Time series forecasting of ozone levels in the Metropolitan Area of Monterrey, Mexico

Abstract

Based on the limitations of air quality models to forecast air pollution, statistical models are convenient and suitable tools to predict pollutant concentrations. This research work proposes a SARMA model to forecast ozone maxima concentrations in five sites of the Metropolitan Area of Monterrey, Mexico. The design of the model includes diverse novel features: meteorological variables were considered as predictors, short-term ozone concentrations (4 times in the day) were forecasted, and appropriated transformations of meteorological parameters were included. The performance measures applied to assess the SARMA model demonstrated that this statistical model is reliable to predict short-term ozone concentrations and it is consistent with the general dynamics of the ozone formation in the metropolitan area.