Fast and accurate approximation of the long wave radiation parameterization in a GCM using neural networks: evaluation of computational performance and accuracy of approximation in the NCAR CAM-2

Abstract

A new approach based on a synergetic combination of statistical/machine learning and deterministic modeling within atmospheric models is presented. The approach uses neural networks as a statistical or machine learning technique for an accurate and fast emulation or statistical approximation of model physics parameterizations. It is applied to the development of an accurate and fast approximation of an atmospheric long wave radiation parameterization for the NCAR Community Atmospheric Model, which is the most time consuming component of model physics. The developed neural network emulation is two orders of magnitude, 50-80 times, faster than the original parameterization. A comparison of the parallel 10-year climate simulations performed with the original parameterization and its neural network emulations, confirmed that these simulations produce almost identical results. The obtained results show the conceptual and practical possibility of an efficient synergetic combination of deterministic and statistical learning components within an atmospheric climate or forecast model.