Abstract
Air quality is a critical issue for populations living in large cities with developed transportation infrastructures. Transport makes a significant contribution to air pollution, and in the era of rapid technological development, the application of intelligent transportation systems, and the advancement of smart cities, the problem of air quality remains acute. Oversaturated traffic flows are difficult to describe using mathematical models and apply effective management strategies. However, models based on the use of artificial neural networks can provide a solution. This paper proposes a strategy for air quality monitoring using a deeply trained neural network, which takes into account real-time parameters of traffic flow and meteorological conditions. This strategy has been successfully implemented in the city of Chelyabinsk, and the calculated data is correlated with data obtained from mobile laboratories at four stations located on one of the central streets of the city.