BP神经网络在不同植被产流产沙分析中的应用  

Application of BP Neural Network to the Analyses of Runoff and Sediment Yield with Different Types of Vegetation

作　　者：李淼[1] 周建国[2] 宋孝玉[3] 沈冰[3] 

机构地区：[1]长沙理工大学 水利学院,湖南长沙410076 [2]中国水电工程顾问集团公司中南勘测设计研究院,湖南长沙410014 [3]西安理工大学 水资源研究所,陕西西安710048

出　　处：《水土保持通报》2007年第6期152-155,224,共5页Bulletin of Soil and Water Conservation

基　　金：国家自然科学基金(50209016);陕西省自然科学基金(2003D13);陕西省教育厅重点实验室项目(04JS15)

摘　　要：以甘肃省西峰市南小河沟小流域径流场为研究对象,利用BP神经网络对4种植被类型的径流小区(农田、林地、人工草地和天然荒坡)进行了产流产沙量模拟和预测。其模拟产流量的相对误差分别为0.2%～5.7%,0.1%～2.5%,0.7%～2.9%和0.1%～3%;模拟产沙量的相对误差分别为0.1%～3.2%,0.2%～3.1%,0.6%～4.2%和0.2%～2.7%。预测农地、林地、草地和天然荒坡产沙量最大相对误差分别为—11%,14%,—14.6%,18%,产流量最大相对误差分别为10.9%,27.3%,15%,26.3%。结果表明,BP神经网络预测产流产沙的效果较好,对径流小区运用神经网络进行蓄水拦沙指标分析是可行的。With the method of BP neural network, simulation and prediction of runoff generation and sediment yield in four different runoff plots （farmland, wood land, artificial grassland, and abandoned land） are studied. Relative errors of runoff generation in four different plots are 0.2%-5.7%, 0.1%-2.5%, 0.7%-2.9%, and 0.1%-3%, respectively; relative errors of sediment yield, 0. 1%-3.2%, 0.2%-3.1%, 0.6%-4.2%, and 0.2%-2.7%; maximum relative errors of runoff generation, -11%, 14%, -14.6%, and 18% ; the maximum relative errors of sediment yield, 10. 9%, 27.3%, 15.0%, and 26.3%. The results show that the effect of simulation and prediction of runoff generation and sediment yield using the method of BP neural network is good and that application of this method to the analyses of impound and intercepting sediment from runoff plot is feasible.

关 键 词：BP神经网络 产流产沙 植被变化 

分 类 号：P333.4[天文地球—水文科学]