A Spatiotemporal Multiscale Graph Convolutional Network for Traffic Flow Prediction

Traffic prediction is vital to traffic planning, control, and optimization, which is necessary for intelligent traffic management. Existing methods mostly capture spatiotemporal correlations on a fine-grained traffic graph, which cannot make full use of cluster information in coarse-grained traffic graph. However, the flow variation of clusters in the coarse-grained traffic graph is more stable compared with nodes in the fine-grained traffic graph. And the flow variation of a fine-grained node is generally consistent with the trend of the cluster to which the node belongs. Thus information in the coarse-grained traffic graph can guide feature learning in the fine-grained traffic graph. To this end, the authors propose a Spatiotemporal Multiscale Graph Convolutional Network (SMGCN) that explores spatiotemporal correlations on a multiscale graph. Specifically, given a fine-grained traffic graph, the authors first generate a coarse-grained traffic graph by graph clustering, and extract spatiotemporal correlations on both fine-grained and coarse-grained traffic graphs. Then the authors propose a cross-scale fusion (CF) to implement information diffusion between the fine-grained and coarse-grained traffic graphs. Moreover, the authors employ an adaptive dynamic graph convolution network to mine both static and dynamic spatial features. The authors evaluate SMGCN on real-world datasets and obtain a $1.18\% -3.32\%$ improvement over state-of-the-arts.

• Record URL:
  • http://dx.doi.org/10.1109/TITS.2024.3354802
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/oclc/41297384
• Supplemental Notes:
  • Copyright © 2024, IEEE.
• Authors:
  • Cao, Shuqin
  • 0000-0001-7058-7650
  • Wu, Libing
  • 0000-0001-9897-1953
  • Zhang, Rui
  • 0000-0002-4301-3878
  • Wu, Dan
  • 0000-0002-5748-3328
  • Cui, Jianqun
  • 0000-0003-1447-8761
  • Chang, Yanan
  • 0000-0001-7101-5750
• Publication Date: 2024-8

Language

• English

Media Info

• Media Type: Web
• Features: References;
• Pagination: pp 8705-8718
• Serial:
  • IEEE Transactions on Intelligent Transportation Systems
  • Volume: 25
  • Issue Number: 8
  • Publisher: Institute of Electrical and Electronics Engineers (IEEE)
  • ISSN: 1524-9050
  • Serial URL: http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=6979

Subject/Index Terms

• TRT Terms: Graph theory; Neural networks; Predictive models; Traffic flow
• Subject Areas: Data and Information Technology; Highways; Operations and Traffic Management;

Filing Info

• Accession Number: 01935982
• Record Type: Publication
• Files: TRIS
• Created Date: Nov 6 2024 9:20AM