Abstract: Pest forecasting model based on the BP neural network shows an inefficient learning speed together with high dimension， which could decrease the prediction accuracy. To improve the accuracy， a fuzzy neural network prediction model based on the combination of the artificial neural network and fuzzy system was built， and was compared with the BP neural network prediction model. It was showed that the fuzzy neural network could be much more accurate and faster， which suggested the new method for pest forecast should be more effective.

Key words: fuzzy neural network, neuron, pest forecasting model