A Hybrid ML-Digital Twin Approach for Urban Traffic Optimization

Urban traffic congestion is a critical challenge facing modern cities worldwide. As urban populations grow, the increasing stress on transportation infrastructure leads to extended journey durations, increased gasoline usage, and heightened environmental contamination, and a diminished quality of life for city dwellers. Traditional traffic management systems have limited ability to handle these issues and often struggle to keep pace with the dynamic and complex nature of urban traffic patterns. To address this problem, this study demonstrates a hybrid system that integrates machine learning (ML) algorithms with digital twin technology. The proposed work is evaluated using four ML models and two statistical parameters: Mean Squared Error (MSE) and coefficient of determination (R²). This approach main aim is to provide a more efficient and adaptive solution to urban traffic optimization, potentially revolutionizing how cities manage their transportation networks.