EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Traffic condition prediction for highway within work zones under dynamic traffic organization changes

Feiping Xu, Bohan Liu iD, Hang Liu, Yonghao Wang, Jundong Wang, Chengcheng Wang

PLOS One · 18.06.2026 · 21 (6) · e0351729

DOI: 10.1371/journal.pone.0351729 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 18.06.2026. Verfasst von Feiping Xu und 5 weiteren Autor:innen. Beteiligte Einrichtung: Shandong Hi-Speed Company Limited, Jinan, China. Hauptthemen laut MEDLINE: Transportation. Die Arbeit nennt 20 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Research on Key Technologies for Traffic Organization and Safety Assurance Improvement in High Speed Reconstruction and Expansion.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In the context of sustainable transportation development, reducing carbon emissions, energy waste, and noise pollution caused by traffic congestion has become an urgent task for achieving environmental and social sustainability. The key to this goal lies in mitigating and preventing traffic congestion, for which high accuracy traffic condition prediction models serve as essential tools. During the reconstruction and expansion of highways and urban arterial roads, frequent adjustments to traffic organization and changes in geometric alignment introduce dynamic and uncertain characteristics into the traffic system. Existing methods struggle to accurately predict traffic conditions in the modified sections. To address this challenge, this study proposes a Dynamic Bayesian Graph Convolutional Neural Network (DBGCN). The model incorporates road geometric parameters and dynamic traffic organization changes as key inputs. It employs a Dynamic Bayesian Network (DBN) to model multi-source dynamic information and infer a dynamic adjacency matrix that reflects latent spatiotemporal dependencies between nodes. This dynamic adjacency matrix is then input into a Graph Convolutional Network (GCN), which fuses spatiotemporal features with traffic flow data to achieve accurate traffic conditions prediction for upgraded sections. Validation on the Wuxuan highway demonstrates that the proposed method outperforms benchmark models in traffic conditions prediction accuracy and produces traffic conditions propagation diagrams with high interpretability.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

TransportationHumansBayes TheoremGraph Neural NetworksModels, TheoreticalPrediction AlgorithmsAir PollutionNoise

Autor:innen und Institutionen

  • Shandong Hi-Speed Company Limited, Jinan, China.
  • Beijing Key Laboratory of Traffic Engineering, College of Metropolitan Transportation, Beijing University of Technology, Beijing, China.
  • Shandong Provincial Communications Planning and Design Institute Group Co., Ltd, Jinan, China.
  • Shandong Hi-speed Group Innovation Research Institute, Jinan, China.
  • State Key Lab of Intelligent Transportation System, Jinan, China.
  • Central South University School of Traffic & Transportation Engineering, Changsha, China.

ORCID-Profile: Bohan Liu

Förderung

  • Research on Key Technologies for Traffic Organization and Safety Assurance Improvement in High Speed Reconstruction and Expansion

Zitieren

APA

Xu, F., Liu, B., Liu, H., Wang, Y., Wang, J., & Wang, C. (2026). Traffic condition prediction for highway within work zones under dynamic traffic organization changes. PLOS One, 21(6), e0351729. https://doi.org/10.1371/journal.pone.0351729

Vancouver

Xu F, Liu B, Liu H, Wang Y, Wang J, Wang C. Traffic condition prediction for highway within work zones under dynamic traffic organization changes. PLOS One. 2026;21(6):e0351729. doi:10.1371/journal.pone.0351729

BibTeX
@article{Xu2026,
  author = {Xu, Feiping and Liu, Bohan and Liu, Hang and Wang, Yonghao and Wang, Jundong and Wang, Chengcheng},
  title = {Traffic condition prediction for highway within work zones under dynamic traffic organization changes},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {6},
  pages = {e0351729},
  doi = {10.1371/journal.pone.0351729}
}
Kostenlos starten →