Description of Invention
Pollution poses major health and environmental risks, especially in urban and industrial zones. This study presents a machine learning-based Air Quality Index (AQI) prediction system using key pollutants (PM2.5, PM10, NO₂, CO, O₃) and meteorological data (temperature, humidity, wind speed). Data from sources like IQ Air and the EPA AQS (2021–2024) were preprocessed and analyzed. Models including Random Forest, Gradient Boosting, and Neural Networks were tested, with Random Forest achieving the best results (MAE: 0.0033, RMSE: 0.0422, R²: 0.9982). The model powers a real-time dashboard, aiding proactive air quality management for planners, policymakers, and the public.