The Study Base On Artificial Network Of Simulated Groundwater Movement Changes

Groundwater systerms is acomplex,which is often affected by many factors such as volume of rainfall, irrigating infiltration , river supply , supply through hydrous stratum, pump water for irrigation and production. Groundwater movement changes have the non-linear feature and nondeterministic features. The tradition groundwater movement changes has not produced good results in application because it involved many reaction process and parameters ,which cannot be determined by sophisticationed methods for measuring. Artificial Neural Network has self-adaptive,self-learning and fault-tolerant capacity as well as large-scale concurrent operation,which is particularly applicable for inaccurate and fuzzy information precessing with many factors and conditions involved. Therefore,the application of Artificial Neural Network provides a new approach to the prediction of groundwater with unique advantages.The paper divide investigating feng and zao river source district into 67 node of proportional apacing., to each node adopts MATLAB 6.5 as computational platporm and BP neual network configation .The data of groundwater movement changes is determined after process analysis, which are olume of rainfall, irrigating infiltration , river supply , supply through hydrous stratum, pump water for irrigation and production refer to output nerve cell. Based on monitoring data of feng and zao river source district,BP network is analyzed in terms of the factors affecting learing efficiency and prediction accuracy. Furthermore ,after its application to groundwater prediction of the station is optimized with regard to the amount of neural cell in implied level, training frequency, excitation function in implied level,learning sample numbers ,BP Artificial Neural Model is introduced to the prediction of latent and pressure groundwater ,and educe to groundwater movement changes rule of each node.The last,the data is simulated the map of groundwater movement changes within calculating district throught MATLAB 6.5,its can be showing intuitionistic changes and trend of groundwater movement.The result indicates that relative errors less than 0.5 meter between the predication results of BP model and the monitoring data of groundwater level,Such a high accuracy can meet the requirements of predication of groundwater resource.