Integrating Machine Learning with Station-Level Pollutant Data for Post-Monsoon AQI Prediction in Southern India

Air pollution is a severe environmental and public health issue, especially in fast urbanizing places like Andhra Pradesh, India. The present study explores the post-monsoon air quality dynamics of the year 2024 using Central Pollution Control Board (CPCB) station data to construct the Air Quality Index (AQI) on the basis of key pollutants: PM<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2.5</inf>, PM<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">10</inf>, NO<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</inf>, SO<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</inf>, CO, and O<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</inf>. Hybrid use of GIS-based spatial mapping and supervised learning machine techniques were utilized to interpret pollutant heterogeneity and to forecast AQI values. Spatial interpolation indicated that urbanized and industrial areas had continuously higher AQI levels, even after the purifying effects of monsoonal rains. From the models evaluated, the SVM performed best with a lower error metrics and coefficient of determination of 0.914, which indicates that there is a very high agreement between observed and predicted AQI values. These results demonstrate the influence of machine learning combined with geographical analysis to appropriately model air quality and direct a regional mitigation scheme.