用交通理论指导深度学习，提升高速公路长期流量预测的可解释性与泛化能力。
Interpretable long-term traffic modelling on national road networks using theory-informed deep learning
- 融合交通需求理论与可微分架构，建模出行源地-目的地关系与出行时间衰减效应。
- 在英国主干道网络上实现R2=0.718、MAE=7406辆的预测性能，优于多种基线模型。
- 揭示了就业中心驱动的多中心出行结构和非线性时间衰减规律，适合交通规划决策者使用。
长期交通建模对交通规划至关重要，但现有方法常在可解释性、可迁移性和预测精度间权衡。经典出行需求模型具备行为结构，但依赖强假设且需大量校准；通用深度学习模型能捕捉复杂模式，却缺乏理论基础和空间可迁移性，限制其在长期规划中的应用。本文提出DeepDemand，一种融入交通需求理论的深度学习框架，利用外部社会经济特征与路网结构预测长期高速公路交通量。该框架结合竞争性双源Dijkstra算法提取局部起讫点（OD）区域与筛选OD对，并采用可微分架构建模OD相互作用与出行时间衰减效应。在覆盖5088个高速公路路段、长达八年的英国战略公路网数据上评估，随机交叉验证下取得R2=0.718、MAE=7406辆的成绩，优于线性、岭回归、随机森林及重力模型等基线。空间交叉验证下仍保持R2=0.665，表明良好地理可迁移性。可解释性分析揭示稳定的非线性出行时间衰减模式、关键社会经济驱动因素以及与主要就业中心和交通枢纽一致的多中心OD交互结构。结果凸显将交通理论与深度学习结合在可解释高速公路建模与实际规划中的价值。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。