smart urban management for cleaner air: a data-driven approach to sustainable transportation in tehran

Given the environmental challenges of tehran, particularly air pollution, this study aims to predict air quality indices based on urban data. the dataset includes traffic density, gps-based public transport routes, and traffic light schedules for the year 1402 (2023–2024). a random forest regression model was implemented to analyze the relationships between these variables and air pollutants (pm2.5, no2, co). results indicate that traffic density and traffic light scheduling have the most significant impact on air quality. the model achieved an r² of 0.81 and a mean absolute error (mae) of 6.2 aqi units, demonstrating strong predictive performance. these findings highlight the potential of intelligent urban management in reducing air pollution and achieving green cities.