Architecting Digital Twins for Intelligent Transportation Systems

2025-02-24

AI Summary

To address challenges in intelligent transportation systems—including real-time traffic control difficulties, low prediction accuracy, and delayed model updates—this paper proposes DigIT, a digital twin platform. Methodologically, DigIT features: (1) a modular, extensible system architecture grounded in a domain conceptual model (DCM); (2) the first digital twin closed loop integrating adaptive MLOps, enabling automated deployment and continuous iteration of traffic forecasting models; and (3) seamless integration of multi-source data fusion, spatiotemporal graph convolutional networks (STGCN)-based time-series forecasting, and lightweight real-time simulation. Experimental evaluation on large-scale road networks demonstrates that DigIT reduces mean absolute error (MAE) in traffic flow prediction by 23%, achieves end-to-end response latency under 300 ms, and significantly improves computational efficiency and system scalability.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Application Domains: Transportation
• Machine Learning: Time-Series/Data Streams

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Modern transportation systems face growing challenges in managing traffic flow, ensuring safety, and maintaining operational efficiency amid dynamic traffic patterns. Addressing these challenges requires intelligent solutions capable of real-time monitoring, predictive analytics, and adaptive control. This paper proposes an architecture for DigIT, a Digital Twin (DT) platform for Intelligent Transportation Systems (ITS), designed to overcome the limitations of existing frameworks by offering a modular and scalable solution for traffic management. Built on a Domain Concept Model (DCM), the architecture systematically models key ITS components enabling seamless integration of predictive modeling and simulations. The architecture leverages machine learning models to forecast traffic patterns based on historical and real-time data. To adapt to evolving traffic patterns, the architecture incorporates adaptive Machine Learning Operations (MLOps), automating the deployment and lifecycle management of predictive models. Evaluation results highlight the effectiveness of the architecture in delivering accurate predictions and computational efficiency.

Problem

• Intelligent traffic management solutions
• Real-time monitoring and predictive analytics
• Adaptive control for dynamic traffic patterns

Innovation

• Digital Twin platform
• Machine Learning Operations
• Predictive traffic modeling