摘要
为获得更精确的径流-水位预报结果,利用Dmey小波变换将水位时间序列分解为高频信号和低频信号,再使用均生函数-最优子集回归对其进行预测,最后利用Dmey小波逆变进行重构,以此建立水位预测模型。通过对柳江历年水位进行实例分析,并与均生函数-最优子集回归模型、逐步回归模型对比。研究结果表明,该模型能充分反映水位时间序列趋势,预报稳定性好,预报准确率高,为径流-水位时间序列预测提供一个有效建模方法。
In order to obtain more accurate forecasting result of runoff water level,by using the dmey wavelet transform,the water level time sequence is decomposed into high frequency part and low frequency part,then by using the mean generating function and optimal subset regression,both of the two subparts are predicted respectively,finally,by using the inverse dmey wavelet transform,both of the two predicted results are reconstructed to form the future behavior of the water level.The method has been compared with mean generating function integrated with optimal subset regression,and step regression.It is noticed that the presented method is superior to the other models presented in this study in terms of the same evaluation measurements.Therefore the nonlinear ensemble model proposed here can reflect the runoff water level time series trend well,and has good forecasting stability and accuracy,and can be used as an alternative forecasting tool for runoff-water level.
出处
《武汉理工大学学报》
CAS
CSCD
北大核心
2012年第12期143-149,共7页
Journal of Wuhan University of Technology
基金
国家自然科学基金(11161029)
广西自然科学基金(2011GXNSFE018006)
广西教育厅资助项目(201204LX501)
关键词
小波变换
均生函数
最优子集回归
径流-水位预测
wavelet transform
mean generating function
optimal subset regression
runoff-water level forecasting
