Generative AI-based Crash Data Augmentation for Enhancing Crash Frequency Modeling

Jinjun Chen*, Qijie He*, Peng Liu, Wanjing Ma, Nan Zheng, Peng Liu, Ziyuan Pu† (* Equal contribution, † Corresponding author)

Overview

Crash frequency modeling is essential for identifying high-risk road segments and improving traffic safety. However, crash datasets are often plagued by excessive zero observations — most road segments record zero crashes — which undermines model accuracy.

Existing approaches (statistical models, resampling techniques) are limited by strict distributional assumptions or fail to handle the multi-type nature of crash data (count, ordinal, nominal, and real-valued variables). This project proposes a data-driven approach using TabSyn, a hybrid VAE-Diffusion generative neural network, to augment crash data while preserving inter-variable correlations.

Approach

• Transformed multi-type crash variables into a unified continuous latent space through a tokenizer-based embedding and VAE encoding.
• Applied a Diffusion model in the latent space to generate high-fidelity synthetic crash records.
• Integrated the augmented data with XGBoost for crash frequency prediction.
• Compared against state-of-the-art generative models (CTGAN, TVAE, GReaT, StaSy) and statistical baselines (ZIP, GAM-Poisson).

Key Findings

• TabSyn achieved the best distributional and structural fidelity among all benchmark generative models.
• The proposed framework achieved the lowest prediction error, particularly for Top-K high-risk segment identification.
• Results demonstrate that deep generative augmentation significantly outperforms traditional resampling and statistical methods for imbalanced crash data.

Presentation

Related Publications

Chen J*, He Q*, Liu P, Ma W, Zheng N, Liu P, Pu Z†. (2026) “Traffic Crash Data Augmentation with Multi-type Variables using Hybrid VAE-Diffusion Generative Neural Networks for Enhancing Crash Frequency Modeling.” Accident Analysis and Prevention, 231: 108508. Link

He Q, Chen J, Liu P, Ma W, Pu Z†. (2025) “Enhancing Crash Frequency Modeling with Mixed-Type Data Using a Hybrid VAE-Diffusion-Based Generative Approach.” Poster, TRB 104th Annual Meeting, Washington, D.C. (Paper No. TRBAM-25-06171)

Citation

@article{chen2026traffic,
  title   = {Traffic Crash Data Augmentation with Multi-type Variables using Hybrid {VAE-Diffusion} Generative Neural Networks for Enhancing Crash Frequency Modeling},
  author  = {Chen, Jinjun and He, Qijie and Liu, Peng and Ma, Wanjing and Zheng, Nan and Liu, Peng and Pu, Ziyuan},
  journal = {Accident Analysis {\&} Prevention},
  volume  = {231},
  pages   = {108508},
  year    = {2026},
  doi     = {10.1016/j.aap.2026.108508}
}