Use of neural networks for stable, accurate and physically consistent parameterization of subgrid atmospheric processes with good performance at reduced precision
Name
2020GL091363.pdf
Description
Published version
Size
412.69 KB
Format
Adobe PDF
Checksum (MD5)
c3e6ba33084cc857353a08ed52bb5fae
Author(s)
Yuval, Janni
O'Gorman, Paul A
Hill, Chris N
Date Issued
2021
Journal
Geophysical Research Letters
Publisher
American Geophysical Union (AGU)
Version
Final published version
Abstract
A promising approach to improve climate-model simulations is to replace
traditional subgrid parameterizations based on simplified physical models by
machine learning algorithms that are data-driven. However, neural networks
(NNs) often lead to instabilities and climate drift when coupled to an
atmospheric model. Here we learn an NN parameterization from a high-resolution
atmospheric simulation in an idealized domain by coarse graining the model
equations and output. The NN parameterization has a structure that ensures
physical constraints are respected, and it leads to stable simulations that
replicate the climate of the high-resolution simulation with similar accuracy
to a successful random-forest parameterization while needing far less memory.
We find that the simulations are stable for a variety of NN architectures and
horizontal resolutions, and that an NN with substantially reduced numerical
precision could decrease computational costs without affecting the quality of
simulations.
MIT Department
Massachusetts Institute of Technology. Department of Earth, Atmospheric, and Planetary Sciences
Terms of Use
Creative Commons Attribution 4.0 International license
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1029/2020GL091363
