运用BP网络预测地下水位

人工神经网络是一门新兴的交叉学科，是处理非线性问题的有效方法。本文把影响地下水位的因素集作为网络的输入向量，地下水位本身作为网络的输出向量，构成了预测地下水位的ＢＰ网络模型。一个实例的应用实践表明，用ＢＰ网络预测地下水位较准确地反映了客观实际，比其它方法如回归模型具有较高的拟合精度和预测精度。

USING BP NETWORKS TO FORECAST GROUNDWATER LEVELS

Being a developing cross-science, the artificial neural network (ANN) is an efficient method to deal with the nonlinear problems. In the paper, a BP network in which the factors to effect groundwater levels are set as input neurons and the groundwater level is set as output neuron,was established to forecast groundwater level. An application of the BP network in a real case indicates that the forecasting model with the BP network may completely describe the relative between the groundwater level and its affecting factors. It also indicates that the BP forecasting model is mor approximate to realities than other forecasting model such as linear or nonlinear regression models'