Correcting Weather and Climate Models by Machine Learning Nudged Historical Simulations

Watt‐Meyer, Oliver; Brenowitz, Noah D.; Clark, Spencer K.; Henn, Brian; Kwa, Anna; McGibbon, Jeremy; Perkins, W. Andre; Bretherton, Christopher S.

doi:10.1029/2021GL092555

i

Correcting Weather and Climate Models by Machine Learning Nudged Historical Simulations

Supporting Files

2021
By Watt‐Meyer, Oliver ; Brenowitz, Noah D. ; Clark, Spencer K. ; ...

Details

Journal Title:

Geophysical Research Letters
Personal Author:

Watt‐Meyer, Oliver ; Brenowitz, Noah D. ; Clark, Spencer K. ; Henn, Brian ; Kwa, Anna ; McGibbon, Jeremy ; Perkins, W. Andre ; Bretherton, Christopher S.
NOAA Program & Office:

OAR (Oceanic and Atmospheric Research) ; GFDL (Geophysical Fluid Dynamics Laboratory)
Description:

Due to limited resolution and inaccurate physical parameterizations, weather and climate models consistently develop biases compared to the observed atmosphere. Using the FV3GFS model at coarse resolution, we propose a method of machine learning corrective tendencies from a hindcast simulation nudged toward observational analysis. We show that a random forest can predict the nudging tendencies from this hindcast simulation with moderate skill using only the model state as input. This random forest is then coupled to FV3GFS, adding corrective tendencies of temperature, specific humidity and horizontal winds at each timestep. The coupled model shows no signs of instability in year-long
Keywords:

General Earth And Planetary Sciences Geophysics General Earth And Planetary Sciences General Earth And Planetary Sciences
Source:

Geophysical Research Letters, 48(15)
DOI:

https://doi.org/10.1029/2021GL092555
ISSN:

0094-8276 ; 1944-8007
Format:

PDF
Publisher:

American Geophysical Union (AGU)
Document Type:

Journal Article
License:

https://creativecommons.org/licenses/by-nc/4.0/
Rights Information:

CC BY-NC
Compliance:

Library
Main Document Checksum:

urn:sha256:b323713f437740c0cac2f434ab6b8a69bc17e36b936db40303ea81a7c7e82644
Download URL:

https://repository.library.noaa.gov/view/noaa/55011/noaa_55011_DS1.pdf
File Type:

[PDF - 1.24 MB ]

Machine readable version (XML)

Download

ON THIS PAGE

Details Supporting Files

The NOAA IR serves as an archival repository of NOAA-published products including scientific findings, journal articles, guidelines, recommendations, or other information authored or co-authored by NOAA or funded partners. As a repository, the NOAA IR retains documents in their original published format to ensure public access to scientific information.