Statistical analysis of factors driving surface ozone variability over continental South Africa

Abstract

Statistical relationships between surface ozone (O₃) concentration, precursor species and meteorological conditions in continental South Africa were examined from data obtained from measurement stations in north-eastern South Africa. Three multivariate statistical methods were applied in the investigation, i.e. multiple linear regression (MLR), principal component analysis (PCA) and –regression (PCR), and generalised additive model (GAM) analysis. The daily maximum 8-h moving average O₃ concentrations were considered in these statistical models (dependent variable). MLR models indicated that meteorology and precursor species concentrations are able to explain ~50% of the variability in daily maximum O₃ levels. MLR analysis revealed that atmospheric carbon monoxide (CO), temperature and relative humidity were the strongest factors affecting the daily O₃ variability. In summer, daily O₃ variances were mostly associated with relative humidity, while winter O₃ levels were mostly linked to temperature and CO. PCA indicated that CO, temperature and relative humidity were not strongly collinear. GAM also identified CO, temperature and relative humidity as the strongest factors affecting the daily variation of O₃. Partial residual plots found that temperature, radiation and nitrogen oxides most likely have a non-linear relationship with O₃ ,while the relationship with relative humidity and CO is probably linear. An inter-comparison between O₃ levels modelled with the three statistical models compared to measured O₃ concentrations showed that the GAM model offered a slight improvement over the MLR model. These findings emphasise the critical role of regional-scale O₃ precursors coupled with meteorological conditions in daily variances of O₃ levels in continental South Africa.