摘要
感潮河段潮位时空变化复杂,难以进行精准模拟。为提高模拟精度,提出了一种考虑多影响因素的感潮河段潮位模拟方法:通过导数动态时间规整方法(DDTW)挖掘上下游潮位的平均传播时间;利用集和经验模态分解(EEMD)对潮位多影响因素数据进行特征分解,提取高频和低频分量信息;融合深度残差收缩网络(DRSN)、双向长短时记忆网络(BILSTM)和注意力机制(Attention)构建了一种智能模型(DRSN-BILSTM-Attention),挖掘分量信息的时空特征。该模型在长江天生港潮位站的应用结果表明:所提方法能够有效提高潮位模拟精度,3 h逐时潮位模拟平均准确率为92.1%,与单一机器学习方法相比,该方法展现出更强的数据时空特征提取能力。研究成果可为长江沿岸地区防洪减灾和活水调度提供依据。
The tidal levels in tidal river reaches exhibit complex spatiotemporal variations,making accurate simulation challenging.In order to improve the simulation accuracy,a tide level simulation method for tidal reach considering multiple influencing factors is proposed.This method uses the derivative dynamic time warping(DDTW)technique to determine the average propagation time of tidal levels between upstream and downstream locations.The ensemble empirical mode decomposition(EEMD)is utilized to decompose the various influencing factors data of tidal levels,extracting high-frequency and low-frequency component information.By combining deep residual shrinkage networks(DRSN),bidirectional long short-term memory networks(BILSTM),and attention mechanisms,an intelligent model(DRSN-BILSTM-Attention)is developed,which effectively captures the spatiotemporal features of the decomposed components.The Tianshenggang tidal level station on the Yangtze River was used as the research focus.Results show that the proposed method significantly improves the precision of tidal level simulation,achieving an average accuracy rate of 92.1%for three-hourly simulations.Compared to single machine learning approaches,the proposed method demonstrates superior capabilities in extracting spatiotemporal data features.This method offers a basis for flood prevention,disaster mitigation,and water regulation in coastal areas.
作者
祝国铸
左翔
丛小飞
刘修恒
徐亚波
ZHU Guozhu;ZUO Xiang;CONG Xiaofei;LIU Xiuheng;XU Yabo(Nanjing Zhongyu Intelligent Water Conservancy Research Institute Co.,Ltd.,Nanjing 210012,China;College of Computer and Information,Hohai University,Nanjing 211100,China;China Mobile Systems Integration Co.,Ltd.,Shijiazhuang 050021,China)
出处
《人民长江》
北大核心
2025年第8期107-115,共9页
Yangtze River
基金
国家重点研发计划项目(2023YFC3006500)
水利部重大科技项目(SKS-2022162)
江苏省水利科技项目(2023048,2023047,2023044,2023005,2024040)。
关键词
长江感潮河段
潮位模拟
多影响因素
智能模型
天生港潮位站
tidal river reach of Yangtze River
tidal level simulation
multiple influencing factors
intelligent model
Tianshenggang tidal level station
作者简介
祝国铸,男,高级工程师,硕士,研究方向为机器学习模型。E-mail:zhuguozhu@hohpower.com;通信作者:左翔,男,高级工程师,博士,研究方向为数字孪生水利。E-mail:knightzuo@163.com。
