论文部分内容阅读
位于黄河流域上游干旱半干旱的青铜峡灌区是宁夏工农业生产和社会经济发展的重要地区。灌区耗水量占宁夏引黄灌区耗水量的绝大部分,因此,对该灌区耗水量研究非常必要。本论文在查阅大量国内外相关文献资料的基础上,针对灌区农业耗水量的影响因素做了分析,将引水量、排水量、降雨量、蒸发量和地下水位埋深作为最主要的影响因子,建立青铜峡河东灌区农业灌溉耗水量的BP神经网络预测模型。结果表明,网络函数的选取和结构设计较为合理,误差满足要求,精度较高,可应用于进行其它年份灌溉耗水量的预测。应用此网络对2003年河东灌区农田灌溉耗水量进行了预测,证明该模型适合于灌区农业耗水量的预测,具有一定的推广价值。
The arid and semi-arid Qingtongxia irrigation area located in the upper reaches of the Yellow River basin is an important area for industrial and agricultural production and social and economic development in Ningxia. The water consumption in irrigated area accounts for most of the water consumption of Yellow River Irrigation District in Ningxia, therefore, it is necessary to study the water consumption in the irrigated area. On the basis of consulting a large number of domestic and foreign literature, this paper analyzed the influencing factors of agricultural water consumption in irrigation districts and established the most important influencing factors of water diversion, displacement, rainfall, evaporation and groundwater table depth Prediction Model of Agricultural Water Consumption for Hetong Irrigation Area in Qingtongxia by BP Neural Network. The results show that the selection of network functions and the structural design are reasonable, the errors meet the requirements and the precision is high, which can be applied to predict the water consumption of irrigation in other years. This network was used to forecast the water consumption of irrigation in Hedong irrigation area in 2003, which proves that the model is suitable for the prediction of agricultural water consumption in irrigation area and has certain promotion value.