Temporal dynamics of urban air pollution: A big data-driven analysis of pollutant trends, health implications, and policy interventions

Urban air pollution remains a critical public health challenge in metropolitan areas worldwide. This study presents a comprehensive big data analytics framework for analyzing temporal dynamics of air quality using a four-year dataset (2021–2024) comprising 1,461 daily observations of key pollutants including PM2.5, PM10, NO2, SO2, CO, and Ozone. Employing a scalable computational pipeline utilizing PySpark for distributed processing and Python-based visualization tools, this research addresses four primary questions: (1) the relationship between seasonal pollutant variations and public health risks; (2) the impact of holiday periods on acute pollution episodes; (3) comparative health implications of particulate versus gaseous pollutants; and (4) long-term trends in photochemical pollutants. Results reveal significant winter peaks in Air Quality Index (AQI) values (30% above annual averages), elevated pollution during holiday periods (15–20% increase), and strong correlations between PM2.5 and overall air quality (r =0.85). The findings provide actionable insights for evidence-based policy interventions, suggesting potential reductions of 10–15% in pollution-related health outcomes through targeted seasonal interventions.