WANG Li-shu;QI Guo-qiang;WANG Ke-fei

;Engineering College, Northeast Agricultural University, Harbin Heilongjiang 150030, PRC

artificial neutral networks;hopfield;soybean;yield forecast

Using the artificial nerve network's knowledge, establish the estimate's mathematics model of the soybean's yield, and by the model we can increase accuracy of the soybean yield forecast. The model is a kind of number value method that is widely usedin forecasting, by setting up simulation model, we can get some relevant conclusions and realize predict function in order to assist people making decision. In general situation, it is very difficult to set up relative and accurate mathematics model reflect objective systems, it is even impossible sometimes, but there are certain relations between various kinds of factors. If we can find the mathematics model which reflect the realistic input and output system, it has very important significance in yield forecasting.