基于最小二乘支持向量机的开都河径流预测  

Forecasting of Kaidu River Runoff Based on LS-SVM Model

作　　者：王暄[1] 屈卫军[1] 

机构地区：[1]新疆巴州水利水电勘测设计院,新疆库尔勒841000

出　　处：《地下水》2012年第5期90-91,共2页Ground water

摘　　要：简述支持向量的回归分析,支持向量机自回归预测模型结构及预测方法,利用开都河大山口水文站52 a的径流资料,采用最小二乘支持向量机方法对径流进行模拟预测,并与BP神经网络方法进行对比分析,其计算结果相对略好。The paper introduced the support vector regression analysis,expounded on support vector machine auto-regression model structure and prediction methods.The runoff data of 52 years were taken for runoff prediction by using least square and Support Vector Machine method(LS-SVM).A contrast analysis was made with the BP neural network method,which showed that the computed result was relatively better than the BP neural network method.

关 键 词：支持向量机 径流预测 BP神经网络 开都河 

分 类 号：P338+.9[天文地球—水文科学]