Abstract

In meteorology, the traditional approach to forecasting employs deterministic models mimicking atmospheric dynamics. Forecast uncertainty due to the partial knowledge of initial conditions is tackled by Ensemble Predictions Systems (EPS). Probabilistic forecasting is a relatively new approach which may properly account for all sources of uncertainty. In this work we propose a hierarchical Bayesian model which develops this idea and makes it possible to deal with an EPS with non-identifiable members using a suitable definition of the second level of the model. An application to Italian small-scale temperature data is shown.