ISSN 1000-1239 CN 11-1777/TP

Journal of Computer Research and Development ›› 2020, Vol. 57 ›› Issue (8): 1715-1728.doi: 10.7544/issn1000-1239.2020.20200169

Special Issue: 2020数据挖掘与知识发现专题

Previous Articles     Next Articles

A Sequence-to-Sequence Spatial-Temporal Attention Learning Model for Urban Traffic Flow Prediction

Du Shengdong1, Li Tianrui1, Yang Yan1, Wang Hao1, Xie Peng1, Horng Shi-Jinn2   

  1. 1(School of Information Science and Technology, Southwest Jiaotong University, Chengdu 610031);2(Department of Computer Science and Information Engineering, Taiwan University of Science and Technology, Taipei 10607)
  • Online:2020-08-01
  • Supported by: 
    This work was supported by the National Key Research and Development Program of China (2019YFB2101801) and the National Natural Science Foundation of China (61773324, 61976247).

Abstract: Urban traffic flow prediction is a key technology to study the behavior of traffic-related big data and predict future traffic flow, which is crucial to guide the early warning of traffic congestion in the intelligent transportation system. But effective traffic flow prediction is very challenging as it is affected by many complex factors, e.g. spatial-temporal dependency and temporal dynamics of traffic networks. In the literature, some research works applied convolutional neural networks (CNN) or recurrent neural networks (RNN) for traffic flow prediction. However, it is difficult for these models to capture the spatial-temporal correlation features of traffic flow related temporal data. In this paper, we propose a novel sequence-to-sequence spatial-temporal attention framework to deal with the urban traffic flow forecasting task. It is an end-to-end deep learning model which is based on convolutional LSTM layers and LSTM layers with attention mechanism to adaptively learn spatial-temporal dependency and non-linear correlation features of urban traffic flow related multivariate sequence data. Extensive experimental results based on three real-world traffic flow datasets show that our model has the best forecasting performance compared with state-of-the-art methods.

Key words: traffic flow prediction, long short-term memory networks, sequence-to-sequence learning, spatial-temporal attention, encoder-decoder

CLC Number: