Document Type : Original Research Paper
Authors
1
Department of Civil and Environmental Engineering, K.N. Toosi University of Technology
2
Department of Civil and Environmental Engineering, K.N. Toosi University of Technology, Tehran, Iran
3
Department of Environmental Engineering, Sharif University of Technology, Tehran, Iran
4
Department of Mechanical and Industrial Engineering, University of Toronto, Toronto, Ontario, Canada
5
Director of Environmental Studies, Tehran Urban Research and Planning Centre (TURPC), Tehran 1964635611, Iran
6
Department of Environmental Planning and Design, Environmental Sciences Research Institute, Shahid Beheshti University, Tehran, Iran
10.22059/poll.2025.393453.2885
Abstract
Air pollution has become one of the most pressing environmental challenges in urban areas, particularly in densely populated and industrialized cities like Tehran. As a vibrant capital with over 8 million residents, Tehran faces significant air quality issues driven by transportation, industries, fossil fuel consumption, urban activities, and energy usage, all of which have detrimental impacts on human health and the environment. To address this complex issue, scientists employ a combination of satellite data, such as Sentinel-5P observations, and advanced artificial intelligence (AI) modeling to analyze and predict air pollutant concentrations, including particulate matter (PM2.5, PM10), ozone (O3), nitrogen dioxide (NO2), sulfur dioxide (SO2), and carbon monoxide (CO). By integrating satellite data with ground-based measurements, hybrid models are developed using machine learning algorithms such as neural networks, decision trees, and regression models, establishing correlations between meteorological variables and pollutant levels. These methods address the limitations of traditional ground-based monitoring systems, such as high costs and spatial constraints, while leveraging the comprehensive coverage and accuracy of remote sensing data. Platforms like Google Earth Engine (GEE) enhance the efficiency of data processing and analysis, enabling researchers to monitor Tehran’s air quality from 2019 to 2024 and develop precise algorithms for forecasting pollutant trends. This integration of AI and satellite data not only provides accurate air quality predictions but also offers policymakers actionable insights for effective pollution mitigation strategies, with significant implications for urban planning, public health initiatives, and sustainable environmental management.
Keywords
Main Subjects
)