Forecasting Model of Irrigation Water Requirement Based on Least Squares Support Vector Machine

摘要：

The irrigation water requirement forecasting is the basis for making scheduling program of water resource and allocating on water in irrigation area rationally and efficiently. The factors influencing the irrigation water are complex and nonlinear, and support vector machine (SVM) has many advantages on nonlinear small samples, therefore, this paper introduces SVM into forecasting irrigation water requirement and proposes a forecasting model of irrigation water requirement based on least squares support vector machine (LS-SVM). Then the forecasting model is applied to estimate the irrigation water requirement of T irrigation area in Tarim River Basin, and is compared with BP artificial neural network (BPANN). The result indicates that the forecasting model based on LS-SVM has an excellent generalization ability and small error. LS-SVM provides an effective method to forecast irrigation water requirement.

关键词： irrigation water requirement forecasting least squares support vector machine

作者: XIE Fang TANG De-shan

作者单位: Hohai University, Nanjing, Jiangsu, 210098, China

会议类型: 国际会议

会议名称: 2010 International Conference on Intelligent Computation Technology and Automation(2010 智能计算技术与自动化国际会议 ICICTA 2010)

会议地点: 长沙

会议语种:英文

页码: 1505-1508

在线出版日期: 2010-05-11（万方平台首次上网日期，不代表论文的发表时间）