摘要
精准的水位预测在自然灾害预警、水资源管理和生态环境保护等领域具有重要应用价值。为此,提出了一种基于鲁棒局部均值分解(RLMD)、样本熵(SampEn)、卷积神经网络(CNN)和正则化极限学习机(RELM)的水位预测混合模型。首先利用RLMD对历史水位数据进行分解,引入样本熵方法对分量数据进行特征重组以减少数据量;然后利用CNN对重组数据进行特征提取以提高训练速度;最后利用RELM预测每个子序列,将预测结果叠加得到水位序列的最终预测值。以岷江流域下游高场水文站点1997~2020年的日水位数据为研究对象,对模型预测性能进行验证。结果表明:在未来1 d水位预测方面,所构建的混合模型与RELM、CNN-RELM、RLMD-CNN-RELM模型相比,准确度分别提升5.93%,5.91%,0.52%;3种不同预见期(1,2,3 d)下,混合模型预测结果的NSE分别为0.934657,0.932588,0.922955,预报精度均达到甲级。建立的RLMD-SE-CNN-RELM模型预测精度高,稳定性强,可为水位预测和水资源的精准调度提供参考。
Accurate water level prediction has important application value in fields of natural disaster early warning,water resource 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 introduced 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 performance 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 0.934657,0.932588,and 0.922955,respectively,and the prediction accuracies all reach Class-A level.The established RLMD-SE-CNN-RELM model demonstrates high prediction accuracy and strong stability,providing a reference for water level prediction and precise water resource scheduling.
作者
张奇伟
刘月馨
许雯
徐军杨
陈佳雷
张楚
ZHANG Qiwei;LIU Yuexin;XU Wen;XU Junyang;CHEN Jialei;ZHANG Chu(PowerChina Huadong Engineering Corporation Limited,Hangzhou 311100,China;Hangzhou Huachen Power Control Engineering Corporation Limited,Hangzhou 310018,China;Faculty of Automation,Huaiyin Institute of Technology,Huaian 223003,China)
出处
《人民长江》
北大核心
2025年第3期116-125,133,共11页
Yangtze River
基金
国家自然科学基金项目(62303191,62306123)
江苏省自然科学基金项目(BK20191052)
江苏省高等学校自然科学研究项目(23KJD480001)。
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
water level prediction
robust local mean decomposition
sample entropy
convolutional neural network
regularized extreme learning machine
Minjiang River Basin
