Groundwater environment evolution can comprehensively reflect groundwater dynamics. Based on the relationship between the groundwater system and the external environment in Jinghuiqu irrigation district, adopting the Principal Component Analysis method, variation characteristics of environmental factors including climate and human activity and their impact on groundwater were systematically analyzed. The results show that groundwater level in Jinghuiqu irrigation district has been significantly dropped in nearly 34 years; the reduction of surface water irrigation use, which reduced the amounts of groundwater recharge and destroyed the water balance, is considered as the most direct cause for falling of regional groundwater level. Besides, reduction in precipitation, increase of evaporation also accelerated the declining of the groundwater level at some extent. Finally, a predicting method of groundwater depth based on BP neural network is developed. The experimental results show that the predicting model can reasonablely predict the groundwater level in Jinghuiqu irrigation district with a high precision.
 Liu, K.K. and Li, C.H. (2012) Water Resources Supply-Consumption (Demand) Balance Analyses in the Yellow River Basin in 2009. Procedia Environmental Sciences, 13, 1956-1965. http://dx.doi.org/10.1016/j.proenv.2012.01.189
 Xu, X. and Huang, G.H. (2010) Assessing the Groundwater Dynamics and Impacts of Water Saving in the Hetao Irrigation District, Yellow River Basin. Agricultural Water Management, 98, 301-313. http://dx.doi.org/10.1016/j.agwat.2010.08.025
 Li, P. and Wei, X.M. (2014) Response of Groundwater Cycle to Environmental Changes in Guanzhong Plain Irrigation District. Transactions of the Chinese Society of Agricultural Engineering, 30, 123-131.
 Daliakopoulos, I.N., Coulibaly, P. and Tsanis, I.K. (2005) Groundwater Level Forecasting Using Artificial Neural Networks. Journal of Hydrology, 309, 229-240. http://dx.doi.org/10.1016/j.jhydrol.2004.12.001
 Sahooa, G.B., Raya, C. and Wadeb, H.F. (2005) Pesticide Prediction in Ground Water in North Carolina Domestic Wells Using Artificial Neural Networks. Ecological Modelling, 183, 29-46. http://dx.doi.org/10.1016/j.ecolmodel.2004.07.021