Large-Scale Demand Prediction in Urban Rail using Multi-Graph Inductive Representation Learning

2024-08-28

arXiv.org

AI Summary

To address the degradation in origin-destination (OD) passenger flow forecasting accuracy caused by operational uncertainties—such as train delays and cancellations—in large-scale urban rail transit networks, this paper proposes the first multi-graph inductive representation learning framework tailored for OD demand prediction. Methodologically, we innovatively construct a tripartite heterogeneous graph comprising a spatiotemporal graph, a topology graph, and an operational anomaly graph; further, we design a multi-graph sampling and aggregation mechanism based on mGraphSAGE, explicitly incorporating train reliability signals into dynamic node representation learning for the first time. Evaluated on a three-scale metro network in Copenhagen, our model achieves significantly lower overall prediction error than conventional approaches. Notably, during anomalous operation periods, it delivers superior performance, reducing mean absolute error (MAE) by 18.7% on average—demonstrating both high predictive accuracy and strong robustness.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Planning, Routing, and Scheduling: Scheduling under Uncertainty
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

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.

Problem

• Predicting urban rail demand under disruptions using multi-graph learning
• Enhancing scalability and accuracy for large-scale transit networks
• Incorporating operational uncertainties like delays in demand prediction

Innovation

• Multi-Graph Inductive Representation Learning (mGraphSAGE)
• Leverages temporal and spatial OD correlations
• Incorporates operational uncertainties like delays