ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
期刊论文

Medium-long-term prediction of water level based on an improved spatio-temporal attention mechanism for long short-term memory networks

Wang, Yingfei; Huang, Yingping; Xiao, Min*; Zhou, Shuangshuang; Xiong, Biao*; Jin, Zhuanchina three gorges univ
Journal of Hydrology2023-3DOI: 10.1016/j.jhydrol.2023.129163
7被引12阅读
引用收藏
分享

摘要

River water level usually given by nonlinear and nonstationary time series and affected by numerous complex spatial and temporal factors. But not all input factors are positively correlated with flood forecasting, and un-correlated inputs tend to bring a lot of noise, resulting in lower prediction accuracy. Attention mechanism is an effective solution to feature filter. This study presents a spatio-temporal attention LSTM (STA-LSTM). Meanwhile, attention visualization makes models interpretation providing the basis. In this work, the attention-weight matrix is generated independently by the spatial attention module and the temporal attention module to focus on the more valuable feature factors in time and space, respectively. Spatio-temporal attention is a combination of spatial attention and temporal attention to assign scores to input sequences. Forecasting the water level of Hanchuan in the next 6 h based on the observations in the past 6 h in the middle and lower reaches of the Hanjiang River, China. The experimental results indicate that the mean absolute error (MAE) of STA-LSTM is 0.74835, root mean square error (RMSE) is 0.90197, mean absolute percent error (MAPE) is 3.29924, and co-efficient of determination (R2) is 0.94138. This study improves the accuracy of the water level prediction method, which makes it easier for decision-makers to plan evacuations in advance.

学科与关键词

关键词
Flood forecastingAttention mechanismLong short-term memory networksHanjiang River
相关
加载中…
  • A stream prediction model based on attention-LSTM
    Yan, Le; Chen, Changwei*; Hang, Tingting; Hu, YouchuanEarth Science Informatics, 2021, 14(2): 723-733.被引 29
  • Hybrid Deep Learning Modeling for Water Level Prediction in Yangtze River
    Xie, Zhaoqing*; Liu, Qing; Cao, YulianINTELLIGENT AUTOMATION AND SOFT COMPUTING, 2021, 28(1): 153-166.被引 11
  • Water level prediction using long short-term memory neural network model for a lowland river: a case study on the Tisza River, Central Europe
    Vizi, Zsolt*; Batki, Balint; Ratki, Luca; Szalanczi, Szabolcs; Fehervary, Istvan; Kozak, Peter; Kiss, TimeaEnvironmental Sciences Europe, 2023, 35(1): 92.被引 6
查看全部 →

发表信息

论文状态
公开发表
期刊
Journal of Hydrology
发表日期
2023-03
卷期
第 618 卷
页码
129163
DOI
10.1016/j.jhydrol.2023.129163
语言
MULTI-LANGUAGE
成果收录
SCIE
资助标注
Foundation of Key Laboratory of Yangtze River Water Environment, Ministry of Education (Tongji Uni-versity) [YRWEF202103]; National Natural Science Foundation of China [:22136003]; Hubei province introduces talents projects [2019BJH004]; Hubei province innovation group project [2015CFA021]

作者

  • W

    Wang, Yingfei (第一作者)

    china three gorges univ

  • H

    Huang, Yingping

    china three gorges univ

查看全部 6 位作者收起作者
  • X

    Xiao, Min (通讯)

    china three gorges univ

  • Z

    Zhou, Shuangshuang

    china three gorges univ

  • X

    Xiong, Biao (通讯)

    china three gorges univ

  • J

    Jin, Zhuan

    china three gorges univ

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417