Using Multiple Air Models To Form A Superensemble

Determining the level of air pollution is a modern day necessity for government regulators and industrialized sources. Air dispersion models are often used to determine the concentration of a pollutant. However changing conditions and several assumptions made by the models limit their accuracy at various times. This research proposed combining four different air dispersion models (Gaussian Plume, Variable K Theory, Box, and AFTOX) into a superensemble. Since the superensemble is typically more accurate than its member models, the end result should be a more accurate prediction under any condition. In the interest of evaluating performance, the change in accuracy was measured through RMSE calculations and the change in precision was measured through calculating the Brier Score. It was found that in the prediction of 2 NO the superensemble produced average reduction of 58.2% (mean RMSE) and a 41.9% (Brier Score) from the other models. In 2 SO prediction, the superensemble produced average reductions of 49.3% (mean RMSE) and a 46.2% (Brier Score) from the lowest model