EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Interpretable long-term traffic modelling on national road networks using theory-informed deep learning

Yue Li, Shujuan Chen, Akihiro Shimoda, Ying Jin

Transportation Research Part C: Emerging Technologies · 2027-01 · 194 · 106102

DOI: 10.1016/j.trc.2026.106102 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Transportation Research Part C: Emerging Technologies, 2027-01. Verfasst von Yue Li und 3 weiteren Autor:innen. Die Arbeit nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Cambridge Commonwealth European and International Trust.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Long-term traffic modelling is fundamental to transport planning, but existing approaches often trade off interpretability, transferability, and predictive accuracy. Classical travel demand models provide behavioural structure but rely on strong assumptions and extensive calibration, whereas generic deep learning models capture complex patterns but often lack theoretical grounding and spatial transferability, limiting their usefulness for long-term planning applications. We propose DeepDemand, a theory-informed deep learning framework that embeds key components of travel demand theory to predict long-term highway traffic volumes using external socioeconomic features and road-network structure. The framework integrates a competitive two-source Dijkstra procedure for local origin-destination (OD) region extraction and OD pair screening with a differentiable architecture modelling OD interactions and travel-time deterrence. The model is evaluated using eight years (2017-2024) of observations on the UK strategic road network, covering 5088 highway segments. Under random cross-validation, DeepDemand achieves an R2 of 0.718 and an MAE of 7406 vehicles, outperforming linear, ridge, random forest, and gravity-style baselines. Performance remains strong under spatial cross-validation (R2 = 0.665), indicating good geographic transferability. Interpretability analysis reveals a stable nonlinear travel-time deterrence pattern, key socioeconomic drivers of demand, and polycentric OD interaction structures aligned with major employment centres and transport hubs. These results highlight the value of integrating transport theory with deep learning for interpretable highway traffic modelling and practical planning applications.

Förderung

  • Cambridge Commonwealth European and International Trust

Zitieren

APA

Li, Y., Chen, S., Shimoda, A., & Jin, Y. (2027). Interpretable long-term traffic modelling on national road networks using theory-informed deep learning. Transportation Research Part C: Emerging Technologies, 194, 106102. https://doi.org/10.1016/j.trc.2026.106102

Vancouver

Li Y, Chen S, Shimoda A, Jin Y. Interpretable long-term traffic modelling on national road networks using theory-informed deep learning. Transportation Research Part C: Emerging Technologies. 2027;194:106102. doi:10.1016/j.trc.2026.106102

BibTeX
@article{Li2027,
  author = {Li, Yue and Chen, Shujuan and Shimoda, Akihiro and Jin, Ying},
  title = {Interpretable long-term traffic modelling on national road networks using theory-informed deep learning},
  journal = {Transportation Research Part C: Emerging Technologies},
  year = {2027},
  volume = {194},
  pages = {106102},
  doi = {10.1016/j.trc.2026.106102}
}
Kostenlos starten →