Research on expressway traffic accident risk prediction method considering Spatio-Temporal effects
- 1School of Transportation and Logistics Engineering, Shandong Jiaotong University, Jinan, China.
- 2Shandong Zhengqu Traffic Engineering Co., Ltd, Jinan, China.
Abstract
Traffic accidents arise from the dynamic evolution of traffic flow under spatio-temporal effects, and their occurrence and severity are significantly influenced by temporal and spatial variations in traffic conditions. Traditional studies predominantly rely on static accident-time data, which limits prediction accuracy. To address this gap, this study proposes a deep learning framework that integrates data preprocessing, spatio-temporal effect analysis, PCA-FCM-based risk labeling, and a CNN-BiLSTM hybrid model. Compared with CNN-LSTM, the proposed model replaces unidirectional LSTM with bidirectional LSTM to capture both forward and backward temporal dependencies. Based on the HighD naturalistic trajectory dataset, the CNN-BiLSTM model achieves an MSE of 0.362, RMSE of 0.601, MAE of 0.197 and MAPE of 0.044, outperforming LSTM, BiLSTM and CNN-LSTM with moderate running time. In accident risk classification, it reaches an overall accuracy of 90%, with class-level precision of 0.90–0.93 and F1 scores of 0.82–0.96. The results demonstrate that the proposed method effectively captures spatio-temporal dynamic characteristics and provides an efficient tool for expressway accident risk prediction.
Related
- Modeling dependent degradation data considering inherent causal relationships for reliability analysis and remaining useful life prediction
- A novel soil-water characteristic curve prediction model for unsaturated soil considering pore structure characteristics
- Machine Learning Prediction of Wind Turbine Blade Icing Considering Class Imbalance
- Translation of Black-Box Clinical Prediction Models into Standalone Transparent Nomograms: Temporal External Validation in Heart Transplantation
- Borrowing Space, Clustering Temporal Dynamics: Bayesian Regime Mapping and Spatial Prediction for European PM10
BibTeX
@article{zhao2026research,
title = {{Research on expressway traffic accident risk prediction method considering Spatio-Temporal effects}},
author = {Liang Zhao and Duo Liu and Han Bai and Tianzheng Wei and Jian Lu and Xiuguang Wang},
journal = {PLOS One},
year = {2026},
month = oct,
doi = {10.1371/journal.pone.0360312},
url = {https://doi.org/10.1371/journal.pone.0360312},
note = {CC BY},
}
RIS
TY - JOUR
TI - Research on expressway traffic accident risk prediction method considering Spatio-Temporal effects
AU - Liang Zhao
AU - Duo Liu
AU - Han Bai
AU - Tianzheng Wei
AU - Jian Lu
AU - Xiuguang Wang
PY - 2026
DA - 2026/10/23
JO - PLOS One
DO - 10.1371/journal.pone.0360312
UR - https://doi.org/10.1371/journal.pone.0360312
AB - Traffic accidents arise from the dynamic evolution of traffic flow under spatio-temporal effects, and their occurrence and severity are significantly influenced by temporal and spatial variations in traffic conditions. Traditional studies predominantly rely on static accident-time data, which limits prediction accuracy. To address this gap, this study proposes a deep learning framework that integrates data preprocessing, spatio-temporal effect analysis, PCA-FCM-based risk labeling, and a CNN-BiLSTM hybrid model. Compared with CNN-LSTM, the proposed model replaces unidirectional LSTM with bidirectional LSTM to capture both forward and backward temporal dependencies. Based on the HighD naturalistic trajectory dataset, the CNN-BiLSTM model achieves an MSE of 0.362, RMSE of 0.601, MAE of 0.197 and MAPE of 0.044, outperforming LSTM, BiLSTM and CNN-LSTM with moderate running time. In accident risk classification, it reaches an overall accuracy of 90%, with class-level precision of 0.90–0.93 and F1 scores of 0.82–0.96. The results demonstrate that the proposed method effectively captures spatio-temporal dynamic characteristics and provides an efficient tool for expressway accident risk prediction.
SN - 1932-6203
ER -