Model for assessing water shortage risk based on support vector machine

Based on the principle of support vector machine a model for assessing water shortage risk is proposed. In the model, the assessment of risk is regarded as the regression of a support vector machine and the risk rate, weakness, possibility of recovery, period of reappear and risk level are defined as the indexes for establishing the comprehensive assessment index system for water shortage risk of regional water resources. The application to analysis of the southeast area of Fujian Province, China, shows that the proposed model is feasible and the result indicates the water shortage risk level in this area will be high in 2010, so that measures for risk management must be adopted in the near future.