Real-Time Modeling of Traffic Flow and Emissions for Enhancing Urban Air Quality

Reducing emissions intensity associated with road traffic is of paramount importance and requires careful investigation to improve air quality. Various models are employed to assess air pollution, providing quantitative evaluations to optimize traffic management. Intelligent driver models account for the human factor to represent real-world behavior. Real-time modeling using video surveillance cameras enables precise monitoring of traffic flows. Neural networks process high-speed data for comprehensive analysis of traffic movement and emission levels. This study focuses on modeling traffic flows with different vehicle categories approaching regulated intersections and calculates emissions of CO, NOx, PM2.5, and PM10. The model results demonstrate good correlation with laboratory measurements. The methodology enables effective implementation of measures within intelligent transportation systems, combating congestion, and improving urban air quality.