Highlights Propose a novel deep learning model for network-level traffic condition forecasting. Implement dynamic modules to learn state-dependent spatial correlations among roads. Decrypt and relate learnt parameters to traffic flow theory. Highlight the possibility to combine accuracy and interpretability in deep neural networks.

    Abstract Accurate and explainable short-term traffic forecasting is pivotal for making trustworthy decisions in advanced traffic control and guidance systems. Recently, deep learning approach, as a data-driven alternative to traffic flow model-based data assimilation and prediction methods, has become popular in this domain. Many of these deep learning models show promising predictive performance, but inherently suffer from a lack of interpretability. This difficulty largely originates from the inconsistency between the static input–output mappings encoded in deep neural networks and the dynamic nature of traffic phenomena. Under different traffic conditions, such as freely-flowing versus heavily congested traffic, different mappings are needed to predict the propagation of congestion and the resulting speeds over the network more accurately. In this study, we design a novel variant of the graph attention mechanism. The major innovation of this so-called dynamic graph convolution (DGC) module is that local area-wide graph convolutional kernels are dynamically generated from evolving traffic states to capture real-time spatial dependencies. When traffic conditions change, the spatial correlation encoded by DGC module changes as well. Using the DGC, we propose a multistep traffic forecasting model, the Dynamic Graph Convolutional Network (DGCN). Experiments using real freeway data show that the DGCN has a competitive predictive performance compared to other state-of-the-art models. Equally importantly, the prediction process in the DGCN and the trained parameters are indeed explainable. It turns out that the DGCN learns to mimic the upstream–downstream asymmetric information flow of typical road traffic operations. Specifically, there exists a speed-dependent optimal receptive field – which governs what information the DGC kernels assimilate – that is consistent with the back-propagation speed of stop-and-go waves in traffic streams. This implies that the learnt parameters are consistent with traffic flow theory. We believe that this research paves a path to more transparent deep learning models applied for short-term traffic forecasting.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Multistep traffic forecasting by dynamic graph convolution: Interpretations of real-time spatial correlations


    Beteiligte:
    Li, Guopeng (Autor:in) / Knoop, Victor L. (Autor:in) / van Lint, Hans (Autor:in)


    Erscheinungsdatum :

    2021-04-27




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Dynamic Graph Filters Networks: A Gray-box Model for Multistep Traffic Forecasting

    LI, Guopeng / Knoop, Victor L. / Lint, Hans van | IEEE | 2020


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

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


    Graph transformer based dynamic multiple graph convolution networks for traffic flow forecasting

    Yongli Hu / Ting Peng / Kan Guo et al. | DOAJ | 2023

    Freier Zugriff

    Graph transformer based dynamic multiple graph convolution networks for traffic flow forecasting

    Hu, Yongli / Peng, Ting / Guo, Kan et al. | Wiley | 2023

    Freier Zugriff

    Dual Dynamic Spatial-Temporal Graph Convolution Network for Traffic Prediction

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