Predictive Modelling of Air Quality Using Machine Learning: Note: A Case Study in New Delhi

The high levels of polluted particulates (PM2.5) gives raise to serious health problem and risks in cities like New Delhi, air pollution is an important public health and environmental concern. In order to forecast the PM2.5 levels in New Delhi, a RandomForestRegressor model was developed and improved using GridSearchCV, utilizing meteorological and air quality data from OpenWeatherMap API. In the test dataset, the model produced a Mean Squared Error of <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$X$</tex> and an R-squared of <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$Y$</tex>, indicating strong performance in air quality prediction. The results demonstrate how machine learning could be used to increase the precision of air quality forecasts, so improving in the development of efficient urban planning and public health management plans in polluted metropolitan areas.