Predicting atmospheric optical properties for radiative transfer computations using neural networks

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.

Bibliographic Details

Main Authors:	Veerman, Menno A., Pincus, Robert, Stoffer, Robin, Van Leeuwen, Caspar M., Podareanu, Damian, Van Heerwaarden, Chiel C.
Format:	Article/Letter to editor biblioteca
Language:	English
Subjects:	atmosphere, neural networks, optical properties, radiative transfer,
Online Access:	https://research.wur.nl/en/publications/predicting-atmospheric-optical-properties-for-radiative-transfer-
Tags:	Add Tag No Tags, Be the first to tag this record!