Using Deep Neural Networks as Cost‐Effective Surrogate Models for Super‐Parameterized E3SM Radiative Transfer.

Deep neural networks (DNNs) are implemented in Super‐Parameterized Energy Exascale Earth System Model (SP‐E3SM) to imitate the shortwave and longwave radiative transfer calculations. These DNNs were able to emulate the radiation parameters with an accuracy of 90–95% at a cost of 8–10 times cheaper than the original radiation parameterization. A comparison of time‐averaged radiative fluxes and the prognostic variables manifested qualitative and quantitative similarity between the DNN emulation and the original parameterization. It has also been found that the differences between the DNN emulation and the original parameterization are comparable to the internal variability of the original parameterization. Although the DNNs developed in this investigation emulate the radiation parameters for a specific set of initial conditions, the results justify the need of further research to generalize the use of DNNs for the emulations of full model radiation and other parameterization for seasonal predictions and climate simulations. Plain Language Summary: The radiative transfer calculations in general circulation models often impose a computational challenge owing to the complexity of the current radiation models. In this study, we have demonstrated that deep neural networks can reduce the cost of radiative transfer calculations in the Super‐Parameterized Energy Exascale Earth System Model while maintaining accuracy. Key Points: We build deep neural networks (DNNs) to emulate the shortwave and longwave radiation parameterization in Super‐Parameterized E3SMThe DNNs accurately predict the instantaneous and annually averaged radiative fluxesThe DNNs compute the radiative fluxes 8‐10 times faster than the original radiation parameterization [ABSTRACT FROM AUTHOR]