Learning Multimodal Embeddings for Traffic Accident Prediction and Causal Estimation

• URL: http://arxiv.org/abs/2512.02920v1
• Date: Tue, 02 Dec 2025 16:39:32 GMT
• Title: Learning Multimodal Embeddings for Traffic Accident Prediction and Causal Estimation
• Authors: Ziniu Zhang, Minxuan Duan, Haris N. Koutsopoulos, Hongyang R. Zhang,
• Abstract summary: We consider analyzing traffic accident patterns using both road network data and satellite images aligned to road graph nodes.<n>We construct a large multimodal dataset across six U.S. states, containing nine million traffic accident records from official sources.<n>We find that accident rates rise by $24%$ under higher precipitation, by $22%$ on higher-speed roads such as motorways, and by $29%$ due to seasonal patterns.
• Score: 15.119440099674918
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We consider analyzing traffic accident patterns using both road network data and satellite images aligned to road graph nodes. Previous work for predicting accident occurrences relies primarily on road network structural features while overlooking physical and environmental information from the road surface and its surroundings. In this work, we construct a large multimodal dataset across six U.S. states, containing nine million traffic accident records from official sources, and one million high-resolution satellite images for each node of the road network. Additionally, every node is annotated with features such as the region's weather statistics and road type (e.g., residential vs. motorway), and each edge is annotated with traffic volume information (i.e., Average Annual Daily Traffic). Utilizing this dataset, we conduct a comprehensive evaluation of multimodal learning methods that integrate both visual and network embeddings. Our findings show that integrating both data modalities improves prediction accuracy, achieving an average AUROC of $90.1\%$, which is a $3.7\%$ gain over graph neural network models that only utilize graph structures. With the improved embeddings, we conduct a causal analysis based on a matching estimator to estimate the key contributing factors influencing traffic accidents. We find that accident rates rise by $24\%$ under higher precipitation, by $22\%$ on higher-speed roads such as motorways, and by $29\%$ due to seasonal patterns, after adjusting for other confounding factors. Ablation studies confirm that satellite imagery features are essential for achieving accurate prediction.

Related papers

• Learning Traffic Anomalies from Generative Models on Real-Time Observations [49.1574468325115]
  We use the Spatiotemporal Generative Adversarial Network (STGAN) framework to capture complex spatial and temporal dependencies in traffic data.<n>We apply STGAN to real-time, minute-by-minute observations from 42 traffic cameras across Gothenburg, Sweden, collected over several months in 2020.<n>Our results demonstrate that the model effectively detects traffic anomalies with high precision and low false positive rates.
  arXiv  Detail & Related papers  (2025-02-03T14:23:23Z)
• Multi-Source Urban Traffic Flow Forecasting with Drone and Loop Detector Data [61.9426776237409]
  Drone-captured data can create an accurate multi-sensor mobility observatory for large-scale urban networks.<n>A simple yet effective graph-based model HiMSNet is proposed to integrate multiple data modalities and learn-temporal correlations.
  arXiv  Detail & Related papers  (2025-01-07T03:23:28Z)
• A Multi-Loss Strategy for Vehicle Trajectory Prediction: Combining Off-Road, Diversity, and Directional Consistency Losses [68.68514648185828]
  Trajectory prediction is essential for the safety and efficiency of planning in autonomous vehicles.<n>Current models often fail to fully capture complex traffic rules and the complete range of potential vehicle movements.<n>This study introduces three novel loss functions: Offroad Loss, Direction Consistency Error, and Diversity Loss.
  arXiv  Detail & Related papers  (2024-11-29T14:47:08Z)
• XTraffic: A Dataset Where Traffic Meets Incidents with Explainability and More [38.092415845567345]
  Research has been conducted on two highly correlated tracks: traffic and incidents. XTraffic dataset includes traffic, i.e., time-series indexes on traffic flow, lane occupancy, and average vehicle speed. Each node includes detailed physical policy-level meta-attributes of lanes.
  arXiv  Detail & Related papers  (2024-07-16T08:16:01Z)
• Leveraging Driver Field-of-View for Multimodal Ego-Trajectory Prediction [69.29802752614677]
  RouteFormer is a novel ego-trajectory prediction network combining GPS data, environmental context, and the driver's field-of-view.<n>To tackle data scarcity and enhance diversity, we introduce GEM, a dataset of urban driving scenarios enriched with synchronized driver field-of-view and gaze data.
  arXiv  Detail & Related papers  (2023-12-13T23:06:30Z)
• Graph Neural Networks for Road Safety Modeling: Datasets and Evaluations for Accident Analysis [23.09889357482818]
  This paper constructs a large-scale dataset of traffic accident records from official reports of various states in the US.<n>Using this new dataset, we evaluate existing deep-learning methods for predicting the occurrence of accidents on road networks.<n>Our main finding is that graph neural networks such as GraphSAGE can accurately predict the number of accidents on roads with less than 22% mean absolute error.
  arXiv  Detail & Related papers  (2023-10-31T21:43:10Z)
• TAP: A Comprehensive Data Repository for Traffic Accident Prediction in Road Networks [36.975060335456035]
  Existing machine learning approaches tend to focus on predicting traffic accidents in isolation. To incorporate graph structure information, Graph Neural Networks (GNNs) can be naturally applied. Applying GNNs to the accident prediction problem faces challenges due to the lack of suitable graph-structured traffic accident datasets.
  arXiv  Detail & Related papers  (2023-04-17T22:18:58Z)
• A Graph and Attentive Multi-Path Convolutional Network for Traffic Prediction [16.28015945020806]
  We propose a graph and attentive multi-path convolutional network (GAMCN) model to predict traffic conditions into the future. Our model focuses on the spatial and temporal factors that impact traffic conditions. Our model outperforms state-of-art traffic prediction models by up to 18.9% in terms of prediction errors and 23.4% in terms of prediction efficiency.
  arXiv  Detail & Related papers  (2022-05-30T16:24:43Z)
• Road Network Guided Fine-Grained Urban Traffic Flow Inference [108.64631590347352]
  Accurate inference of fine-grained traffic flow from coarse-grained one is an emerging yet crucial problem. We propose a novel Road-Aware Traffic Flow Magnifier (RATFM) that exploits the prior knowledge of road networks. Our method can generate high-quality fine-grained traffic flow maps.
  arXiv  Detail & Related papers  (2021-09-29T07:51:49Z)
• Risk Prediction on Traffic Accidents using a Compact Neural Model for Multimodal Information Fusion over Urban Big Data [4.467592626294754]
  Predicting risk map of traffic accidents is vital for accident prevention and early planning of emergency response. Here, the challenge lies in the multimodal nature of urban big data. We propose a compact neural ensemble model to fusing in multimodal features and develop some new features such as fractal road complexity measure in satellite images, taxifitting flows, POIs, and road width and connectivity in OpenStreetMap. The solution is more promising in performance than the baseline methods and the single-modality data based solutions.
  arXiv  Detail & Related papers  (2021-02-21T08:21:19Z)
• A Graph Convolutional Network with Signal Phasing Information for Arterial Traffic Prediction [63.470149585093665]
  arterial traffic prediction plays a crucial role in the development of modern intelligent transportation systems. Many existing studies on arterial traffic prediction only consider temporal measurements of flow and occupancy from loop sensors and neglect the rich spatial relationships between upstream and downstream detectors. We fill this gap by enhancing a deep learning approach, Diffusion Convolutional Recurrent Neural Network, with spatial information generated from signal timing plans at targeted intersections.
  arXiv  Detail & Related papers  (2020-12-25T01:40:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.