Spatial‐temporal correlation graph convolutional networks for traffic forecasting

• Published in: IET intelligent transport systems Vol. 17; no. 7; pp. 1380 - 1394
• Main Authors: Huang, Ru, Chen, Zijian, Zhai, Guangtao, He, Jianhua, Chu, Xiaoli
• Format: Journal Article
• Language: English
• Published: Wiley 01.07.2023
• Subjects: management and control; network topology; neural net architecture; traffic modeling
• ISSN: 1751-956X; 1751-9578
• DOI: 10.1049/itr2.12330

Traffic forecasting, as a fundamental and challenging problem of intelligent transportation systems (ITS), has always been the focus of researchers. Nevertheless, accurate traffic forecasting still exists some problems due to the complex spatial‐temporal dependencies and irregularities of traffic flows. Most of the existing methods typically use the spatial adjacency matrix and complicated mechanism to model spatial‐temporal relationships separately, while ignoring the latent spatial‐temporal correlations. In this paper, a novel architecture is proposed named spatial‐temporal correlation graph convolutional networks (STCGCN) for traffic prediction. First, an informative fused graph structure is constructed to better learn the complex spatial‐temporal correlations, which breaks the limitation that the general spatial adjacency matrix cannot reflect temporal correlations. Moreover, spatial‐temporal correlation graph convolution and gated temporal convolution are performed in parallel and they are integrated into a unified layer, which enables capturing both local and global spatial‐temporal dependencies simultaneously. By stacking multiple layers, STCGCN can learn more long‐range spatial‐temporal dependencies. Experimental results on five public traffic datasets demonstrate the effectiveness and robustness of the proposed STCGCN in urban traffic forecasting. In this paper, we propose a novel architecture named spatial‐temporal correlation graph convolutional networks (STCGCN) for traffic prediction. First, we construct an informative fused graph structure to better learn the complex spatial‐temporal correlations, which breaks the limitation that the general spatial adjacency matrix cannot reflect temporal correlations. Moreover, we perform spatial‐temporal correlation graph convolution and gated temporal convolution in parallel and integrate them into a unified layer, which enables capturing both local and global spatial‐temporal dependencies simultaneously. By stacking multiple layers, STCGCN can learn more long‐range spatial‐temporal dependencies. Experimental results on five public traffic datasets demonstrate the effectiveness and robustness of the proposed STCGCN in urban traffic forecasting.