Many countries experience a rise in annual health costs due to poor air quality, which is a major source of health problems. The key to raising living standards is forecasting air quality metrics in severely impacted locations. Sri Lanka falls short in this regard, nevertheless, particularly when urban development raises the levels of bad air quality. The weather, car emissions, and power plant emissions are just a few of the variables that make it difficult to predict the quality of the air. Using both real-time and predicted data along with air quality measurements, our model provides a comprehensive machine learning framework. The forecasting models were assessed using several performance indicators, including mean absolute error (MAE), root mean square error (RMSE), mean square error (MSE), coefficient of determination (R2), and mean absolute relative error (MARE). Due to the serious health effects of contaminated air, clean air is necessary for human survival. Air quality is rarely given enough attention, despite studies showing that 68% of human illnesses are caused by air pollution. Typical air pollutants such as PM2.5 raise the risk of cancer and harm the lungs, heart, and immune system. To cut hospital admissions and enhance general health, immediate action to minimize air pollution is required.