Revisiting Machine Learning Approaches for Short- and Longwave Radiation Inference in Weather and Climate Models, Part II: Online Performance

This paper continues the exploration of {ml} parameterization for radiative transfer for the {icon}. Three {ml} models, developed in Part I of this study, are coupled to {icon}. More specifically, a UNet model and a bidirectional {rnn} with {lstm} are compared against a random forest. The {ml} parameterizations are coupled to the {icon} code that includes OpenACC compiler directives to enable {gpu} support. The coupling is done through Infero, developed by ECMWF, and PyTorch-Fortran. The most accurate model is the bidirectional {rnn} with physics-informed normalization strategy and heating rate penalty, but the fluxes above 15\,km height are computed with a simplified formula for numerical stability reasons. The presented setup enables stable aquaplanet simulations with {icon} for several weeks at a resolution of about 80\,km and compare well with the physics-based radiative transfer solver ecRad. However, the achieved speed up when using the emulators and the minimum required memory usage relative to the {gpu}-enabled ecRad depend strongly on the {nn} architecture. Future studies may explore physics-constraint emulators that predict heating rates inside the atmospheric model and fluxes at the top.