Passenger Flow Redistribution Prediction Method Considering Metro Passengers’ Heterogeneity under Train Delay Conditions

Train delays propagate rapidly throughout the Urban Rail Transit (URT) network under networked operation conditions, posing significant challenges to operating departments. Accurate passenger flow redistribution prediction is a crucial foundation for formulating reasonable metro service recovery plans under urban rail transit delay conditions. This paper proposes a novel framework for predicting passenger flow redistribution based on passengers’ heterogeneity under delay conditions. We identify the affected passengers and determine their locations by tracing the travel chains, proposing the data-driven passenger travel choice model, and predicting the passenger redistribution. The proposed framework is validated using a real-world case of Shenzhen Metro in China, and it exhibits a high accuracy. The proposed method provides a microscopic view of passenger travel choices for macro-level passenger flow prediction and contributes to operation adjustments under delay conditions.