Saved in:
Bibliographic Details
Main Authors: Mo, Zhaobin, Liao, Xiangyi, Karbowski, Dominik A., Wang, Yanbing
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.17109
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916705269186560
author Mo, Zhaobin
Liao, Xiangyi
Karbowski, Dominik A.
Wang, Yanbing
author_facet Mo, Zhaobin
Liao, Xiangyi
Karbowski, Dominik A.
Wang, Yanbing
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2504_17109
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Discovering the Precursors of Traffic Breakdowns Using Spatiotemporal Graph Attribution Networks
Mo, Zhaobin
Liao, Xiangyi
Karbowski, Dominik A.
Wang, Yanbing
Machine Learning
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.
title Discovering the Precursors of Traffic Breakdowns Using Spatiotemporal Graph Attribution Networks
topic Machine Learning
url https://arxiv.org/abs/2504.17109