Use of a neural-network-based long-wave radiative-transfer scheme in the ECMWF atmospheric model

The definition of an approach for radiative-transfer modelling that would enable computation times suitable for climate studies and a satisfactory accuracy, has proved to be a challenge for modellers. A fast radiative-transfer model is tested at ECMWF: NeuroFlux. It is based on an artificial neural-network technique used in conjunction with a classical cloud approximation (the multilayer grey-body model). The accuracy of the method is assessed through code-by-code comparisons, climate simulations and ten-day forecasts with the ECMWF model. The accuracy of NeuroFlux appears to be comparable to the accuracy of the ECMWF operational scheme, with a negligible impact on the simulations, while its computing time is seven times faster.