Discovering the Precursors of Traffic Breakdowns Using Spatiotemporal Graph Attribution Networks

2025/04/23 by Zhaobin Mo, Mo, Zhaobin, Xiangyi Liao +5
Computer Science · Physics and Astronomy · #Advanced Graph Neural Networks #Complex Network Analysis Techniques #FOS: Computer and information sciences #Graph Theory and Algorithms #Machine Learning (cs.LG)

paper · pdf · doi:10.48550/arxiv.2504.17109

openalex publication_date 2025/04/23 · openalex created_date 2025/10/18 · openalex updated_date 2026/07/28

Abstract

Understanding and predicting the precursors of traffic breakdowns is critical for improving road safety and traffic flow management. This paper presents a novel approach combining spatiotemporal graph neural networks (ST-GNNs) with Shapley values to identify and interpret traffic breakdown precursors. By extending Shapley explanation methods to a spatiotemporal setting, our proposed method bridges the gap between black-box neural network predictions and interpretable causes. We demonstrate the method on the Interstate-24 data, and identify that road topology and abrupt braking are major factors that lead to traffic breakdowns.

Citations

• Virtual trajectories for I-24 MOTION: data and tools
• I-24 MOTION: An instrument for freeway traffic science
• GraphSVX: Shapley Value Explanations for Graph Neural Networks
• The many Shapley values for model explanation
• Reconstructing the Traffic State by Fusion of Heterogeneous Data

Related

• RadNet: Incident Prediction in Spatio-Temporal Road Graph Networks Using Traffic Forecasting
• ST-GraphNet: A Spatio-Temporal Graph Neural Network for Understanding and Predicting Automated Vehicle Crash Severity
• Graph Neural Networks for Road Safety Modeling: Datasets and Evaluations for Accident Analysis
• Enhancing Graph Neural Networks in Large-scale Traffic Incident Analysis with Concurrency Hypothesis
• Traffic Flow Forecasting with Spatial-Temporal Graph Diffusion Network