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

Abstract

Featured Application: This research introduces an innovative framework for predicting passenger origin–destination (OD) matrices during operational disruptions in urban rail transit (URT) systems. By leveraging a dual-channel deep counterfactual inference model, the framework integrates factual predictions with counterfactual estimations, enabling the prediction of passenger flows under both normal and disrupted conditions. This approach has practical applications in optimizing emergency response strategies and managing the impact of disruptions on urban rail networks. The model can be used to construct a multi-level incident classification system, categorizing disruptions into varying severities from high-impact incidents such as power equipment incidents to less severe ones like door malfunctions. Based on these classifications, tailored emergency plans can be developed, outlining specific measures for passenger flow management, including crowd control, station-level passenger redirection, and the activation of bus shuttle services. The model’s ability to predict delay propagation throughout the network allows transit operators to predict which stations will likely be affected and take preemptive actions. By analyzing the spatial and temporal effects of incidents, the framework helps minimize congestion and improve overall system resilience during emergencies. 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.