Research on Natural Disaster Risk Assessment Model Based on Support Vector Machine and Its Application

The natural disaster risk assessment model based on support vector machine (SVM) is put forward according to the features of natural disaster risk assessment. The indicator system which includes the collapse of houses, the affected areas, the number of casualties, direct economic losses is established by China's actual situation of the regional meteorological disaster. A case for assessing the natural disasters risk of Chinese regions is studied using the established model. The evaluation results show that the evaluation model established is simple and effective. It has good generalization ability in the case of small samples. The results of research in this paper have important reference for natural disaster risk management and decision-making.