Hierarchical Forecast Reconciliation for Urban Rail Transit Demand Prediction under Operational Disruptions

2026-06-05

AI Summary

This study addresses the issue of hierarchical inconsistency in station-level and origin–destination (OD)-level passenger flow prediction under urban rail transit service disruptions, which arises from independent modeling and leads to biased operational decisions. To resolve this, the paper proposes the first hierarchical forecasting reconciliation framework tailored to disruption scenarios, introducing a nonlinear neural network mechanism based on a fully connected reconciler (FCR) that rigorously enforces hierarchical coherence. Experiments on Copenhagen S-train data demonstrate that the FCR reduces OD prediction error by up to 17.45% in multi-step disruption settings, significantly outperforming classical reconciliation methods such as ordinary least squares (OLS), weighted least squares (WLS), and minimum trace (MinT).

Abstract

Accurate and coherent passenger demand forecasting is essential for Urban Rail Transit (URT) operations. Passenger demand has a hierarchical structure in which origin-destination (OD) flows aggregate to station-level inflows and outflows through conservation constraints. In practice, station-level and OD-level forecasts are often generated independently, producing incoherent predictions that violate these constraints and introduce inconsistencies into operational decision-making. Such issues become more severe during disruptions, when forecasting reliability is most critical. This paper presents the first hierarchical forecast reconciliation framework for joint station-level and OD-level URT demand prediction. A neural Fully Connected Reconciler (FCR) learns a non-linear mapping from incoherent base forecasts to coherent hierarchical predictions while guaranteeing exact structural consistency by construction. The method is benchmarked against OLS, WLS, and Minimum Trace (MinT) variants using Rejsekort smart-card data from the Copenhagen S-train network under one-step, multi-step, and disruption forecasting scenarios. Results show that reconciliation consistently improves OD forecasting accuracy while ensuring hierarchical coherence. Under normal conditions, FCR performs competitively with MinT-based methods. An oracle analysis indicates that perfect station-level forecasts could reduce OD prediction error by up to 34 percent, highlighting the value of improved base forecasts. Under severe disruptions, FCR outperforms classical methods, reducing OD forecasting error by up to 17.45 percent in multi-step destination-side delay scenarios. These findings establish hierarchical reconciliation as an effective mechanism for improving forecast robustness, with the largest benefits occurring under the most challenging operating conditions.

Problem

• hierarchical forecast reconciliation
• urban rail transit
• demand prediction
• operational disruptions
• origin-destination flows

Innovation

• hierarchical forecast reconciliation
• neural reconciler
• urban rail transit demand prediction
• operational disruptions
• origin-destination forecasting