周焕,闪丽洁,揭梦璇,汤斌.基于混合回归模型的沿海平原河网洪水位预报研究[J].中国水利水电科学研究院学报,2022,20(2):145-152
基于混合回归模型的沿海平原河网洪水位预报研究
Research on flood level forecasting in coastal plain river network based on mixture regressive model
投稿时间:2021-01-21  修订日期:2021-10-18
DOI:10.13244/j.cnki.jiwhr.20210021
中文关键词:  混合回归模型  沿海平原河网  洪水位预报  温瑞平原  预报因子
英文关键词:mixture regressive model  coastal plain river network  flood level forecasting  Wen-rui plain  forecast factor
基金项目:浙江省水利厅科技项目(RB1904)
作者单位E-mail
周焕 浙江省水利水电勘测设计院, 浙江 杭州 310002 shanlijie0701@163.com 
闪丽洁 浙江省水利水电勘测设计院, 浙江 杭州 310002  
揭梦璇 浙江省水利水电勘测设计院, 浙江 杭州 310002  
汤斌 浙江省水利水电勘测设计院, 浙江 杭州 310002  
摘要点击次数: 1042
全文下载次数: 1825
中文摘要:
      本文针对沿海平原河网水文情势复杂、洪水位预报困难的特点,以温瑞平原为研究对象构建混合回归模型,采取物理成因与数理统计相结合的思路,探究适用于沿海平原地区的洪水位预报新途径。利用产汇流模型计算求得各水文分区洪水过程,形成预报因子库,并在此基础上构建混合回归模型,通过耦合多元逐步回归模型与门限回归模型进行洪水位预报研究。研究结果表明:混合回归模型在温瑞平原洪水位预报中取得了较好的效果,验证洪水确定性系数为0.82,合格率为75.60%,具有较高的预报精度。该模型算法结构简单,对输入资料的要求较低,可操作性和实用性较强,可以为沿海平原地区洪水预报实际工作提供一定的参考。
英文摘要:
      In view of the characteristics of complex hydrological situation and difficulty forecasting in coastal plain river network, a mixture regressive model was built based on the idea of combining physical causes with mathematical statistical analysis in order to explore the suitable flood level forecasting methods for plain river networks in coastal areas. Firstly,a predictive factor database was formed by flood processes which were calculated by using the runoff generation and concentration model for hydrological regionalization. On this basis, the mixture regression model was built by coupling stepwise multiple regression method and threshold regression model to research the flood level forecasting technology. The results show that, the mixture regression model can effectively improve the accuracy of flood level forecasting in coastal plain river networks. The certainty factor and qualified rate of verification flood are 0.82 and 75.60%, respectively. Mixture regressive model is a better forecasting method in terms of operation and practicability with its mature algorithms, clear structure and simple input conditions, which can provide references for the work of the flood forecasting in coastal areas.
查看全文  查看/发表评论  下载PDF阅读器
关闭