Satellite, ground-based, and other observational platforms, together with chemical transport models, have greatly advanced our ability to characterize atmospheric composition and air quality from local to global scales. Recent advances in polar-orbiting and geostationary satellite sensors, ground-based networks, and field campaigns are providing unprecedented observations of aerosols, reactive trace gases, and greenhouse gases with improved spatial, temporal, and spectral resolution. These complementary observing systems offer new opportunities to characterize diurnal variability, extreme pollution events, emission sources, and transboundary transport, while improving our understanding of human exposure to air pollution and its associated health impacts. At the same time, advances in artificial intelligence (AI), data fusion, and atmospheric modeling are creating new opportunities to integrate satellite observations, ground-based measurements, meteorological data, and chemical transport models. These approaches enable high-resolution and gap-free characterization of atmospheric composition, support near-real-time monitoring and forecasting, and improve assessments of air pollution exposure, radiative effects, emissions, and health impacts. This session invites contributions that advance our understanding of atmospheric composition, air quality, and health through observations, modeling, data integration, and emerging computational approaches. We particularly welcome studies using satellite and ground-based observations, field measurements, chemical transport models, AI and machine learning, multi-source data fusion, and novel approaches for air pollution monitoring, exposure assessment, and environmental health applications.