EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Research on expressway traffic accident risk prediction method considering Spatio-Temporal effects

Liang Zhao, Duo Liu, Han Bai, Tianzheng Wei iD, Jian Lu, Xiuguang Wang

PLOS One · 2026

DOI: 10.1371/journal.pone.0360312 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, 2026. Verfasst von Liang Zhao und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Transportation and Logistics Engineering, Shandong Jiaotong University, Jinan, China. Hauptthemen laut MEDLINE: Accidents, Traffic. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Shandong Provincial Natural Science Foundation project, Innovative Team Pro-ject of Ji’nan Government.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Accidents, TrafficHumansLong Short Term MemoryPrediction AlgorithmsSpatio-Temporal AnalysisPredictive Learning ModelsConvolutional Neural NetworksDeep Learning

Autor:innen und Institutionen

  • School of Transportation and Logistics Engineering, Shandong Jiaotong University, Jinan, China.
  • Shandong Zhengqu Traffic Engineering Co., Ltd, Jinan, China.

ORCID-Profile: Tianzheng Wei

Förderung

  • Shandong Provincial Natural Science Foundation project
  • Innovative Team Pro-ject of Ji’nan Government

Zitieren

APA

Zhao, L., Liu, D., Bai, H., Wei, T., Lu, J., & Wang, X. (2026). Research on expressway traffic accident risk prediction method considering Spatio-Temporal effects. PLOS One. https://doi.org/10.1371/journal.pone.0360312

Vancouver

Zhao L, Liu D, Bai H, Wei T, Lu J, Wang X. Research on expressway traffic accident risk prediction method considering Spatio-Temporal effects. PLOS One. 2026. doi:10.1371/journal.pone.0360312

BibTeX
@article{Zhao2026,
  author = {Zhao, Liang and Liu, Duo and Bai, Han and Wei, Tianzheng and Lu, Jian and Wang, Xiuguang},
  title = {Research on expressway traffic accident risk prediction method considering Spatio-Temporal effects},
  journal = {PLOS One},
  year = {2026},
  doi = {10.1371/journal.pone.0360312}
}
Kostenlos starten →