• 综合
  • 标题
  • 关键词
  • 摘要
  • 学者
  • 期刊-刊名
  • 期刊-ISSN
  • 会议名称
搜索

作者:

Lin, Yongze (Lin, Yongze.) | Qiao, Junfei (Qiao, Junfei.) | Bi, Jing (Bi, Jing.) | Yuan, Haitao (Yuan, Haitao.) | Gao, Han (Gao, Han.) | Zhou, MengChu (Zhou, MengChu.)

收录:

EI Scopus

摘要:

Spatio-temporal prediction has a wide range of applications in many fields, e.g., air pollution, weather forecasting, and traffic forecasting. Water quality prediction is also one of spatio-temporal prediction tasks. However, it faces the following challenges: 1) Water quality in river networks has complex spatial dependencies; 2) There are complex nonlinear relations in water quality time series; and 3) It is difficult to realize long-term forecasting. To address these challenges, this work proposes a spatio-temporal prediction model called a Graph Attention-based Spatio-Temporal (GAST) neural network. GAST investigates spatial and temporal dependencies of water quality time series. First, we introduce a temporal attention mechanism to capture time series dependencies, which can effectively handle nonlinear relationships in time series. Second, we adopt a spatial attention mechanism to extract spatial dependencies of river networks and fuse temporal features of spatial nodes. Third, we adopt a temporal convolution residual mechanism based on the spatio-temporal fusion, which improves the accuracy of long-term series prediction. This work adopts two real-world datasets to evaluate the proposed GAST and experiments demonstrate that GAST outperforms several state-of-the-art methods in terms of prediction accuracy. © 2022 IEEE.

关键词:

Water quality Complex networks Weather forecasting Convolution Deep learning Rivers Time series River pollution

作者机构:

  • [ 1 ] [Lin, Yongze]Beijing University of Technology, Faculty of Information Technology, Beijing; 100124, China
  • [ 2 ] [Qiao, Junfei]Beijing University of Technology, Faculty of Information Technology, Beijing; 100124, China
  • [ 3 ] [Bi, Jing]Beijing University of Technology, Faculty of Information Technology, Beijing; 100124, China
  • [ 4 ] [Yuan, Haitao]Beihang University, School of Automation Science and Electrical Engineering, Beijing; 100191, China
  • [ 5 ] [Gao, Han]Chinese Academy of Environmental Planning, Beijing; 100012, China
  • [ 6 ] [Zhou, MengChu]New Jersey Institute of Technology, Dept. of Electrical and Computer Engineering, Newark; NJ; 07102, United States

通讯作者信息:

电子邮件地址:

查看成果更多字段

相关关键词:

相关文章:

来源 :

ISSN: 1062-922X

年份: 2022

卷: 2022-October

页码: 1419-1424

语种: 英文

被引次数:

WoS核心集被引频次:

SCOPUS被引频次: 9

ESI高被引论文在榜: 0 展开所有

万方被引频次:

中文被引频次:

近30日浏览量: 0

归属院系:

在线人数/总访问数:485/4912307
地址:北京工业大学图书馆(北京市朝阳区平乐园100号 邮编:100124) 联系我们:010-67392185
版权所有:北京工业大学图书馆 站点建设与维护:北京爱琴海乐之技术有限公司