Predicting atmospheric optical properties for radiative transfer computations using neural networks Journal Article uri icon



  • ; The radiative transfer equations are well known, but radiation parametrizations in atmospheric models are computationally expensive. A promising tool for accelerating parametrizations is the use of machine learning techniques. In this study, we develop a machine learning-based parametrization for the gaseous optical properties by training neural networks to emulate a modern radiation parametrization (RRTMGP). To minimize computa- tional costs, we reduce the range of atmospheric conditions for which the neural networks are applicable and use machine-specific optimized BLAS functions to accelerate matrix computations. To generate training data, we use a set of randomly perturbed atmospheric profiles and calculate optical properties using RRTMGP. Predicted optical properties are highly accurate and the resulting radiative fluxes have average errors within 0.5 W m; −2; compared to RRTMGP. Our neural network-based gas optics parametrization is up to four times faster than RRTMGP, depending on the size of the neural networks. We further test the trade-off between speed and accuracy by training neural networks for the narrow range of atmospheric conditions of a single large-eddy simulation, so smaller and therefore faster networks can achieve a desired accuracy. We conclude that our machine learning-based parametrization can speed-up radiative transfer computations while retaining high accuracy.; ; This article is part of the theme issue ‘Machine learning for weather and climate modelling’.

publication date

  • April 5, 2021

Full Author List

  • Veerman MA; Pincus R; Stoffer R; van Leeuwen CM; Podareanu D; van Heerwaarden CC

Other Profiles

Additional Document Info

start page

  • 20200095

end page

  • 20200095


  • 379


  • 2194