Forecasting the rice stem borer occurrence tendency based on support vector machine

Support vector machine (SVM) which overcomes the drawbacks of neural networks has been widely used for forecasting and pattern recognition in recent years. In the study, the proposed SVM model is applied to pest degree forecasting of rice stem borer, and the structure of SVM forecasting system of pest degree is presented. The real data sets are used to investigate its feasibility in pest degree forecasting. The forecasting results indicate that SVM has higher forecasting accuracy than that of RBFNN in pest degree forecasting.