Accurately forecasting the real-time travel demand for dockless scooter-sharing is crucial for the planning and operations of transportation systems. Deep learning models provide researchers with powerful tools to achieve this task, but research in this area is still lacking. This paper thus proposes a novel deep learning architecture named Spatio-Temporal Multi-Graph Transformer (STMGT) to forecast the real-time spatiotemporal dockless scooter-sharing demand. The proposed model uses a graph convolutional network (GCN) based on adjacency graph, functional similarity graph, demographic similarity graph, and transportation supply similarity graph to attach spatial dependency to temporal input (i.e., historical demand). The output of GCN is subsequently processed with weather condition information by the Transformer to capture temporal dependency. Then, a convolutional layer is used to generate the final prediction. The proposed model is evaluated for two real-world case studies in Washington, D.C. and Austin, TX, respectively, and the results show that for both case studies, STMGT significantly outperforms all the selected benchmark models, and the most important model component is the weather information. The proposed model can help micromobility operators develop optimal vehicle rebalancing schemes and guide cities to better manage dockless scooter-sharing operations.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Real-Time Forecasting of Dockless Scooter-Sharing Demand: A Spatio-Temporal Multi-Graph Transformer Approach


    Contributors:
    Xu, Yiming (author) / Zhao, Xilei (author) / Zhang, Xiaojian (author) / Paliwal, Mudit (author)


    Publication date :

    2023-08-01


    Size :

    1698316 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Dynamic repositioning problem of dockless electric scooter sharing systems

    Chu, James C. / Lin, Hsin-Chia / Liao, Fan-Yu et al. | Taylor & Francis Verlag | 2023


    Spatial associations of dockless shared e-scooter usage

    Caspi, Or / Smart, Michael J. / Noland, Robert B. | Elsevier | 2020


    A data-driven approach to estimating dockless electric scooter service areas

    Karimpour, Abolfazl / Hosseinzadeh, Aryan / Kluger, Robert | Elsevier | 2023


    The analysis of spatio-temporal characteristics and determinants of dockless bike-sharing and metro integration

    Ma, Junze / Zheng, Changjiang / Yu, Miao et al. | Taylor & Francis Verlag | 2024