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

TL;DR

DeepDemand is a theory-informed deep learning framework that predicts long-term highway traffic volumes with high accuracy and interpretability, integrating transport theory with neural networks.

Contribution

It introduces a novel deep learning model embedding travel demand theory components, improving interpretability and transferability in long-term traffic prediction.

Findings

Achieves R2 of 0.718 on UK data, outperforming baselines.

Maintains strong performance with R2 of 0.665 under spatial cross-validation.

Reveals stable travel-time deterrence and socioeconomic demand drivers.

Abstract

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.