In this paper, short-term forecasts of the rate of plants affected by
rice stripe disease per pentad were conducted using three different
models: stepwise regression, a back propagation neural network, and
support vector machines. The accuracies of the three short-term
forecasting models were determined. By comparing the pros and cons
of this three prediction methods, we can improve the accuracy of
predicting rice plant diseases and provide a scientific basis for its
prevention and control decisions.