On precipitation prediction model from the combination of artificial neural network and mean generation function

In this paper, the primitive monthly precipitation series are reconstructed as independent variables by mean generating function, and the primitive rainfall series are dependent variables. The factor affecting is withdrew by means of principal component analysis method to extract the most important components so that it can be input as the neural network, and a forecast model of the neural network is established with principal component analysis based on mean generating function. By applying normal testing methods in this essay, monthly precipitation in May in the north of Guangxi tallies with normal distribution. The model of precipitation in May in the north of Guangxi is worked out. Results show that the model is superior in predictions compared to the time series analysis model, and it is a useful model for the actual operational forecasting.