IDEAS home Printed from https://ideas.repec.org/a/gam/jmathe/v11y2023i4p839-d1060231.html
   My bibliography  Save this article

Train Delay Predictions Using Markov Chains Based on Process Time Deviations and Elastic State Boundaries

Author

Listed:
  • Thomas Spanninger

    (Institute for Transport Planning and Systems (IVT), ETH Zurich, Stefano-Franscini-Platz 5, 8093 Zurich, Switzerland)

  • Beda Büchel

    (Institute for Transport Planning and Systems (IVT), ETH Zurich, Stefano-Franscini-Platz 5, 8093 Zurich, Switzerland)

  • Francesco Corman

    (Institute for Transport Planning and Systems (IVT), ETH Zurich, Stefano-Franscini-Platz 5, 8093 Zurich, Switzerland)

Abstract

Train delays are inconvenient for passengers and major problems in railway operations. When delays occur, it is vital to provide timely information to passengers regarding delays at their departing, interchanging, and final stations. Furthermore, real-time traffic control requires information on how delays propagate throughout the network. Among a multitude of applied models to predict train delays, Markov chains have proven to be stochastic benchmark approaches due to their simplicity, interpretability, and solid performances. In this study, we introduce an advanced Markov chain setting to predict train delays using historical train operation data. Therefore, we applied Markov chains based on process time deviations instead of absolute delays and we relaxed commonly used stationarity assumptions for transition probabilities in terms of direction, train line, and location. Additionally, we defined the state space elastically and analyzed the benefit of an increasing state space dimension. We show (via a test case in the Swiss railway network) that our proposed advanced Markov chain model achieves a prediction accuracy gain of 56% in terms of mean absolute error (MAE) compared to state-of-the-art Markov chain models based on absolute delays. We also illustrate the prediction performance advantages of our proposed model in the case of training data sparsity.

Suggested Citation

  • Thomas Spanninger & Beda Büchel & Francesco Corman, 2023. "Train Delay Predictions Using Markov Chains Based on Process Time Deviations and Elastic State Boundaries," Mathematics, MDPI, vol. 11(4), pages 1-23, February.
  • Handle: RePEc:gam:jmathe:v:11:y:2023:i:4:p:839-:d:1060231
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/2227-7390/11/4/839/pdf
    Download Restriction: no

    File URL: https://www.mdpi.com/2227-7390/11/4/839/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Betsy S. Greenberg & Robert C. Leachman & Ronald W. Wolff, 1988. "Predicting Dispatching Delays on a Low Speed, Single Track Railroad," Transportation Science, INFORMS, vol. 22(1), pages 31-38, February.
    2. Gorman, Michael F., 2009. "Statistical estimation of railroad congestion delay," Transportation Research Part E: Logistics and Transportation Review, Elsevier, vol. 45(3), pages 446-456, May.
    3. Huang, Ping & Wen, Chao & Fu, Liping & Lessan, Javad & Jiang, Chaozhe & Peng, Qiyuan & Xu, Xinyue, 2020. "Modeling train operation as sequences: A study of delay prediction with operation and weather data," Transportation Research Part E: Logistics and Transportation Review, Elsevier, vol. 141(C).
    4. Yuexin Wang & Chao Wen & Ping Huang, 2022. "Predicting the effectiveness of supplement time on delay recoveries: a support vector regression approach," International Journal of Rail Transportation, Taylor & Francis Journals, vol. 10(3), pages 375-392, May.
    5. Murali, Pavankumar & Dessouky, Maged & Ordóñez, Fernando & Palmer, Kurt, 2010. "A delay estimation technique for single and double-track railroads," Transportation Research Part E: Logistics and Transportation Review, Elsevier, vol. 46(4), pages 483-495, July.
    6. Susan Fraley Hallowell & Patrick T. Harker, 1996. "Predicting On-Time Line-Haul Performance in Scheduled Railroad Operations," Transportation Science, INFORMS, vol. 30(4), pages 364-378, November.
    7. Carey, Malachy & Kwiecinski, Andrzej, 1994. "Stochastic approximation to the effects of headways on knock-on delays of trains," Transportation Research Part B: Methodological, Elsevier, vol. 28(4), pages 251-267, August.
    8. Yuan, Jianxin & Hansen, Ingo A., 2007. "Optimizing capacity utilization of stations by estimating knock-on train delays," Transportation Research Part B: Methodological, Elsevier, vol. 41(2), pages 202-217, February.
    9. Meester, Ludolf E. & Muns, Sander, 2007. "Stochastic delay propagation in railway networks and phase-type distributions," Transportation Research Part B: Methodological, Elsevier, vol. 41(2), pages 218-230, February.
    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. Huang, Ping & Wen, Chao & Fu, Liping & Lessan, Javad & Jiang, Chaozhe & Peng, Qiyuan & Xu, Xinyue, 2020. "Modeling train operation as sequences: A study of delay prediction with operation and weather data," Transportation Research Part E: Logistics and Transportation Review, Elsevier, vol. 141(C).
    2. Huang, Ping & Guo, Jingwei & Liu, Shu & Corman, Francesco, 2024. "Explainable train delay propagation: A graph attention network approach," Transportation Research Part E: Logistics and Transportation Review, Elsevier, vol. 184(C).
    3. Leachman, Robert C. & Jula, Payman, 2012. "Estimating flow times for containerized imports from Asia to the United States through the Western rail network," Transportation Research Part E: Logistics and Transportation Review, Elsevier, vol. 48(1), pages 296-309.
    4. Harshad Khadilkar, 2017. "Data-Enabled Stochastic Modeling for Evaluating Schedule Robustness of Railway Networks," Transportation Science, INFORMS, vol. 51(4), pages 1161-1176, November.
    5. Chao Wen & Weiwei Mou & Ping Huang & Zhongcan Li, 2020. "A predictive model of train delays on a railway line," Journal of Forecasting, John Wiley & Sons, Ltd., vol. 39(3), pages 470-488, April.
    6. Tiong, Kah Yong & Ma, Zhenliang & Palmqvist, Carl-William, 2023. "Analyzing factors contributing to real-time train arrival delays using seemingly unrelated regression models," Transportation Research Part A: Policy and Practice, Elsevier, vol. 174(C).
    7. Krüger, Niclas A. & Vierth , Inge & Fakhraei Roudsari, Farzad, 2013. "Spatial, temporal and size distribution of freight train delays: evidence from Sweden," Working papers in Transport Economics 2013:8, CTS - Centre for Transport Studies Stockholm (KTH and VTI).
    8. Agbelie, Bismark & Libnao, Kathleen, 2018. "Unobserved heterogeneity analysis of rail transit incident delays," Transportation Research Part A: Policy and Practice, Elsevier, vol. 117(C), pages 39-43.
    9. Krier, Betty & Liu, Chia-Mei & McNamara, Brian & Sharpe, Jerrod, 2014. "Individual freight effects, capacity utilization, and Amtrak service quality," Transportation Research Part A: Policy and Practice, Elsevier, vol. 64(C), pages 163-175.
    10. Gert Janssenswillen & Benoît Depaire & Sabine Verboven, 2018. "Detecting train reroutings with process mining," EURO Journal on Transportation and Logistics, Springer;EURO - The Association of European Operational Research Societies, vol. 7(1), pages 1-24, March.
    11. Taslimi, Bijan & Babaie Sarijaloo, Farnaz & Liu, Hongcheng & Pardalos, Panos M., 2022. "A novel mixed integer programming model for freight train travel time estimation," European Journal of Operational Research, Elsevier, vol. 300(2), pages 676-688.
    12. Bernal, Margarita & Welch, Eric W. & Sriraj, P.S., 2016. "The effect of slow zones on ridership: An analysis of the Chicago Transit Authority “El” Blue Line," Transportation Research Part A: Policy and Practice, Elsevier, vol. 87(C), pages 11-21.
    13. Mu, Shi & Dessouky, Maged, 2013. "Efficient dispatching rules on double tracks with heterogeneous train traffic," Transportation Research Part B: Methodological, Elsevier, vol. 51(C), pages 45-64.
    14. Jovanović, Predrag & Kecman, Pavle & Bojović, Nebojša & Mandić, Dragomir, 2017. "Optimal allocation of buffer times to increase train schedule robustness," European Journal of Operational Research, Elsevier, vol. 256(1), pages 44-54.
    15. Wei, Dali & Liu, Hongchao & Qin, Yong, 2015. "Modeling cascade dynamics of railway networks under inclement weather," Transportation Research Part E: Logistics and Transportation Review, Elsevier, vol. 80(C), pages 95-122.
    16. Wang, Shuaian & Meng, Qiang, 2012. "Liner ship route schedule design with sea contingency time and port time uncertainty," Transportation Research Part B: Methodological, Elsevier, vol. 46(5), pages 615-633.
    17. Meng, Lingyun & Zhou, Xuesong, 2011. "Robust single-track train dispatching model under a dynamic and stochastic environment: A scenario-based rolling horizon solution approach," Transportation Research Part B: Methodological, Elsevier, vol. 45(7), pages 1080-1102, August.
    18. Franciszek Restel & Łukasz Wolniewicz & Matea Mikulčić, 2021. "Method for Designing Robust and Energy Efficient Railway Schedules," Energies, MDPI, vol. 14(24), pages 1-12, December.
    19. Hallowell, Susan F. & Harker, Patrick T., 1998. "Predicting on-time performance in scheduled railroad operations: methodology and application to train scheduling," Transportation Research Part A: Policy and Practice, Elsevier, vol. 32(4), pages 279-295, May.
    20. Sobrie, Léon & Verschelde, Marijn & Hennebel, Veerle & Roets, Bart, 2023. "Capturing complexity over space and time via deep learning: An application to real-time delay prediction in railways," European Journal of Operational Research, Elsevier, vol. 310(3), pages 1201-1217.

    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:11:y:2023:i:4:p:839-:d:1060231. 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.