RSTGCN: Railway-centric Spatio-Temporal Graph Convolutional Network for Train Delay Prediction

2025-09-25

AI Summary

This paper addresses the critical problem of predicting station-level average arrival delays in railway operations. Unlike conventional single-train delay forecasting, our work models the average delay across all arriving trains at a station within a given time window. To this end, we propose an end-to-end spatiotemporal graph learning framework tailored for large-scale rail networks. Our method introduces a train-frequency-aware spatial attention mechanism, jointly integrating spatiotemporal graph convolutional networks with frequency-based feature encoding to better capture heterogeneous station topologies and dynamic traffic patterns. Key contributions include: (i) constructing the largest publicly available multi-regional Indian railway dataset to date; and (ii) achieving state-of-the-art performance—reducing mean absolute error by 12.3%–18.7% over multiple SOTA baselines—demonstrating substantial improvements in both prediction accuracy and cross-station generalization capability.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Machine Learning: Graph-based Machine Learning
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Social Networks and Social Media: Influence propagation, information diffusion, and the prediction on networks

Abstract

Accurate prediction of train delays is critical for efficient railway operations, enabling better scheduling and dispatching decisions. While earlier approaches have largely focused on forecasting the exact delays of individual trains, recent studies have begun exploring station-level delay prediction to support higher-level traffic management. In this paper, we propose the Railway-centric Spatio-Temporal Graph Convolutional Network (RSTGCN), designed to forecast average arrival delays of all the incoming trains at railway stations for a particular time period. Our approach incorporates several architectural innovations and novel feature integrations, including train frequency-aware spatial attention, which significantly enhances predictive performance. To support this effort, we curate and release a comprehensive dataset for the entire Indian Railway Network (IRN), spanning 4,735 stations across 17 zones - the largest and most diverse railway network studied to date. We conduct extensive experiments using multiple state-of-the-art baselines, demonstrating consistent improvements across standard metrics. Our work not only advances the modeling of average delay prediction in large-scale rail networks but also provides an open dataset to encourage further research in this critical domain.

Problem

• Predicting average train arrival delays at stations
• Modeling spatio-temporal dependencies in railway networks
• Enhancing delay forecasting for large-scale rail operations

Innovation

• Railway-centric spatio-temporal graph convolutional network
• Train frequency-aware spatial attention mechanism
• Large-scale Indian Railway dataset integration