AI-driven dynamic timetable optimization for the Casablanca-Mohammedia-Rabat commuter railway

Abstract

Purpose-This study aims to investigate how artificial intelligence can enhance the resilience and efficiency of railway timetables in disruption-prone commuter corridors. Specifically, it focuses on Moroccan railway networks connecting Casablanca, Mohammedia, and Rabat, where recurrent delays and congestion compromise service reliability. The research seeks to determine how integrating predictive delay modeling with adaptive passenger behavior can reduce secondary delays, alleviate congestion, and maintain timetable stability under operational disturbances.

Design/methodology/approach-A unified, simulation-based framework was developed, combining 3 interlinked modules: (1) machine learning-based predictive delay forecasting, (2) agent-based modeling of passenger adaptive behavior, and (3) dynamic timetable reoptimization using a rolling-horizon heuristic approach. The framework operates as a closed-loop system, where predicted delays and simulated passenger responses continuously inform real-time timetable adjustments. Empirical validation was conducted using operational data from Moroccan commuter trains, with scenario-based analysis comparing baseline, prediction-only, and fully integrated interventions.

Findings-Results show that the fully integrated framework significantly improves operational performance. Average train delays were reduced by 46%, total passenger waiting time decreased by 43%, and congestion intensity was nearly halved, while timetable stability remained high at 95%. The study also demonstrates that passenger behavior plays a critical role in delay propagation, and that combining predictive forecasting with adaptive control strategies prevents the nonlinear amplification of secondary delays that traditional train-centric models fail to address.

Originality/value-This research advances the field of railway operations by presenting a passenger-centered, AI-driven timetable reoptimization framework that integrates predictive analytics and behavioral simulation within a dynamic feedback loop. Unlike conventional models, it captures emergent congestion patterns, anticipates disruptions proactively, and provides actionable operational strategies without requiring major infrastructure expansion. The study offers a novel methodological contribution with practical implications for enhancing commuter railway resilience in high-density, disruption-prone contexts.

Keywords

Artificial intelligence / Railway timetable optimization / Delay prediction / Agent-based simulation / Commuter railway resilience

References

[1] Besinovic, N. (2020). Resilience in railway transport systems: A literature review and research agenda. Transport Reviews, 40(4), 457-478. doi: 10.1080/01441647.2020.1728419.

[2] Chen, E., Luo, Q., Chen, J., & He, Y. (2023). Understanding passenger travel choice behaviours under train delays in urban rail transits: A data-driven approach. Transportation Business: Transport Dynamics, 11 (1), 1496-1524. doi: 10.1080/21680566.2023.2226824.

[3] Dai, X., Zhao, H., Yu, S., Cui, D., Zhang, Q., Dong, H., & Chai, T. (2021). Dynamic scheduling, operation control and their integration in high-speed railways: A review of recent research. IEEE Transactions on Intelligent Transportation Systems, 23(9), 13994-14010. doi: 10.1109/tits.2021.3131202.

[4] El Moussaoui, A. E., & El Moussaoui, T. (2026a). Rail freight development and modal shift from road transport: An empirical analysis of economic, energy and environmental perceptions in Morocco. Railway Sciences, 5(2), 225-244. doi: 10.1108/rs-01-2026-0001.

[5] El Moussaoui, T., & El Moussaoui, A. E. (2026b). Artificial intelligence for integrating railway freight into multi-actor supply chains: Insights from machine learning, deep learning and neural networks. Railway Sciences, 5(2), 204-224. doi: 10.1108/rs-01-2026-0002.

[6] Garrisi, G., & Cervello-Pastor, C. (2020). Train-scheduling optimization model for railway networks with multiplatform stations. Sustainability, 12(1), 257. doi: 10.3390/su12010257.

[7] Hoummirat, I., & Blayac, T. (2025). High-speed railway in developing countries: Mind the gap-lessons from Morocco-. Applied Economics, 57(41), 6448-6464. doi: 10.1080/00036846.2024.2385748.

[8] König, E. (2020). A review on railway delay management. Public Transport, 12(2), 335-361. doi: 10.1007/s12469-020-00233-1.

[9] Kuipers, R. (2024). Dwell time delays for commuter trains: An analysis of the influence of passengers on dwell time delays. (No. 331). PhD thesis, Germany: Dresden University of Technology.

[10] Kuipers, R. A., Palmqvist, C. W., Olsson, N. O., & Winslott Hiselius, L. (2021). The passenger’s influence on dwell times at station platforms: A literature review. Transport Reviews, 41(6), 721-741. doi: 10.1080/01441647.2021.1887960.

[11] Li, B., Guo, T., Li, R., Wang, Y., Gandomi, A. H., & Chen, F. (2023a). Self-adaptive predictive passenger flow modeling for large-scale railway systems. IEEE Internet of Things Journal, 10(16), 14182-14196. doi: 10.1109/jiot.2023.3270427.

[12] Li, P., Xue, R., Shao, S., Zhu, Y., & Liu, Y. (2023b). Current state and predicted technological trends in global railway intelligent digital transformation. Railway Sciences, 2(4), 397-412. doi: 10.1108/rs-10-2023-0036.

[13] Monsuur, F., Enoch, M., Quddus, M., & Meek, S. (2021). Modelling the impact of rail delays on passenger satisfaction. Transportation Research Part A: Policy and Practice, 152, 19-35. doi: 10.1016/j.tra.2021.08.002.

[14] Pang, Z., Wang, L., Wang, S., Li, L., & Peng, Q. (2023). Dynamic train dwell time forecasting: A hybrid approach to address the influence of passenger flow fluctuations. Railway Engineering Science, 31(4), 351-369. doi: 10.1007/s40534-023-00311-7.

[15] Safitri, C., Harjono, M. S., Hasrito, E. S., & Roestam, R. (2024). Comprehensive survey: Quality of service in railway communication using information-centric networking and light fidelity. IEEE Transactions on Intelligent Transportation Systems, 25(12), 19218-19251. doi: 10.1109/tits.2024.3472698.

[16] Salhi, S., Benhsain, W., & Boujrouf, S. (2024). The territorial dynamics of railroads in Morocco between disparities and economic development. GeoJournal, 89(4), 131. doi: 10.1007/s10708-024-11143-1.

[17] Sarp, S., Kuzlu, M., Jovanovic, V., Polat, Z., & Guler, O. (2024). Digitalization of railway transportation through AI-powered services: Digital twin trains. European Transport Research Review, 16(1), 58. doi: 10.1186/s12544-024-00679-5.

[18] Seriani, S., Aprigliano, V., Minatogawa, V., Peña, A., Lopez, A., & Gonzalez, F. (2025). Passenger service time at the platform-train interface: A review of variability, design factors, and crowd management implications based on laboratory experiments. Applied Sciences, 15(15), 8256. doi: 10.3390/app15158256.

[19] Sharma, B., Pellegrini, P., Rodriguez, J., & Chaudhary, N. (2023). A review of passenger-oriented railway rescheduling approaches. European Transport Research Review, 15(1), 14. doi: 10.1186/s12544-023-00587-0.

[20] Singh, A., & Kumar, S. (2026). Machine learning for train delay prediction: Techniques, challenges, and applications. In Artificial Intelligence and Sustainable Innovation (pp. 637-647). London: CRC Press.

[21] Taslimi, B., Sarijaloo, F. B., Liu, H., & Pardalos, P. M. (2022). A novel mixed integer programming model for freight train travel time estimation. European Journal of Operational Research, 300(2), 676-688. doi: 10.1016/j.ejor.2021.08.030.

[22] Yin, H., Liu, L., Chang, X., Fu, H., & Wu, J. (2025). Optimizing integrated train rescheduling strategies for diverse disruption scenarios using reinforcement learning. Computers & Industrial Engineering, 207, 111329. doi: 10.1016/j.cie.2025.111329.

[23] Zhang, J., & Zhang, J. (2023). Artificial intelligence applied on traffic planning and management for rail transport: A review and perspective. Discrete Dynamics in Nature and Society, 2023 (1), 1832501. doi: 10.1155/2023/1832501.