Accelerating Radiation Computations for Dynamical Models With Targeted Machine Learning and Code Optimization
Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
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 tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Harvard
APA
Vancouver
Author
Bibtex
}
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