Abstract Air traffic flow prediction is vital for its supporting function for collaborative decision making in Air Traffic Management. However, due to the inherent spatial and temporal dependencies of air traffic flow and the irregular sector structure in which flow operates in, it is still a challenging problem. To solve this problem, numerous methods are proposed considering airspace adjacency, while flight routes and the origin-destination dependency are not taken into account. In this paper, we propose a temporal attention aware dual-graph convolution network (TAaDGCN) to predict air traffic flow, in which the airspace structure and routes of flow are both included. Firstly, a complementary spatial dual graph convolution module is constructed to capture the dependencies of adjacent sectors and origin-destination (OD) sectors. Then, to include long path information, a spatial embedding (SE) block is adopted to represent potential related sectors of flight traversal. Furthermore, to characterize temporal evolution pattern, a temporal attention (TA) module is applied to access past features of input sequence. Based on the blocks stated above, a spatio-temporal block is constructed in which multiple spatial and temporal dependencies are covered. The experimental results on real-world flight data demonstrate the proposed method can achieve a better prediction performance than other state-of-the-art comparison methods, especially superior to the methods that ignore the sector spatial structure.

    Highlights The dual-graph module is designed to effectively extract complex spatial relationships specifically for the characteristics of air traffic flow. Developing a novel path-based spatial embedding module on adjacency graph to represent potential related sectors of flight traversal. Attention mechanism is adopted to efficiently capture long-term temporal dependencies, which contributes to obtaining multi-step predictions simultaneously, alleviating error propagation to a certain extent. Multiple spatial-temporal dependencies including spatial adjacency, long-distance dependencies and long-term temporal dependencies are taken into account.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Temporal attention aware dual-graph convolution network for air traffic flow prediction


    Contributors:
    Cai, Kaiquan (author) / Shen, Zhiqi (author) / Luo, Xiaoyan (author) / Li, Yue (author)


    Publication date :

    2022-09-07




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English




    Spatio-Temporal Graph Attention Convolution Network for Traffic Flow Forecasting

    Liu, Kun / Zhu, Yifan / Wang, Xiao et al. | Transportation Research Record | 2024



    Dual Dynamic Spatial-Temporal Graph Convolution Network for Traffic Prediction

    Sun, Yanfeng / Jiang, Xiangheng / Hu, Yongli et al. | IEEE | 2022


    Traffic flow prediction method based on graph attention convolution network

    ZHENG HONG / ZHANG SIKAI / LIU JIAMOU et al. | European Patent Office | 2020

    Free access

    Spatial-Temporal Position-Aware Graph Convolution Networks for Traffic Flow Forecasting

    Zhao, Yiji / Lin, Youfang / Wen, Haomin et al. | IEEE | 2023