IDEAS home Printed from https://ideas.repec.org/a/gam/jsusta/v15y2023i10p7903-d1144885.html
   My bibliography  Save this article

Convolutional Long Short-Term Memory Two-Dimensional Bidirectional Graph Convolutional Network for Taxi Demand Prediction

Author

Listed:
  • Yibo Cao

    (Shenzhen International Graduate School, Tsinghua University, Shenzhen 518000, China
    Shenzhen Urban Transport Planning Center, Shenzhen 518057, China)

  • Lu Liu

    (Shenzhen International Graduate School, Tsinghua University, Shenzhen 518000, China
    Shenzhen Urban Transport Planning Center, Shenzhen 518057, China)

  • Yuhan Dong

    (Shenzhen International Graduate School, Tsinghua University, Shenzhen 518000, China)

Abstract

With the rise of the online ride-hailing market, taxi demand prediction has received more and more research interest in intelligent transportation. However, most traditional research methods mainly focused on the demand based on the original point and ignored the intention of the passenger’s destination. At the same time, many forecasting methods need sufficient investigation and data processing, which undoubtedly increases the complexity and operability of forecasting problems. Therefore, we regard the current taxi demand prediction as an origin–destination problem in order to provide more accurate predictions for the taxi demand problem. By combining a spatial network based on graph convolutional network (GCN) and a temporal network of convolutional long short-term memory (Conv-LSTM), we propose a new spatial-temporal model of Conv-LSTM two-dimensional bidirectional GCN (CTBGCN) to uncover the potential correlation between origin and destination. We utilize the temporal network for effective temporal information and the spatial network of multi-layers to get the implicit origin–destination correlation. Numerical results suggest that the proposed method outperforms the state-of-the-art baseline and other traditional methods.

Suggested Citation

  • Yibo Cao & Lu Liu & Yuhan Dong, 2023. "Convolutional Long Short-Term Memory Two-Dimensional Bidirectional Graph Convolutional Network for Taxi Demand Prediction," Sustainability, MDPI, vol. 15(10), pages 1-14, May.
  • Handle: RePEc:gam:jsusta:v:15:y:2023:i:10:p:7903-:d:1144885
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/2071-1050/15/10/7903/pdf
    Download Restriction: no

    File URL: https://www.mdpi.com/2071-1050/15/10/7903/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Blume, Steffen O.P. & Corman, Francesco & Sansavini, Giovanni, 2022. "Bayesian origin-destination estimation in networked transit systems using nodal in- and outflow counts," Transportation Research Part B: Methodological, Elsevier, vol. 161(C), pages 60-94.
    2. John Y. Campbell & Samuel B. Thompson, 2008. "Predicting Excess Stock Returns Out of Sample: Can Anything Beat the Historical Average?," The Review of Financial Studies, Society for Financial Studies, vol. 21(4), pages 1509-1531, July.
    3. Maher, M. J., 1983. "Inferences on trip matrices from observations on link volumes: A Bayesian statistical approach," Transportation Research Part B: Methodological, Elsevier, vol. 17(6), pages 435-447, December.
    4. Cascetta, Ennio, 1984. "Estimation of trip matrices from traffic counts and survey data: A generalized least squares estimator," Transportation Research Part B: Methodological, Elsevier, vol. 18(4-5), pages 289-299.
    5. Spiess, Heinz, 1987. "A maximum likelihood model for estimating origin-destination matrices," Transportation Research Part B: Methodological, Elsevier, vol. 21(5), pages 395-412, October.
    6. Yang, Hai & Wong, S. C. & Wong, K. I., 2002. "Demand-supply equilibrium of taxi services in a network under competition and regulation," Transportation Research Part B: Methodological, Elsevier, vol. 36(9), pages 799-819, November.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Menon, Aditya Krishna & Cai, Chen & Wang, Weihong & Wen, Tao & Chen, Fang, 2015. "Fine-grained OD estimation with automated zoning and sparsity regularisation," Transportation Research Part B: Methodological, Elsevier, vol. 80(C), pages 150-172.
    2. Bielli, Maurizio & Reverberi, Pierfrancesco, 1996. "New operations research and artificial intelligence approaches to traffic engineering problems," European Journal of Operational Research, Elsevier, vol. 92(3), pages 550-572, August.
    3. Shao, Hu & Lam, William H.K. & Sumalee, Agachai & Chen, Anthony & Hazelton, Martin L., 2014. "Estimation of mean and covariance of peak hour origin–destination demands from day-to-day traffic counts," Transportation Research Part B: Methodological, Elsevier, vol. 68(C), pages 52-75.
    4. Bierlaire, M. & Toint, Ph. L., 1995. "Meuse: An origin-destination matrix estimator that exploits structure," Transportation Research Part B: Methodological, Elsevier, vol. 29(1), pages 47-60, February.
    5. Hai Yang & Qiang Meng & Michael G. H. Bell, 2001. "Simultaneous Estimation of the Origin-Destination Matrices and Travel-Cost Coefficient for Congested Networks in a Stochastic User Equilibrium," Transportation Science, INFORMS, vol. 35(2), pages 107-123, May.
    6. Abdullah Alshehri & Mahmoud Owais & Jayadev Gyani & Mishal H. Aljarbou & Saleh Alsulamy, 2023. "Residual Neural Networks for Origin–Destination Trip Matrix Estimation from Traffic Sensor Information," Sustainability, MDPI, vol. 15(13), pages 1-21, June.
    7. Doblas, Javier & Benitez, Francisco G., 2005. "An approach to estimating and updating origin-destination matrices based upon traffic counts preserving the prior structure of a survey matrix," Transportation Research Part B: Methodological, Elsevier, vol. 39(7), pages 565-591, August.
    8. Juha-Matti Kuusinen & Janne Sorsa & Marja-Liisa Siikonen, 2015. "The Elevator Trip Origin-Destination Matrix Estimation Problem," Transportation Science, INFORMS, vol. 49(3), pages 559-576, August.
    9. Seungkyu Ryu, 2020. "A Bicycle Origin–Destination Matrix Estimation Based on a Two-Stage Procedure," Sustainability, MDPI, vol. 12(7), pages 1-14, April.
    10. Z. Wu & W. Lam, 2006. "Transit passenger origin-destination estimation in congested transit networks with elastic line frequencies," Annals of Operations Research, Springer, vol. 144(1), pages 363-378, April.
    11. Fu, Hao & Lam, William H.K. & Shao, Hu & Ma, Wei & Chen, Bi Yu & Ho, H.W., 2022. "Optimization of multi-type sensor locations for simultaneous estimation of origin-destination demands and link travel times with covariance effects," Transportation Research Part B: Methodological, Elsevier, vol. 166(C), pages 19-47.
    12. Hazelton, Martin L., 2003. "Some comments on origin-destination matrix estimation," Transportation Research Part A: Policy and Practice, Elsevier, vol. 37(10), pages 811-822, December.
    13. Xie, Chi & Kockelman, Kara M. & Waller, S. Travis, 2011. "A maximum entropy-least squares estimator for elastic origin–destination trip matrix estimation," Transportation Research Part B: Methodological, Elsevier, vol. 45(9), pages 1465-1482.
    14. Dimitris Bertsimas & Julia Yan, 2018. "From Physical Properties of Transportation Flows to Demand Estimation: An Optimization Approach," Transportation Science, INFORMS, vol. 52(4), pages 1002-1011, August.
    15. S. Travis Waller & Sai Chand & Aleksa Zlojutro & Divya Nair & Chence Niu & Jason Wang & Xiang Zhang & Vinayak V. Dixit, 2021. "Rapidex: A Novel Tool to Estimate Origin–Destination Trips Using Pervasive Traffic Data," Sustainability, MDPI, vol. 13(20), pages 1-27, October.
    16. Guo, Jianhua & Liu, Yu & Li, Xiugang & Huang, Wei & Cao, Jinde & Wei, Yun, 2019. "Enhanced least square based dynamic OD matrix estimation using Radio Frequency Identification data," Mathematics and Computers in Simulation (MATCOM), Elsevier, vol. 155(C), pages 27-40.
    17. Yang, Yudi & Fan, Yueyue & Royset, Johannes O., 2019. "Estimating probability distributions of travel demand on a congested network," Transportation Research Part B: Methodological, Elsevier, vol. 122(C), pages 265-286.
    18. Louis Grange & Felipe González & Shlomo Bekhor, 2017. "Path Flow and Trip Matrix Estimation Using Link Flow Density," Networks and Spatial Economics, Springer, vol. 17(1), pages 173-195, March.
    19. Hazelton, Martin L., 2000. "Estimation of origin-destination matrices from link flows on uncongested networks," Transportation Research Part B: Methodological, Elsevier, vol. 34(7), pages 549-566, September.
    20. Yang, Yudi & Fan, Yueyue, 2015. "Data dependent input control for origin–destination demand estimation using observability analysis," Transportation Research Part B: Methodological, Elsevier, vol. 78(C), pages 385-403.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gam:jsusta:v:15:y:2023:i:10:p:7903-:d:1144885. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.