三江平原井灌水稻区地下水动态变化规律的小波神经网络分析

Dynamic Variation Regularities Analysis of Groundwater in Well Irrigation Paddy in Sanjiang Plain Based on Wavelet Neural Network

以853农场为例,利用小波分析的多分辨率功能和人工神经网络的非线性逼近功能,建立了基于小波变换和BP神经网络的853农场地下水埋深动态预测小波神经网络模型,对地下水动态变化规律进行分析,精度检验及对比分析结果表明,模型拟合和预测精度均较高。预测结果表明,853农场未来几年内地下水位会持续下降,年平均降幅为0.66 m左右,因此当地应加强地下水的科学管理。该模型揭示了区域地下水动态变化规律,为853农场乃至三江平原井灌区地下水资源的可持续利用提供了科学依据。

Taking 853 Farm as example, through applying wavelet analysis＇s multi-resolution function and artificial neural network＇s nonlinear approaching function, built up the monthly groundwater embedment depth dynamic prediction model of Farm 853 based on wavelet transform and BP neural network. Through using this model, the groundwater dynamic variation regularities were analyzed. The results of precision test and comparative analysis showed that the precisions of this model were high in fitting and prediction. The results of prediction showed that the groundwater level of Farm 853 will continually descend within the intending several years, the annual descending extent will be about 0.66 m on average. So, local government should reinforce the scientific management towards groundwater. The model revealed the region＇s groundwater dynamic variation regularities. The study can provide scientific gist for sustainable utilization of groundwater resource in area of well irrigation paddy in Farm 853 so much as the entire Sanjiang Plain.