High-Order Graph Convolutional Recurrent Neural Network: A Deep Learning Framework for Network-Scale Traffic Learning and Forecasting

Traffic forecasting is a challenging task, due to the complicated spatial dependencies on roadway networks and the time-varying traffic patterns. To address this challenge, the authors learn the traffic network as a graph and propose a novel deep learning framework, High-Order Graph Convolutional Long Short-Term Memory Neural Network (HGC-LSTM), to learn the interactions between links in the traffic network and forecast the network-wide traffic state. The authors define the high-order traffic graph convolution based on the physical network topology. The proposed framework employs L1-norms on the graph convolution weights and L2-norms on the graph convolution features to identify the most influential links in the traffic network. The authors propose a novel Real-Time Branching Learning (RTBL) algorithm for the HGC-LSTM framework to accelerate the training process for spatio-temporal data. Experiments show that the authors HGC-LSTM network is able to capture the complex spatio-temporal dependencies efficiently present in a vehicle traffic network and consistently outperforms state-of-the-art baseline methods on two heterogeneous real-world traffic datasets. The visualization of graph convolution weights shows that the proposed framework can accurately recognize the most influential roadway segments in real-world traffic networks.

• Supplemental Notes:
  • This paper was sponsored by TRB committee ABJ70 Standing Committee on Artificial Intelligence and Advanced Computing Applications.
• Corporate Authors:

  Transportation Research Board

  ,    
• Authors:
  • Cui, Zhiyong
  • 0000-0002-5780-4312
  • Henrickson, Kristian
  • Ke, Ruimin
  • Dong, Xiao
  • Wang, Yinhai
• Conference:
  • Transportation Research Board 98th Annual Meeting
  • Location: Washington DC, United States
  • Date: 2019-1-13 to 2019-1-17
• Date: 2019

Language

• English

Media Info

• Media Type: Digital/other
• Features: Figures; References; Tables;
• Pagination: 6p

Subject/Index Terms

• TRT Terms: Intelligent transportation systems; Machine learning; Neural networks; Traffic forecasting; Traffic speed
• Subject Areas: Data and Information Technology; Highways; Operations and Traffic Management;

Filing Info

• Accession Number: 01698033
• Record Type: Publication
• Report/Paper Numbers: 19-05236
• Files: TRIS, TRB, ATRI
• Created Date: Mar 1 2019 3:51PM