Simulation-Driven Railway Delay Prediction: An Imitation Learning Approach
This work addresses the need for reliable delay prediction to enhance railway system robustness and efficiency, representing an incremental improvement through a novel hybrid method.
The paper tackled the problem of predicting train delays by reframing it as a stochastic simulation task, introducing Drift-Corrected Imitation Learning (DCIL) to mitigate covariate shift, and demonstrated superior performance over traditional models with a real-world dataset of over three million train movements for predictions up to 30 minutes ahead.
Reliable prediction of train delays is essential for enhancing the robustness and efficiency of railway transportation systems. In this work, we reframe delay forecasting as a stochastic simulation task, modeling state-transition dynamics through imitation learning. We introduce Drift-Corrected Imitation Learning (DCIL), a novel self-supervised algorithm that extends DAgger by incorporating distance-based drift correction, thereby mitigating covariate shift during rollouts without requiring access to an external oracle or adversarial schemes. Our approach synthesizes the dynamical fidelity of event-driven models with the representational capacity of data-driven methods, enabling uncertainty-aware forecasting via Monte Carlo simulation. We evaluate DCIL using a comprehensive real-world dataset from \textsc{Infrabel}, the Belgian railway infrastructure manager, which encompasses over three million train movements. Our results, focused on predictions up to 30 minutes ahead, demonstrate superior predictive performance of DCIL over traditional regression models and behavioral cloning on deep learning architectures, highlighting its effectiveness in capturing the sequential and uncertain nature of delay propagation in large-scale networks.