A Disturbance-Driven Textual Model for Train Running Time Prediction on High-Speed Railways
Publication: Journal of Transportation Engineering, Part A: Systems
Volume 150, Issue 10
Abstract
Accurately predicting train running times (TRTs) during disturbances is crucial for effective timetable rescheduling. Previous studies on train running prediction have overlooked the detailed textual description of disturbance events. To improve the prediction accuracy, this paper proposes a hybrid neural network model consisting of a transformer encoder and a fully connected neural network (FCNN) to predict the TRTs under disturbances, which is called transformer-FCNN here. In the proposed transformer-FCNN architecture, a transformer encoder is used to process textual disturbance events, while FCNN is used to deal with static features. The performance of transformer-FCNN is validated using data from the Wuhan-Guangzhou and Xiamen-Shenzhen high-speed railways. The results show that the models considering the disturbance category can substantially improve the predictive performance compared with those that do not. Further, based on the same algorithm, models which use textual disturbance event records are shown to reduce the mean absolute error and the root mean squared error, respectively, by over 10.8% and 8.3% on average compared with those that only consider the disturbance category. The proposed model can support potential strategies of train operation control, by providing accurate prediction results.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
Some or all data, models, or code that support the findings of this study are available from the corresponding author upon reasonable request.
Acknowledgments
This work was supported by the National Key Research and Development Program of China (Grant No. 2022YFB4300502), the Research and development project of China National Railway Group Co., Ltd (Grant No. P2020X016), China Railway Chengdu Group Co. Ltd (Grant No. CX 2120), Ltd, Yunnan Fundamental Research Project (Grant No. 202301AU070052) and Kunming University of Science and Technology (Grant Nos. KUST-xk2022002 and JPSC2023003). We are grateful for the contributions made by our project partners.
References
Arshad, M., and M. Ahmed. 2021. “Train delay estimation in Indian railways by including weather factors through machine learning techniques.” Recent Adv. Comput. Sci. Commun. 14 (4): 1300–1307. https://doi.org/10.2174/2666255813666190912095739.
Ba, J. L., J. R. Kiros, and G. E. Hinton. 2016. “Layer normalization.” Preprint, submitted July 21, 2016. https://arxiv.org/abs/1607.06450.
Barbour, W., J. C. M. Mori, S. Kuppa, and D. B. Work. 2018. “Prediction of arrival times of freight traffic on US railroads using support vector regression.” Transp. Res. Part C Emerging Technol. 93 (Aug): 211–227. https://doi.org/10.1016/j.trc.2018.05.019.
Corman, F., and P. Kecman. 2018. “Stochastic prediction of train delays in real-time using Bayesian networks.” Transp. Res. Part C Emerging Technol. 95 (Oct): 599–615. https://doi.org/10.1016/j.trc.2018.08.003.
Ding, X., X. Xu, J. Li, and R. Shi. 2021. “A train delays prediction model under different causes based on MTGNN Approach.” In Proc., 2021 IEEE Int. Intelligent Transportation Systems Conf. (ITSC), 2387–2392. New York: IEEE.
Gaurav, R., and B. Srivastava. 2018. “Estimating train delays in a large rail network using a zero shot Markov model.” In Proc., 2018 21st Int. Conf. on Intelligent Transportation Systems (ITSC), 1221–1226. New York: IEEE.
He, K., X. Zhang, S. Ren, and J. Sun. 2016. “Deep residual learning for image recognition.” In Proc., IEEE Conf. on Computer Vision and Pattern Recognition, 770–778. New York: IEEE.
Huang, P., Z. Li, Y. Zhu, C. Wen, and F. Corman. 2023. “Train traffic control in merging stations: A data-driven approach.” Transp. Res. Part C Emerging Technol. 152 (Jul): 104155. https://doi.org/10.1016/j.trc.2023.104155.
Huang, P., C. Wen, L. Fu, Q. Peng, and Z. Li. 2020. “A hybrid model to improve the train running time prediction ability during high-speed railway disruptions.” Saf. Sci. 122 (Feb): 104510. https://doi.org/10.1016/j.ssci.2019.104510.
Huang, P., C. Wen, Q. Peng, C. Jiang, Y. Yang, and Z. Fu. 2019. “Modeling the influence of disturbances in high-speed railway systems.” J. Adv. Transp. 2019 (Mar): 8639589. https://doi.org/10.1155/2019/8639589.
Kingma, D. P., and J. Ba. 2014. “Adam: A method for stochastic optimization.” Preprint, submitted December 22, 2014. https://arxiv.org/abs/1412.6980.
Krüger, N. A., I. Vierth, and F. Fakhraei Roudsari. 2013. Spatial, temporal and size distribution of freight train delays: Evidence from Sweden. Stockholm, Sweden: Centre for Transport Studies.
Lee, W.-H., L.-H. Yen, and C.-M. Chou. 2016. “A delay root cause discovery and timetable adjustment model for enhancing the punctuality of railway services.” Transp. Res. Part C Emerging Technol. 73 (Dec): 49–64. https://doi.org/10.1016/j.trc.2016.10.009.
Lessan, J., L. Fu, and C. Wen. 2019. “A hybrid Bayesian network model for predicting delays in train operations.” Comput. Ind. Eng. 127 (Jan): 1214–1222. https://doi.org/10.1016/j.cie.2018.03.017.
Lessan, J., L. Fu, C. Wen, P. Huang, and C. Jiang. 2018. “Stochastic model of train running time and arrival delay: A case study of Wuhan–Guangzhou high-speed rail.” Transp. Res. Rec. 2672 (10): 215–223. https://doi.org/10.1177/0361198118780830.
Ling, X., Y. Peng, S. Sun, P. Li, and P. Wang. 2018. “Uncovering correlation between train delay and train exposure to bad weather.” Physica A 512 (Dec): 1152–1159. https://doi.org/10.1016/j.physa.2018.07.057.
Liu, J., P. M. Schonfeld, C. Shuai, M. He, and K. C. Wang. 2022. “The controllability of China’s high-speed rail network in terms of delivering emergency supplies.” Physica A 606 (Nov): 128055. https://doi.org/10.1016/j.physa.2022.128055.
Liu, J., P. M. Schonfeld, S. Zhan, B. Du, M. He, K. C. Wang, and Y. Yin. 2023. “The economic value of reserve capacity considering the reliability and robustness of a rail transit network.” J. Transp. Eng. Part A. Syst. 149 (6): 04023046. https://doi.org/10.1061/JTEPBS.TEENG-7691.
Marković, N., S. Milinković, K. S. Tikhonov, and P. Schonfeld. 2015. “Analyzing passenger train arrival delays with support vector regression.” Transp. Res. Part C Emerging Technol. 56 (Jul): 251–262. https://doi.org/10.1016/j.trc.2015.04.004.
Mason, L., J. Baxter, P. Bartlett, and M. Frean. 1999. “Boosting algorithms as gradient descent.” In Advances in neural information processing systems, 12. Cambridge, MA: MIT Press.
Nabian, M. A., N. Alemazkoor, and H. Meidani. 2019. “Predicting near-term train schedule performance and delay using bi-level random forests.” Transp. Res. Rec. 2673 (5): 564–573. https://doi.org/10.1177/0361198119840339.
Nair, R., T. L. Hoang, M. Laumanns, B. Chen, R. Cogill, J. Szabó, and T. Walter. 2019. “An ensemble prediction model for train delays.” Transp. Res. Part C Emerging Technol. 104 (Jul): 196–209. https://doi.org/10.1016/j.trc.2019.04.026.
Nystrom, B., and U. Kumar. 2005. “Delay analysis of a freight train an Improvement case study from a steel company.” In Proc., World Congress on Railway Research, 20–32. Paris: UIC.
Ochsner, M., C.-W. Palmqvist, L. Winslott Hiselius, and N. Olsson. 2023. “The effects of flooding on railway infrastructure: A literature review.” Transp. Res. Arena 72 (Jan): 1786–1791. https://doi.org/10.1016/j.trpro.2023.11.654.
Olsson, N. O., and H. Haugland. 2004. “Influencing factors on train punctuality—Results from some Norwegian studies.” Transp. Policy 11 (4): 387–397. https://doi.org/10.1016/j.tranpol.2004.07.001.
Oneto, L., I. Buselli, P. Sanetti, R. Canepa, S. Petralli, and D. Anguita. 2019. “Restoration time prediction in large scale railway networks: Big data and interpretability.” In Proc., INNS Big Data and Deep Learning Conf., 136–141. Cham, Switzerland: Springer.
Oneto, L., E. Fumeo, G. Clerico, R. Canepa, F. Papa, C. Dambra, N. Mazzino, and D. Anguita. 2016. “Advanced analytics for train delay prediction systems by including exogenous weather data.” In Proc., 2016 IEEE Int. Conf. on Data Science and Advanced Analytics (DSAA), 458–467. New York: IEEE.
Pedregosa, F., G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, and V. Dubourg. 2011. “Scikit-learn: Machine learning in Python.” J. Mach. Learn. Res. 12 (10): 2825–2830.
Pongnumkul, S., T. Pechprasarn, N. Kunaseth, and K. Chaipah. 2014. “Improving arrival time prediction of Thailand’s passenger trains using historical travel times.” In Proc., Computer Science and Software Engineering (JCSSE), 2014 11th Int. Joint Conf., 307–312. New York: IEEE.
Rodrigues, F., I. Markou, and F. C. Pereira. 2019. “Combining time-series and textual data for taxi demand prediction in event areas: A deep learning approach.” Inf. Fusion 49 (Sep): 120–129. https://doi.org/10.1016/j.inffus.2018.07.007.
Şahin, İ. 2022. “Data-driven stochastic model for train delay analysis and prediction.” Int. J. Rail Transp. 11 (2): 207–226. https://doi.org/10.1080/23248378.2022.2065372.
Svozil, D., V. Kvasnicka, and J. Pospichal. 1997. “Introduction to multi-layer feed-forward neural networks.” Chemometr. Intell. Lab. Syst. 39 (1): 43–62. https://doi.org/10.1016/S0169-7439(97)00061-0.
Tang, Y., C. Wen, P. Huang, Z. Li, J. Li, and Y. Yang. 2018. “Support vector regression models for influenced time prediction in high-speed rail system.” In Proc., 2018 Transportation Research Board. Washington, DC: Transportation Research Board.
Vaswani, A., N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, and I. Polosukhin. 2017. “Attention is all you need.” Preprint, submitted June 12, 2017. https://arxiv.org/abs/1706.03762.
Wang, P., and Q.-P. Zhang. 2019. “Train delay analysis and prediction based on big data fusion.” Transp. Saf. Environ. 1 (1): 79–88. https://doi.org/10.1093/tse/tdy001.
Wen, C., P. Huang, Z. Li, J. Lessan, L. Fu, C. Jiang, and X. Xu. 2019a. “Train dispatching management with data-driven approaches: A comprehensive review and appraisal.” IEEE Access 7 (Aug): 114547–114571. https://doi.org/10.1109/ACCESS.2019.2935106.
Wen, C., Z. Li, P. Huang, J. Lessan, L. Fu, and C. Jiang. 2019b. “Cause-specific investigation of primary delays of Wuhan–Guangzhou HSR.” Transp. Lett. 12 (7): 451–464. https://doi.org/10.1080/19427867.2019.1634902.
Zhan, S., L. G. Kroon, J. Zhao, and Q. Peng. 2016. “A rolling horizon approach to the high speed train rescheduling problem in case of a partial segment blockage.” Transp. Res. Part E Logist. Transp. Rev. 95 (Nov): 32–61. https://doi.org/10.1016/j.tre.2016.07.015.
Zhuang, H., C. Wen, Z. Li, Y. Tang, and P. Huang. 2017. “Cause based primary delay distribution models of high-speed trains on account of operation records.” J. China Railway Soc. 39 (9): 25–31. https://doi.org/10.3969/j.issn.1001-8360.2017.09.004.
Zilko, A., A. Hanea, D. Kurowicka, and R. Goverde. 2014. “Non-parametric Bayesian network to forecast railway disruption lengths.” In Proc., Second Int. Conf. on Railway Technology: Research, Development and Maintenance (Railways 2014). Stirling, UK: Civil-Comp Press.
Zilko, A. A., D. Kurowicka, and R. M. Goverde. 2016. “Modeling railway disruption lengths with Copula Bayesian Networks.” Transp. Res. Part C Emerging Technol. 68 (Jul): 350–368. https://doi.org/10.1016/j.trc.2016.04.018.
Information & Authors
Information
Published In
Journal of Transportation Engineering, Part A: Systems
Volume 150 • Issue 10 • October 2024
Copyright
© 2024 American Society of Civil Engineers.
History
Received: Nov 8, 2023
Accepted: Mar 21, 2024
Published online: Aug 7, 2024
Published in print: Oct 1, 2024
Discussion open until: Jan 7, 2025
ASCE Technical Topics:
- Artificial intelligence (AI)
- Artificial intelligence and machine learning
- Computer programming
- Computing in civil engineering
- Engineering fundamentals
- Errors (statistics)
- High-speed rail
- Hybrid methods
- Infrastructure
- Mathematics
- Methodology (by type)
- Model accuracy
- Models (by type)
- Neural networks
- Public transportation
- Rail transportation
- Railroad trains
- Statistics
- Transportation engineering
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.