DSTGCN: Dynamic Spatial-Temporal Graph Convolutional Network for Traffic Prediction

• Published in: IEEE sensors journal Vol. 22; no. 13; pp. 13116 - 13124
• Main Authors: Hu, Jia, Lin, Xianghong, Wang, Chu
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.07.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial neural networks; Correlation; dynamic graph; Heterogeneity; Modules; Nodes; Predictive models; Roads; Sensor phenomena and characterization; Sensors; spatial heterogeneity; spatial-temporal correlation; Task analysis; Traffic information; Traffic prediction; Vehicle dynamics
• ISSN: 1530-437X; 1558-1748
• DOI: 10.1109/JSEN.2022.3176016

Traffic prediction is an important part of building a smart city. Reasonable traffic prediction can help the relevant departments to make important decisions and help people to plan their travel routes. However, due to its complex spatial-temporal correlation has been a challenging task, and even though current research has progressed to some extent, it still generally focuses on modelling relationships between node pairs and between node history information, neglecting the analysis of node properties, leading to performance bottlenecks. To overcome these problems, we propose a dynamic spatial-temporal graph convolutional network (DSTGCN). Specifically, we design a dynamic graph generation module that collects information on geographical proximity and spatial heterogeneity between node pairs in advance and adaptively fuses the two types of information at each time step to generate a new dynamic graph. The dynamic graph module gives DSTGCN the ability to capture dynamic traffic information. In addition, we construct a graph convolution cycle module that captures local temporal dependencies on the basis of merging spatial relationships. It complements the dynamic graph module to jointly capture the spatial-temporal dependence of the traffic data. We validate the effectiveness of our model on two types of traffic prediction tasks, with DSTGCN outperforming the majority of baseline models.