Air pollution poses a significant challenge to global public health and sustainable development, with an exceptionally high health burden in low- and middle-income countries. Traditional ground monitoring networks rely on high-precision instruments. However, they have natural limitations regarding spatial coverage, operating costs, and the ability to compare data across regions. This often creates an "information gap" for policymakers when they seek to identify pollution hotspots, evaluate policy effectiveness, or assess population exposure. Over the past 30 years, satellite remote sensing has rapidly become a crucial data source for monitoring and managing air pollution, thanks to its global coverage and continuous observation capabilities. Low Earth Orbit (LEO) missions, such as Terra/Aqua’s MODIS, Aura’s OMI, and Sentinel-5P (TROPOMI), provide data on key pollutants, including NO2, SO2, O3, CO, CH4, and Aerosol Optical Depth (AOD). By combining this data with chemical transport models (CTMs) and machine learning, scientists can estimate ground-level concentrations and exposure levels. Furthermore, the new generation of Geostationary (GEO) missions, such as GEMS, TEMPO, and Sentinel-4, provides hourly data. This significantly enhances our ability to track daily changes in pollution and specific events, ushering in a new era of "near real-time, high-frequency, and high-resolution" air quality monitoring.