Traffic accident prediction plays a vital role in Intelligent Transportation Systems (ITS), where a large number of traffic streaming data are generated on a daily basis for spatiotemporal big data analysis. The rarity of accidents and the absent interconnection information make it hard for spatiotemporal modeling. Moreover, the inherent characteristic of the black box predictive model makes it difficult to interpret the reliability and effectiveness of the deep learning model. To address these issues, a novel self-explanatory spatial-temporal deep learning model–Attention Spatial-Temporal Multi-Graph Convolutional Network (ASTMGCN) is proposed for traffic accident prediction. The original recorded rare accident data is formulated as a multivariate irregularly interval-aligned dataset, and the temporal discretization method is used to transfer into regularly sampled time series. Multiple graphs are defined to construct edge features and represent spatial relationships when node-related information is missing. Multi-graph convolutional operators and attention mechanisms are integrated into a Sequence-to-Sequence (Seq2Seq) framework to effectively capture dynamic spatial and temporal features and correlations in multi-step prediction. Comparative experiments and interpretability analysis are conducted on a real-world data set, and results indicate that our model can not only yield superior prediction performance but also has the advantage of interpretability.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Interpretable Traffic Accident Prediction: Attention Spatial–Temporal Multi-Graph Traffic Stream Learning Approach


    Contributors:
    Li, Chaojie (author) / Zhang, Borui (author) / Wang, Zeyu (author) / Yang, Yin (author) / Zhou, Xiaojun (author) / Pan, Shirui (author) / Yu, Xinghuo (author)

    Published in:

    Publication date :

    2024-11-01


    Size :

    3513002 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Traffic accident severity prediction based on interpretable deep learning model

    Pei, Yulong / Wen, Yuhang / Pan, Sheng | Taylor & Francis Verlag | 2025


    A Spatial–Temporal Attention Approach for Traffic Prediction

    Shi, Xiaoming / Qi, Heng / Shen, Yanming et al. | IEEE | 2021


    Traffic Flow Prediction Using Novel Spatial-Temporal Multi-Head Attention Graph Convolution Networks

    Cheng, Yuan / Peng, Cheng / Wang, Ze et al. | Transportation Research Record | 2024


    Spatio-temporal graph attention networks for traffic prediction

    Ma, Chuang / Yan, Li / Xu, Guangxia | Taylor & Francis Verlag | 2024


    STATNet: Spatial-temporal attention in the traffic prediction

    Moghadas, Seyed Mohamad / Gheibi, Amin / Alahi, Alexander | TIBKAT | 2022

    Free access