RESEARCH ON PREDICTION ABOUT FRUIT TREE DISEASES AND INSECT PESTS BASED ON NEURAL NETWORK

摘要

Fruit tree diseases and insect pests always occur which are related to weather. According to weather information and occurrence status of fruit tree diseases and insect pests in orchards of the Qixia county for 11 years, the MATLAB neural network toolbox was used to build up the prediction system about fruit tree diseases and insect pests based on Back Propagation (BP) neural network. Then the system was trained by the history record data. Finally, the ring spot, a fruit tree disease, was chosen as the research object to compare the predicted value with the actual value. The results indicate that the system can predict accurately, run fast, and function robustly. The system can be applied for prediction about fruit tree diseases and insect pests.