Accelerating Radiation Computations for Dynamical Models With Targeted Machine Learning and Code Optimization

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningfagfællebedømt

Standard

Accelerating Radiation Computations for Dynamical Models With Targeted Machine Learning and Code Optimization. / Ukkonen, Peter; Pincus, Robert; Hogan, Robin J.; Pagh Nielsen, Kristian; Kaas, Eigil.

I: Journal of Advances in Modeling Earth Systems, Bind 12, Nr. 12, e2020MS002226, 15.11.2020.

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningfagfællebedømt

Harvard

Ukkonen, P, Pincus, R, Hogan, RJ, Pagh Nielsen, K & Kaas, E 2020, 'Accelerating Radiation Computations for Dynamical Models With Targeted Machine Learning and Code Optimization', Journal of Advances in Modeling Earth Systems, bind 12, nr. 12, e2020MS002226. https://doi.org/10.1029/2020MS002226

APA

Ukkonen, P., Pincus, R., Hogan, R. J., Pagh Nielsen, K., & Kaas, E. (2020). Accelerating Radiation Computations for Dynamical Models With Targeted Machine Learning and Code Optimization. Journal of Advances in Modeling Earth Systems, 12(12), [e2020MS002226]. https://doi.org/10.1029/2020MS002226

Vancouver

Ukkonen P, Pincus R, Hogan RJ, Pagh Nielsen K, Kaas E. Accelerating Radiation Computations for Dynamical Models With Targeted Machine Learning and Code Optimization. Journal of Advances in Modeling Earth Systems. 2020 nov 15;12(12). e2020MS002226. https://doi.org/10.1029/2020MS002226

Author

Ukkonen, Peter ; Pincus, Robert ; Hogan, Robin J. ; Pagh Nielsen, Kristian ; Kaas, Eigil. / Accelerating Radiation Computations for Dynamical Models With Targeted Machine Learning and Code Optimization. I: Journal of Advances in Modeling Earth Systems. 2020 ; Bind 12, Nr. 12.

Bibtex

@article{d8f24992c4074cd08842ffc11040426d,
title = "Accelerating Radiation Computations for Dynamical Models With Targeted Machine Learning and Code Optimization",
abstract = "Atmospheric radiation is the main driver of weather and climate, yet due to a complicated absorption spectrum, the precise treatment of radiative transfer in numerical weather and climate models is computationally unfeasible. Radiation parameterizations need to maximize computational efficiency as well as accuracy, and for predicting the future climate many greenhouse gases need to be included. In this work, neural networks (NNs) were developed to replace the gas optics computations in a modern radiation scheme (RTE+RRTMGP) by using carefully constructed models and training data. The NNs, implemented in Fortran and utilizing BLAS for batched inference, are faster by a factor of 1-6, depending on the software and hardware platforms. We combined the accelerated gas optics with a refactored radiative transfer solver, resulting in clear-sky longwave (shortwave) fluxes being 3.5 (1.8) faster to compute on an Intel platform. The accuracy, evaluated with benchmark line-by-line computations across a large range of atmospheric conditions, is very similar to the original scheme with errors in heating rates and top-of-atmosphere radiative forcings typically below 0.1 K day(-1) and 0.5 W m(-2), respectively. These results show that targeted machine learning, code restructuring techniques, and the use of numerical libraries can yield material gains in efficiency while retaining accuracy.",
keywords = "machine learning, radiation, atmospheric model, parameterization, CORRELATED-K METHOD, PARAMETERIZATION",
author = "Peter Ukkonen and Robert Pincus and Hogan, {Robin J.} and {Pagh Nielsen}, Kristian and Eigil Kaas",
year = "2020",
month = nov,
day = "15",
doi = "10.1029/2020MS002226",
language = "English",
volume = "12",
journal = "Journal of Advances in Modeling Earth Systems",
issn = "1942-2466",
publisher = "Wiley-Blackwell",
number = "12",

}

RIS

TY - JOUR

T1 - Accelerating Radiation Computations for Dynamical Models With Targeted Machine Learning and Code Optimization

AU - Ukkonen, Peter

AU - Pincus, Robert

AU - Hogan, Robin J.

AU - Pagh Nielsen, Kristian

AU - Kaas, Eigil

PY - 2020/11/15

Y1 - 2020/11/15

N2 - Atmospheric radiation is the main driver of weather and climate, yet due to a complicated absorption spectrum, the precise treatment of radiative transfer in numerical weather and climate models is computationally unfeasible. Radiation parameterizations need to maximize computational efficiency as well as accuracy, and for predicting the future climate many greenhouse gases need to be included. In this work, neural networks (NNs) were developed to replace the gas optics computations in a modern radiation scheme (RTE+RRTMGP) by using carefully constructed models and training data. The NNs, implemented in Fortran and utilizing BLAS for batched inference, are faster by a factor of 1-6, depending on the software and hardware platforms. We combined the accelerated gas optics with a refactored radiative transfer solver, resulting in clear-sky longwave (shortwave) fluxes being 3.5 (1.8) faster to compute on an Intel platform. The accuracy, evaluated with benchmark line-by-line computations across a large range of atmospheric conditions, is very similar to the original scheme with errors in heating rates and top-of-atmosphere radiative forcings typically below 0.1 K day(-1) and 0.5 W m(-2), respectively. These results show that targeted machine learning, code restructuring techniques, and the use of numerical libraries can yield material gains in efficiency while retaining accuracy.

AB - Atmospheric radiation is the main driver of weather and climate, yet due to a complicated absorption spectrum, the precise treatment of radiative transfer in numerical weather and climate models is computationally unfeasible. Radiation parameterizations need to maximize computational efficiency as well as accuracy, and for predicting the future climate many greenhouse gases need to be included. In this work, neural networks (NNs) were developed to replace the gas optics computations in a modern radiation scheme (RTE+RRTMGP) by using carefully constructed models and training data. The NNs, implemented in Fortran and utilizing BLAS for batched inference, are faster by a factor of 1-6, depending on the software and hardware platforms. We combined the accelerated gas optics with a refactored radiative transfer solver, resulting in clear-sky longwave (shortwave) fluxes being 3.5 (1.8) faster to compute on an Intel platform. The accuracy, evaluated with benchmark line-by-line computations across a large range of atmospheric conditions, is very similar to the original scheme with errors in heating rates and top-of-atmosphere radiative forcings typically below 0.1 K day(-1) and 0.5 W m(-2), respectively. These results show that targeted machine learning, code restructuring techniques, and the use of numerical libraries can yield material gains in efficiency while retaining accuracy.

KW - machine learning

KW - radiation

KW - atmospheric model

KW - parameterization

KW - CORRELATED-K METHOD

KW - PARAMETERIZATION

U2 - 10.1029/2020MS002226

DO - 10.1029/2020MS002226

M3 - Journal article

VL - 12

JO - Journal of Advances in Modeling Earth Systems

JF - Journal of Advances in Modeling Earth Systems

SN - 1942-2466

IS - 12

M1 - e2020MS002226

ER -

ID: 255502385