English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We address the question of how to use a machine learned parameterization in ageneral circulation model, and assess its performance both computationally andphysically. We take one particular machine learned parameterization\cite{Guillaumin1&Zanna-JAMES21} and evaluate the online performance in adifferent model from which it was previously tested. This parameterization is adeep convolutional network that predicts parameters for a stochastic model ofsubgrid momentum forcing by mesoscale eddies. We treat the parameterization aswe would a conventional parameterization once implemented in the numericalmodel. This includes trying the parameterization in a different flow regimefrom that in which it was trained, at different spatial resolutions, and withother differences, all to test generalization. We assess whether tuning ispossible, which is a common practice in general circulation model development.We find the parameterization, without modification or special treatment, to bestable and that the action of the parameterization to be diminishing as spatialresolution is refined. We also find some limitations of the machine learningmodel in implementation: 1) tuning of the outputs from the parameterization atvarious depths is necessary; 2) the forcing near boundaries is not predicted aswell as in the open ocean; 3) the cost of the parameterization is prohibitivelyhigh on CPUs. We discuss these limitations, present some solutions to problems,and conclude that this particular ML parameterization does inject energy, andimprove backscatter, as intended but it might need further refinement before wecan use it in production mode in contemporary climate models.

Implementation and Evaluation of a Machine Learned Mesoscale Eddy Parameterization into a Numerical Ocean Circulation Model