Predicting Air Pollution Particulate Matter Levels in India using Weighted Ensemble Learning Method

Over the past few decades, air pollution had been the biggest hazard of environment which contains harmful pollutants like particulate matter (PM<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2.5</inf>) which may cause cardio vascular diseases, chronic respiratory conditions in children and adults. Heavy industries, limitless traffic and extensive urbanization were some of the reasons of air pollutant concentration. Hence, it is very important to have a clear vision on the quality of air that people consume and also the presence of pollutants in the air. This research carried out a pollutant concentration based air quality analysis and predicted the amount of that pollutant in future. By taking help machine learning predictive algorithms and deep learning models on Air Quality dataset of India from 2017 – 2022, the air quality is measured and the applied models were compared. Mean Absolute Error(MAE), Mean Squared Error(MSE), Root Mean Squared Error(RMSE) and R<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> value were used as evaluation metrics for predictive performance assessment of the models. Early prediction of pollutants may communicate a warning alert for population and government which can implement sustainable measures on controlling the pollution, saving the greenery and preserving the environment.