奇异谱分析在中长期径流预测中的应用研究  

Application of singular spectrum analysis method in mid-long term runoff prediction

作　　者：汪芸[1] 郭生练[1] 李响[1] 

机构地区：[1]武汉大学水资源与水电工程科学国家重点实验室,湖北武汉430072

出　　处：《人民长江》2011年第9期4-7,22,共5页Yangtze River

基　　金：国家"十一五"科技支撑计划(2009BAC56B01);国家自然科学基金(51079100)

摘　　要：针对目前中长期径流预测精度较低的问题,运用奇异谱分析法对隔河岩水库1951～2009年入库径流资料进行预处理得到重构序列,以达到浓缩主要信息和减小误差的目的。分别采用自回归模型和混沌支持向量机模型对原始序列和处理后的重构序列进行模拟预测。结果表明,应用奇异谱分析法进行资料的预处理可以大大提高中长期径流的预测精度。According to the problem that the current mid-long term runoff prediction accuracy is relatively low,we use the singular spectrum analysis method to preprocess inflow runoff data of Geheyan Reservoir from 1951 to 2009 and obtain reconstructed sequence so as to concentrate the main information and reduce errors.The autoregressive model and chaotic support vector machines were applied to stimulate and predict the original and reconstructed data series.The results show that the singular spectrum analysis method for data preprocessing can significantly improve the accuracy of mid-long term runoff prediction.

关 键 词：中长期径流预测 奇异谱分析 混沌支持向量机 自回归模型 隔河岩水库 

分 类 号：TV121[水利工程—水文学及水资源]