Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
September 10, 2025Transportation Research Record Journal of the Transportation Research Board

Spatiotemporal Adaptive Hybrid Graph Convolutional Networks for Traffic Flow Forecasting

View Full Paper
Ask AI
Bookmark
Share

Authors

PZPeng ZhangZLZheheng LiuYTYu Tang

Discussion

Loading...

Member takes

Overview

New spatiotemporal adaptive hybrid graph convolutional network predicts traffic flow, indicating enhanced accuracy.

Key Points

  • The STAHGCN improves traffic flow prediction, outperforming existing models by addressing complex spatial and temporal relationships.
  • In experiments on PEMS-BAY, STAHGCN reduces mean absolute error and root mean squared error by 15.49% and 9.88%, showcasing its effectiveness.
  • The model integrates an adaptive hybrid graph convolutional module and a gated temporal convolutional network to enhance prediction accuracy.
  • Dynamic graph learning and static adaptive graph learning work together to capture dynamic spatial features of historical traffic flow.

Cite This Study

Zhang et al. (2025) studied this question.

synapsesocial.com/papers/68c1b36054b1d3bfb60ea56bhttps://doi.org/10.1177/03611981251344899
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1A Spatial-Temporal Gated Hypergraph Convolution Network for Traffic Prediction2024 · 24 citations
  2. 2Research on traffic flow prediction of dynamic graph convolution network based on spatio-temporal attention mechanism2026
  3. 3Traffic flow prediction based on graph wave adaptive spatiotemporal graph convolution network2024
  4. 4Adaptive Diffused Spatiotemporal Graph Convolution for Traffic Flow Forecasting2026
  5. 5A Freeway Traffic Flow Prediction Model Based on a Generalized Dynamic Spatio-Temporal Graph Convolutional Network2024 · 22 citations