A comparison of bayesian and conditional density models in probabilistic ozone forecasting

— Probabilistic models were developed to provide predictive distributions of daily maximum surface level ozone concentrations. Five forecast models were compared at two stations (Chilliwack and Surrey) in the Lower Fraser Valley of British Columbia, Canada, with local meteorological variables used as predictors. The models were of two types, conditional density models and Bayesian models. The Bayesian models (especially the Gaussian Processes) gave better forecasts for extreme events, namely poor air quality events defined as having ozone concentration ≥ 82 ppb.

• Type: Conference
• Year: 2008
• Where: IJCNN
• Authors: Song Cai, William W. Hsieh, Alex J. Cannon
• Keywords: Artificial Intelligence, Bayesian Models, Conditional Density Models, IJCNN 2008, Ozone Concentration