Probabilistic Forecasting of Surface Ozone with a Novel Statistical Approach

Nikolay V. Balashov, Anne M. Thompson, George S. Young
2017 Journal of Applied Meteorology and Climatology  
The recent change in US Environmental Protection Agency (EPA) surface ozone regulation, lowering surface ozone daily maximum 8-hour average (MDA8) exceedance threshold from 75 ppbv to 70 ppbv, poses significant challenges to US air quality (AQ) forecasters responsible for ozone MDA8 forecasts. The forecasters, supplied by only a few AQ model products, end up relying heavily on self-developed tools. To help US AQ forecasters, this study explores surface ozone MDA8 forecasting tool based solely
more » ... statistical methods and standard meteorological variables from the numerical weather prediction (NWP) models. The model combines self-organizing map (SOM), a clustering technique, with a stepwise weighted quadratic regression using meteorological variables as predictors for ozone MDA8. The SOM method identifies different weather regimes, to distinguish between various modes of ozone variability, and groups them according to similarity. In this way, when a regression is developed for a specific regime, data from the other regimes are also used, with weights based on their similarity to this specific regime. This approach, regression in SOM (REGiS), yields a distinct model for each regime taking into account both the training cases for that regime and other similar training cases. To produce probabilistic MDA8 ozone forecasts, REGiS weighs and combines all of the developed regression models based on the weather patterns predicted by a NWP model. REGiS is evaluated over San Joaquin Valley in California and northeastern plains of Colorado. The results suggest that the model performs best when trained and adjusted separately for an individual AQ station and its corresponding meteorological site. Real-time ozone forecasting using REGiS is demonstrated for the Philadelphia area over a brief period of time in 2016. iv
doi:10.1175/jamc-d-16-0110.1 fatcat:2gjp6zc33nabzfgyhx55gr4w3m