根据白城市1960年-2010年的年降雨量数据,应用自相关分析方法来确定降雨量预测模型的输入输出变量,然后应用径向基函数人工神经网络方法来识别前期降雨量和后期降雨量的关系,并对白城市未来的年降雨量进行预测。结果表明:模型精度较高,所建立的神经网络预测模型可以用来对白城市的年降雨量进行预测。预测结果将对农业管理和灾害防治起到重要的作用。 According to the annual rainfall data of 1960 to 2010 in Baicheng City, the autocorrelation analysis method was used to determine the input and output variables of the rainfall forecast model, and then the RBF neural network method was used to identify the pre- and post-rainfall Relations, and predict the future annual rainfall of Baicheng City. The results show that the accuracy of the model is high, and the neural network prediction model can be used to predict the annual rainfall of Baicheng City. The forecast results will play an important role in agricultural management and disaster prevention.