Bayesian spatiotemporal modeling of passenger trip assignment in metro networks

2025-07-30

AI Summary

This paper addresses the inverse problem of inferring subway passenger routes from Automated Fare Collection (AFC) data—where only origin-destination (OD) pairs and total travel times are observed, while actual paths and dynamic network costs remain latent. We propose a Bayesian spatiotemporal joint modeling framework. Specifically, we develop a spatiotemporally varying-coefficient multinomial logit model, integrating kernelized tensor decomposition with Gaussian process priors to capture heterogeneous route choice preferences and time-varying network costs. We further model travel time components via piecewise random walks and embed them in a hierarchical Bayesian structure, accompanied by an efficient MCMC inference algorithm. Evaluated on large-scale real-world AFC data from the Hong Kong MTR, our method significantly outperforms baseline approaches, accurately recovering the dynamic evolution of route choice behavior and its spatiotemporal heterogeneity. The framework delivers interpretable, uncertainty-quantified insights for passenger flow forecasting, capacity planning, and service optimization.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Reasoning under Uncertainty: Relational Probabilistic Models
• Machine Learning: Bayesian Learning

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics

Abstract

Assigning passenger trips to specific network paths using automatic fare collection (AFC) data is a fundamental application in urban transit analysis. The task is a difficult inverse problem: the only available information consists of each passenger's total travel time and their origin and destination, while individual passenger path choices and dynamic network costs are unobservable, and behavior varies significantly across space and time. We propose a novel Bayesian hierarchical model to resolve this problem by jointly estimating dynamic network costs and passenger path choices while quantifying their uncertainty. Our model decomposes trip travel time into four components -- access, in-vehicle, transfer, and egress -- each modeled as a time-varying random walk. To capture heterogeneous passenger behavior, we introduce a multinomial logit model with spatiotemporally varying coefficients. We manage the high dimensionality of these coefficients using kernelized tensor factorization with Gaussian process priors to effectively model complex spatiotemporal correlations. We develop a tailored and efficient Markov chain Monte Carlo (MCMC) algorithm for model inference. A simulation study demonstrates the method's effectiveness in recovering the underlying model parameters. On a large-scale dataset from the Hong Kong Mass Transit Railway, our framework demonstrates superior estimation accuracy over established benchmarks. The results reveal significant spatiotemporal variations in passenger preferences and provide robust uncertainty quantification, offering transit operators a powerful tool for enhancing service planning and operational management.

Problem

• Estimating dynamic network costs and passenger path choices from AFC data
• Modeling spatiotemporal variations in passenger behavior and preferences
• Quantifying uncertainty in trip assignment for transit service planning

Innovation

• Bayesian hierarchical model for dynamic network costs
• Multinomial logit with spatiotemporal varying coefficients
• Kernelized tensor factorization for high-dimensional data