Predicting atmospheric optical properties for radiative transfer computations using neural networks.
Philos Trans A Math Phys Eng Sci
; 379(2194): 20200095, 2021 Apr 05.
Article
em En
| MEDLINE
| ID: mdl-33583269
ABSTRACT
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 Wâ
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'.
Texto completo:
1
Base de dados:
MEDLINE
Tipo de estudo:
Prognostic_studies
/
Risk_factors_studies
Idioma:
En
Ano de publicação:
2021
Tipo de documento:
Article