Zhang, Yifei (Beijing Jiaotong University), Li, Haiying (Beijing Jiaotong University), Jiang, Xi (Beijing Jiaotong University), Yang, yuedi (Beijing Wuzi University), xu, xinyue (Beijing Jiaotong University), WANG, Xiaoran (Beijing Jiaotong University)

Estimation of Passenger Flow Status under Urban Rail Transit Disruption Based on a Two-Phase Parallel Framework

Scheduled for presentation during the Video Session "On-Demand Video Presentations" (VP-VP), Saturday, November 22, 2025, 08:00−18:00, On-Demand Platform

2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC), November 18-21, 2025, Gold Coast, Australia

This information is tentative and subject to change. Compiled on April 2, 2026

Abstract

Under unexpected service disruptions, rapid and accurate estimation of passenger flow status is crucial for ensuring timely responses and improving service reliability. This study proposes an integrated framework for rolling estimates of the passenger flow status across the entire Urban rail transit (URT) network. First, we describe passengers' path choice behavior under risk and uncertainty using Cumulative Prospect Theory (CPT). Second, we construct a space-time network to depict the coupling relationship between passengers and trains, revealing dynamic changes in passenger flow status at a minute-level granularity. Next, we analyze the transfer relationships to decompose the network structure and establish a two-phase (TP) parallel framework for lines. Finally, we evaluate the performance of the proposed framework using real Automated Fare Collection (AFC) and Automatic Vehicle Location (AVL) data from the Guangzhou Metro. The results show that the CPT-based model ensures that 92.8% of passengers have an arrival time deviation within 10 minutes. The proposed TP parallel framework reduces the computational load of passenger assignment by 85.63%.