IDEAS home Printed from https://ideas.repec.org/a/gam/jmathe/v10y2022i19p3664-d934869.html

Short-Term Online Forecasting for Passenger Origin–Destination (OD) Flows of Urban Rail Transit: A Graph–Temporal Fused Deep Learning Method

Author

Listed:
  • Han Zheng

    (School of Traffic and Transportation, Beijing Jiaotong University, No. 3 Shang Yuan Cun, Hai Dian District, Beijing 100044, China)

  • Junhua Chen

    (School of Traffic and Transportation, Beijing Jiaotong University, No. 3 Shang Yuan Cun, Hai Dian District, Beijing 100044, China)

  • Zhaocha Huang

    (School of Traffic and Transportation, Beijing Jiaotong University, No. 3 Shang Yuan Cun, Hai Dian District, Beijing 100044, China)

  • Kuan Yang

    (School of Traffic and Transportation, Beijing Jiaotong University, No. 3 Shang Yuan Cun, Hai Dian District, Beijing 100044, China)

  • Jianhao Zhu

    (School of Traffic and Transportation, Beijing Jiaotong University, No. 3 Shang Yuan Cun, Hai Dian District, Beijing 100044, China)

Abstract

Predicting short-term passenger flow accurately is of great significance for daily management and for a timely emergency response of rail transit networks. In this paper, we propose an attention-based Graph–Temporal Fused Neural Network (GTFNN) that can make online predictions of origin–destination (OD) flows in a large-scale urban transit network. In order to solve the key issue of the passenger hysteresis in online flow forecasting, the proposed GTFNN takes finished OD flow and a series of features, which are known or observable, as the input and performs multi-step prediction. The model is constructed from capturing both spatial and temporal characteristics. For learning spatial characteristics, a multi-layer graph neural network is proposed based on hidden relationships in the rail transit network. Then, we embedded the graph convolution into a Gated Recurrent Unit to learn spatial–temporal features. For learning temporal characteristics, a sequence-to-sequence structure embedded with the attention mechanism is proposed to enhance its ability to capture both local and global dependencies. Experiments based on real-world data collected from Chongqing’s rail transit system show that the metrics of GTFNN are better than other methods, e.g., the SMAPE (Symmetric Mean Absolute Percentage Error) score is about 14.16%, with a range from 5% to 20% higher compared to other methods.

Suggested Citation

  • Han Zheng & Junhua Chen & Zhaocha Huang & Kuan Yang & Jianhao Zhu, 2022. "Short-Term Online Forecasting for Passenger Origin–Destination (OD) Flows of Urban Rail Transit: A Graph–Temporal Fused Deep Learning Method," Mathematics, MDPI, vol. 10(19), pages 1-30, October.
    • Handle: RePEc:gam:jmathe:v:10:y:2022:i:19:p:3664-:d:934869
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/2227-7390/10/19/3664/pdf
    Download Restriction: no
    File URL: https://www.mdpi.com/2227-7390/10/19/3664/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Eleni I. Vlahogianni & John C. Golias & Matthew G. Karlaftis, 2003. "Short‐term traffic forecasting: Overview of objectives and methods," Transport Reviews, Taylor & Francis Journals, vol. 24(5), pages 533-557, November.
    2. Makridakis, Spyros & Spiliotis, Evangelos & Assimakopoulos, Vassilios, 2020. "The M4 Competition: 100,000 time series and 61 forecasting methods," International Journal of Forecasting, Elsevier, vol. 36(1), pages 54-74.
    3. Yujuan Sun & Guanghou Zhang & Huanhuan Yin, 2014. "Passenger Flow Prediction of Subway Transfer Stations Based on Nonparametric Regression Model," Discrete Dynamics in Nature and Society, Hindawi, vol. 2014, pages 1-8, April.
    4. Zhou, Xuesong & Mahmassani, Hani S., 2007. "A structural state space model for real-time traffic origin-destination demand estimation and prediction in a day-to-day learning framework," Transportation Research Part B: Methodological, Elsevier, vol. 41(8), pages 823-840, October.
    5. Lim, Bryan & Arık, Sercan Ö. & Loeff, Nicolas & Pfister, Tomas, 2021. "Temporal Fusion Transformers for interpretable multi-horizon time series forecasting," International Journal of Forecasting, Elsevier, vol. 37(4), pages 1748-1764.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Nithin K. Shanthappa & Raviraj H. Mulangi & Harsha M. Manjunath, 2025. "Deep learning-based public transit passenger flow prediction model: integration of weather and temporal attributes," Public Transport, Springer, vol. 17(2), pages 367-390, June.

    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. Tiantian Tu, 2025. "Bridging Short- and Long-Term Dependencies: A CNN-Transformer Hybrid for Financial Time Series Forecasting," Papers 2504.19309, arXiv.org.
    2. Gerg, Isaac D. & Tashie, Arik M. & Patanaik, Amiya & Koester, Evan & Gupta, Himanshu & Farnham, David J., 2026. "The substantial role of weather data in consumer spending prediction: A robust machine learning assessment," Journal of Retailing and Consumer Services, Elsevier, vol. 90(C).
    3. Frison, Lilli & Gölzhäuser, Simon & Bitterling, Moritz & Kramer, Wolfgang, 2024. "Evaluating different artificial neural network forecasting approaches for optimizing district heating network operation," Energy, Elsevier, vol. 307(C).
    4. Gonca Gürses-Tran & Antonello Monti, 2022. "Advances in Time Series Forecasting Development for Power Systems’ Operation with MLOps," Forecasting, MDPI, vol. 4(2), pages 1-24, May.
    5. Abdelfatah, Omar Sharafeldin Mohamed, 2026. "AI-Driven Demand Forecasting and Its Impact on Inventory Optimization," SocArXiv uw57j_v1, Center for Open Science.
    6. Tuominen, Jalmari & Pulkkinen, Eetu & Peltonen, Jaakko & Kanniainen, Juho & Oksala, Niku & Palomäki, Ari & Roine, Antti, 2024. "Forecasting emergency department occupancy with advanced machine learning models and multivariable input," International Journal of Forecasting, Elsevier, vol. 40(4), pages 1410-1420.
    7. Vogl, Markus & Kojić, Milena & Sharma, Abhishek & Stanisic, Nikola, 2025. "Decoding financial markets: Empirical DGPs as the key to model selection and forecasting excellence – A proof of concept," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 666(C).
    8. Thabang Mathonsi & Terence L. van Zyl, 2021. "A Statistics and Deep Learning Hybrid Method for Multivariate Time Series Forecasting and Mortality Modeling," Forecasting, MDPI, vol. 4(1), pages 1-25, December.
    9. Frederick Nsambu Kijjambu & Benjamin Musiita & Asaph Kaburura Katarangi & Geoffrey Kahangane & Sheilla Akampwera, 2023. "Determinants of Uganda’s Debt Sustainability: The Public Debt Dynamics Model in Perspective," Journal of Economics and Behavioral Studies, AMH International, vol. 15(4), pages 106-124.
    10. Hoang, Nam H. & Vu, Hai L. & Lo, Hong K., 2018. "An informed user equilibrium dynamic traffic assignment problem in a multiple origin-destination stochastic network," Transportation Research Part B: Methodological, Elsevier, vol. 115(C), pages 207-230.
    11. Hoang Anh Nguyen & Nhat Hoang Bach, 2026. "QI-HRNN: a quantum-inspired hybrid framework for resilient currency forecasting under extreme market conditions," Digital Finance, Springer, vol. 8(2), pages 1-40, June.
    12. Jang, Junkyu, 2025. "Selective news selection model for explainable stock prediction via cross-attention integration," Finance Research Letters, Elsevier, vol. 85(PD).
    13. Frank, Johannes, 2023. "Forecasting realized volatility in turbulent times using temporal fusion transformers," FAU Discussion Papers in Economics 03/2023, Friedrich-Alexander University Erlangen-Nuremberg, Institute for Economics.
    14. He, Miao & Jiang, Weiwei & Gu, Weixi, 2024. "TriChronoNet: Advancing electricity price prediction with Multi-module fusion," Applied Energy, Elsevier, vol. 371(C).
    15. Chen, Xiaoxu & Cheng, Zhanhong & Sun, Lijun, 2025. "Bayesian inference of time-varying origin–destination matrices from boarding and alighting counts for transit services," Transportation Research Part B: Methodological, Elsevier, vol. 199(C).
    16. Spiliotis, Evangelos & Makridakis, Spyros & Kaltsounis, Anastasios & Assimakopoulos, Vassilios, 2021. "Product sales probabilistic forecasting: An empirical evaluation using the M5 competition data," International Journal of Production Economics, Elsevier, vol. 240(C).
    17. Tsoumalis, Georgios I. & Bampos, Zafeirios N. & Biskas, Pandelis N. & Keranidis, Stratos D. & Symeonidis, Polychronis A. & Voulgarakis, Dimitrios K., 2022. "A novel system for providing explicit demand response from domestic natural gas boilers," Applied Energy, Elsevier, vol. 317(C).
    18. d'Aspremont, Alexandre & Ben Arous, Simon & Bricongne, Jean-Charles & Lietti, Benjamin & Meunier, Baptiste, 2025. "Satellites turn “concrete”: Tracking cement with satellite data and neural networks," Journal of Econometrics, Elsevier, vol. 249(PC).
    19. Lu, Chung-Cheng & Ying, Kuo-Ching & Chen, Hui-Ju, 2016. "Real-time relief distribution in the aftermath of disasters – A rolling horizon approach," Transportation Research Part E: Logistics and Transportation Review, Elsevier, vol. 93(C), pages 1-20.
    20. Caicedo, Juan D. & Guirado, Carlos & González, Marta C. & Walker, Joan L., 2025. "Sharing, collaborating, and benchmarking to advance travel demand research: A demonstration of short-term ridership prediction," Transport Policy, Elsevier, vol. 171(C), pages 531-541.

    More about this item

    Keywords

    ;
    ;
    ;
    ;
    ;
    ;

    Statistics

    Access and download statistics

    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:jmathe:v:10:y:2022:i:19:p:3664-:d:934869. 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 The email address of this maintainer does not seem to be valid anymore. Please ask MDPI Indexing Manager to update the entry or send us the correct address (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.