人民长江2025，Vol.56Issue(3)：116-125,133,11.DOI:10.16232/j.cnki.1001-4179.2025.03.015
基于RLMD-SE-CNN-RELM的水位预测混合模型研究
Research on hybrid water level prediction model based on RLMD-SE-CNN-RELM
摘要
Abstract
Accurate water level prediction has important application value in fields of natural disaster early warning,water re-source management and ecological environmental protection.Therefore,a hybrid water level prediction model based on robust local mean decomposition(RLMD),sample entropy(SampEn),convolutional neural network(CNN)and regularized extreme learning machine(RELM)is proposed.Firstly,RLMD is used to decompose the historical water level data,and the SampEn method is in-troduced to reorganize features of the component data in order to reduce data volume.Then,CNN is used to extract features of the reorganized data to improve the training speed.Finally,RELM is used to predict each sub-sequence,and the prediction results are superimposed to get the final prediction value of the water level sequence.Taking the daily water level data of Gaochang hydrological station in the lower reaches of Minjiang River Basin from 1997 to 2020 as the research object,the predictive perform-ance of the model is verified.The results show that,in terms of predicting the water level 1-day ahead,the proposed hybrid model achieves accuracy improvement of 5.93%,5.91%,and 0.52%compared to the RELM,CNN-RELM,and RLMD-CNN-RELM models,respectively.For three different forecast period(1,2,and 3 days),the NSE values of the hybrid model's prediction results are 0.934 657,0.932 588,and 0.922 955,respectively,and the prediction accuracies all reach Class-A level.The estab-lished RLMD-SE-CNN-RELM model demonstrates high prediction accuracy and strong stability,providing a reference for wa-ter level prediction and precise water resource scheduling.关键词
水位预测/鲁棒局部均值分解/样本熵/卷积神经网络/正则化极限学习机/岷江流域Key words
water level prediction/robust local mean decomposition/sample entropy/convolutional neural network/regular-ized extreme learning machine/Minjiang River Basin分类
建筑与水利引用本文复制引用
张奇伟,刘月馨,许雯,徐军杨,陈佳雷,张楚..基于RLMD-SE-CNN-RELM的水位预测混合模型研究[J].人民长江,2025,56(3):116-125,133,11.基金项目
国家自然科学基金项目(62303191,62306123) （62303191,62306123）
江苏省自然科学基金项目(BK20191052) （BK20191052）
江苏省高等学校自然科学研究项目(23KJD480001) （23KJD480001）
