From Reactive to Proactive: Can AI Digital Twins Transform Traffic Management?

Urban traffic systems are becoming increasingly complex, making it harder for transportation agencies to quickly spot and respond to problems. Many current traffic management approaches rely on limited data and respond only after issues occur, which can delay responses to events such as lane closures or signal failures. To address this issue, new Mineta Transportation Institute (MTI) research, SMART-TWIN: Systematic Modeling and Real-Time Transportation with Digital Twins, introduces SMART-TWIN, an Artificial Intelligence (AI)-driven Digital Twin framework designed to model, analyze, and predict traffic conditions in real time.

By combining detailed traffic modeling, simulated travel patterns, and machine learning, the SMART-TWIN can detect disruptions early. The framework can quantify the impacts of these disruptions into usable metrics on congestion, delay, and user cost. 

The framework was demonstrated through a corridor-scale Digital Twin of the Shaw–Cedar intersection in Fresno, California. From this, the study’s author found that:

• Traffic disruptions examined led to disproportionately large increases in congestion and delay, demonstrating the importance of early detection.

• The model achieved near-perfect accuracy (~99.9%) in identifying traffic conditions, including lane closures and signal failures.

• Disruptions such as signal failures were detected within one analysis interval (i.e., 10 minutes), enabling proactive intervention before severe congestion develops.

• The system successfully translated traffic conditions into measurable impacts, including queue buildup, delay, and user cost, providing actionable insights for traffic management, demonstrating its potential as a scalable framework.

“A transportation Digital Twin is a virtual representation of physical infrastructure and traffic processes that integrates data, simulation, and analytics to monitor system conditions and evaluate operational strategies,” explains the study’s author, Dr. Hovannes Kulhandjian. “Recent large-scale initiatives have demonstrated the feasibility of city-scale Digital Twin environments, such as the Virtual Singapore project. However, many existing implementations emphasize visualization or offline scenario analysis. They often lack tight integration between microscopic simulation, machine learning–based state inference, and interpretable performance metrics that directly support operational and infrastructure decisions.”

Overall, the results of this project indicate that AI-enabled Digital Twins provide a practical and scalable foundation for next-generation transportation systems, enabling proactive operations, improved system reliability, and data-driven infrastructure decision-making. Future applications of SMART-TWIN-like frameworks could support smarter traffic management, more resilient infrastructure, and safer, more efficient transportation networks as cities continue to grow.

ABOUT THE MINETA TRANSPORTATION INSTITUTE

At the Mineta Transportation Institute (MTI) at San Jose State University (SJSU) our mission is to increase mobility for all by improving the safety, efficiency, accessibility, and convenience of our nations’ transportation system. Through research, education, workforce development and technology transfer, we help create a connected world. Founded in 1991, MTI is a university transportation center funded by the US Department of Transportation, the California Department of Transportation, and public and private grants, including those made available by the Road Repair and Accountability Act of 2017 (SB1). MTI is affiliated with SJSU’s Lucas College and Graduate School of Business.

ABOUT THE AUTHORS

Dr. Hovannes Kulhandjian is a tenured full Professor in the Department of Electrical and Computer Engineering at California State University, Fresno. 

Media Contact: