the hazard in mining area.