TGDT: A Temporal Graph-based Digital Twin for Urban Traffic Corridors

2025-04-25

AI Summary

Urban signalized intersections suffer from traffic congestion, causing excessive delays, elevated emissions, and economic losses; however, existing deep learning models exhibit poor generalizability, high architectural complexity, and limited suitability for real-time deployment. Method: This paper proposes a temporal graph-structured digital twin framework tailored for traffic corridors. It innovatively integrates lightweight Temporal Convolutional Networks (TCNs) with attention-enhanced Graph Neural Networks (GNNs), forming a modular and scalable architecture capable of modeling intersections of arbitrary scale. The framework achieves real-time, direction-aware, robust, and high-accuracy prediction of multiple key metrics—including queue length and travel time—using minimal input features. Contribution/Results: The method ensures interpretability and low deployment overhead, completing parallel simulation across thousands of scenarios in seconds. Under extreme conditions, it significantly outperforms state-of-the-art models.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Machine Learning: Deep Neural Architectures and Foundation Models
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Urban congestion at signalized intersections leads to significant delays, economic losses, and increased emissions. Existing deep learning models often lack spatial generalizability, rely on complex architectures, and struggle with real-time deployment. To address these limitations, we propose the Temporal Graph-based Digital Twin (TGDT), a scalable framework that integrates Temporal Convolutional Networks and Attentional Graph Neural Networks for dynamic, direction-aware traffic modeling and assessment at urban corridors. TGDT estimates key Measures of Effectiveness (MOEs) for traffic flow optimization at both the intersection level (e.g., queue length, waiting time) and the corridor level (e.g., traffic volume, travel time). Its modular architecture and sequential optimization scheme enable easy extension to any number of intersections and MOEs. The model outperforms state-of-the-art baselines by accurately producing high-dimensional, concurrent multi-output estimates. It also demonstrates high robustness and accuracy across diverse traffic conditions, including extreme scenarios, while relying on only a minimal set of traffic features. Fully parallelized, TGDT can simulate over a thousand scenarios within a matter of seconds, offering a cost-effective, interpretable, and real-time solution for traffic signal optimization.

Problem

• Urban congestion causes delays, economic losses, and emissions
• Existing models lack generalizability and real-time deployment capability
• Proposing a scalable digital twin for dynamic traffic modeling

Innovation

• Integrates Temporal Convolutional and Attentional Graph Networks
• Modular architecture for scalable intersection and corridor modeling
• Fully parallelized for real-time multi-scenario simulation