University Of Tehran Press Pollution 2383-451X 12 1 2026 01 01 Integrating Satellite Data and Artificial Intelligence for Air Quality Prediction and Mitigation Strategies: A Case Study of Tehran 58 70 105138 10.22059/poll.2025.393453.2885 EN Mohammad Amin Javadi K. N. Toosi University of Technology, Civil and Environmental Engineering Department, Tehran, Iran Armin Mollaei Rudsary Department of Civil and Environmental Engineering, Sharif University of Technology, Tehran, Iran Zahra Amiri Department of Mechanical and Industrial Engineering, University of Toronto, Toronto, Ontario, Canada Maryam Zare Shahne Department of Civil and Environmental Engineering, K.N. Toosi University of Technology, Tehran, Iran Zahra Barzegar Director of Environmental Studies, Tehran Urban Research and Planning Centre (TURPC), Tehran 1964635611, Iran Naghmeh Mobarghaee Dinan Department of Environmental Planning and Design, Environmental Sciences Research Institute, Shahid Beheshti University, Tehran, Iran Journal Article 2025 04 14 Air pollution is a critical challenge in urban centers like Tehran, where over 8 million residents are exposed to pollutants from transportation, industry, and energy use. To address this, researchers combine satellite observations (e.g., Sentinel-5P) with AI models to monitor and predict concentrations of pollutants such as PM2.5, PM10, O3 and NO2. By integrating remote sensing data with ground measurements, machine learning methods—including neural networks, decision trees, and regression models—establish links between meteorological conditions and pollution levels. This hybrid approach overcomes the limitations of traditional monitoring systems while benefiting from tools like Google Earth Engine for efficient analysis of Tehran’s air quality (2019–2024). The resulting forecasts provide policymakers with actionable insights for pollution control, urban planning, and public health strategies. https://jpoll.ut.ac.ir/article_105138_cbc8097bed809915da9108811d83b46d.pdf