Multi-Graph Inductive Representation Learning for Large-Scale Urban Rail Demand Prediction under Disruptions

TL;DR

This paper introduces mGraphSAGE, a scalable multi-graph inductive learning model that improves urban rail demand prediction by incorporating operational uncertainties like delays and cancellations, validated on Copenhagen's networks.

Contribution

The study presents a novel multi-graph inductive learning approach that enhances demand prediction accuracy and scalability for large-scale urban rail networks under operational uncertainties.

Findings

mGraphSAGE outperforms existing machine learning methods in OD demand prediction.

Including operational uncertainties improves prediction accuracy during disruptions.

The model is effective across different network scales and conditions.

Abstract

With the expansion of cities over time, URT (Urban Rail Transit) networks have also grown significantly. Demand prediction plays an important role in supporting planning, scheduling, fleet management, and other operational decisions. In this study, we propose an Origin-Destination (OD) demand prediction model called Multi-Graph Inductive Representation Learning (mGraphSAGE) for large-scale URT networks under operational uncertainties. Our main contributions are twofold: we enhance prediction results while ensuring scalability for large networks by relying simultaneously on multiple graphs, where each OD pair is a node on a graph and distinct OD relationships, such as temporal and spatial correlations; we show the importance of including operational uncertainties such as train delays and cancellations as inputs in demand prediction for daily operations. The model is validated on three different scales of the URT network in Copenhagen, Denmark. Experimental results show that by leveraging information from neighboring ODs and learning node representations via sampling and aggregation, mGraphSAGE is particularly suitable for OD demand prediction in large-scale URT networks, outperforming reference machine learning methods. Furthermore, during periods with train cancellations and delays, the performance gap between mGraphSAGE and other methods improves compared to normal operating conditions, demonstrating its ability to leverage system reliability information for predicting OD demand under uncertainty.