Predicting Urban Rail Transit Network Origin–Destination Matrix Under Operational Incidents with Deep Counterfactual Inference

The rapid expansion of urban rail networks has resulted in increasingly complex passenger flow patterns, presenting significant challenges for operational management, especially during incidents and emergencies. Disruptions such as power equipment failures, trackside faults, and train malfunctions can severely impact transit efficiency and reliability, leading to congestion and cascading network effects. Existing models for predicting passenger origin–destination (OD) matrices struggle to provide accurate and timely predictions under these disrupted conditions. This study proposes a deep counterfactual inference model that improves both the prediction accuracy and interpretability of OD matrices during incidents. The model uses a dual-channel framework based on multi-task learning, where the factual channel predicts OD matrices under normal conditions and the counterfactual channel estimates OD matrices during incidents, enabling the quantification of the spatiotemporal impacts of disruptions. Our approach which incorporates KL divergence-based propensity matching enhances prediction accuracy by 4.761% to 12.982% compared to baseline models, while also providing interpretable insights into disruption mechanisms. The model reveals that incident types vary in delay magnitude, with power equipment incidents causing the largest delays, and shows that incidents have time-lag effects on OD flows, with immediate impacts on origin stations and progressively delayed effects on destination and neighboring stations. This research offers practical tools for urban rail transit operators to estimate incident-affected passenger volumes and implement more efficient emergency response strategies, advancing emergency response capabilities in smart transit systems.