Stochastic representation of model uncertainties in the ECMWF Ensemble Prediction System

A stochastic representation of random error associated with parametrized ph ysical processes ('stochastic physics') is described, and its impact in the European Centre for Medium-Range Weather Forecasts Ensemble Prediction Sys tem (ECMWF EPS) is discussed. Model random errors associated with physical parametrizations are simulated by multiplying the total parametrized tenden cies by a random number sampled from a uniform distribution between 0.5 and 1.5. A number of diagnostics are described and a choice of parameters is m ade. It is shown how the scheme increases the spread of the ensemble, and i mproves the skill of the probabilistic prediction of weather parameters suc h as precipitation. A choice of stochastic parameters is made for operation al implementation. The scheme was implemented successfully in the operation al ECMWF EPS on 21 October 1998.