Machine Learning-based Air Pollution Prediction Model
Madhushika Mihirani, S.L.P. Yasakethu, Sachintha Balasooriya
Abstract
Air pollution is currently a critical issue for both public health and the environment. It is vital to provide advance notice of pollution levels, and air quality forecasts can play a crucial role in achieving this goal. To measure pollution levels, experts rely on the air quality index (AQI). For this research, gathered data on air pollution, specifically focusing on Fine particles (PM <inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2.5</inf> ), Sulphur Dioxide (SO <inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</inf> ), Nitrogen Dioxide (NO <inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</inf> ), and Carbon monoxide (CO), which were used as the primary dataset. Different machine learning models, including linear regression, lasso regression, random forest regression, and K-nearest neighbor regression, were then employed to analyze the collected data. The mean absolute error(MAE), mean-squared error (MSE), root-mean squared error(RMSE) and accuracy are used to evaluate the performance of the ML model. The comparison between these models is also discussed in this paper. Random forest regression is giving the high accuracy and low RMSE among other models.