Modelling and Forecasting Temporal Pm2.5 Concentration Using Ensemble Machine Learning Methods

Exposure of humans to high concentration of PM2.5 has adverve effect on their health . Reseachers estimate that exposure to particulate matter from fossil fuel emissions accounted for 18% of these deaths in 2018. A challenge policy makers argue is being exercabated by increase in numbers of extreme weather events and rapid urbanization as they thinker with strategies for reducing air pollutants. Drawing on a few ensemble machine learning methods which have emerged as a result of advancement in data science, this study examines the effectiveness of using ensemble models for forecasting the concentration of air pollutants, using PM2.5 as a representative case. A comprehensive evaluation of the ensemble methods was carried by comparing its predictive performance with other standalone algorithms. Finding suggests hybrid models provide useful tools for PM 2.5 concentration forecasting. The developed models show that machine learning models are efficient in predicting air particulate and can be used for air pollution forecasting. The study also provides insights into how the climatic factors influences the volume of pollutants found in the air.