ST-GraphNet: A Spatio-Temporal Graph Neural Network for Understanding and Predicting Automated Vehicle Crash Severity
Not on the map. Why?
Abstract (arXiv)
Understanding the spatial and temporal dynamics of automated vehicle (AV) crash severity is critical for advancing urban mobility safety and infrastructure planning. In this work, we introduce ST-GraphNet, a spatio-temporal graph neural network framework designed to model and predict AV crash severity by using both fine-grained and region-aggregated spatial graphs. Using a balanced dataset of 2,352 real-world AV-related crash reports from Texas (2024), including geospatial coordinates, crash timestamps, SAE automation levels, and narrative descriptions, we construct two complementary graph representations: (1) a fine-grained graph with individual crash events as nodes, where edges are defined via spatio-temporal proximity; and (2) a coarse-grained graph where crashes are aggregated into Hexagonal Hierarchical Spatial Indexing (H3)-based spatial cells, connected through hexagonal adjacency. Each node in the graph is enriched with multimodal data, including semantic, spatial, and temporal attributes, including textual embeddings from crash narratives using a pretrained Sentence-BERT model. We evaluate various graph neural network (GNN) architectures, such as Graph Convolutional Networks (GCN), Graph Attention Networks (GAT), and Dynamic Spatio-Temporal GCN (DSTGCN), to classify crash severity and predict high-risk regions. Our proposed ST-GraphNet, which utilizes a DSTGCN backbone on the coarse-grained H3 graph, achieves a test accuracy of 97.74%, substantially outperforming the best fine-grained model (64.7% test accuracy). These findings highlight the effectiveness of spatial aggregation, dynamic message passing, and multi-modal feature integration in capturing the complex spatio-temporal patterns underlying AV crash severity.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 8 of its 49 references that are in the map. First posted on arXiv 9 Jun 2025.
Builds on
8 of 49 references.
References · 8
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
- 2015Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcastingcited by 1,436
- 2023NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classificationcited by 210
- 2023PDFormer: Propagation Delay-Aware Dynamic Long-Range Transformer for Traffic Flow Predictioncited by 137
- 2023Uncertainty-Aware Probabilistic Graph Neural Networks for Road-Level Traffic Accident Predictioncited by 8
- 2023MSGNN: Multi-scale Spatio-temporal Graph Neural Network for Epidemic Forecastingcited by 6
- 2021A Secure Sensor Fusion Framework for Connected and Automated Vehicles under Sensor Attackscited by 4
- 2024SST-GCN: The Sequential based Spatio-Temporal Graph Convolutional networks for Minute-level and Road-level Traffic Accident Risk Predictioncited by 2
Built on by
Citing papers per year: 2025: 2.
2 papers.