Predicting air quality is essential for addressing environmental threats and public health issues. Advances in data analytics and real-time monitoring technology have created new avenues for precise and rapid air quality forecasting in recent years. In order to deliver accurate and useful data, this research proposes a novel method for real-time air quality prediction. The suggested method makes use of machine learning techniques, meteorological data, and data to anticipate air quality in real time. Throughout the target area, a network of air quality sensors is installed to continually measure different pollutants like sulphur oxide (SO2), nitrogen dioxide (NO2), and particulate matter (PM). Meteorological information on temperature, humidity, wind speed, and atmospheric pressure is added to these observations