Benchmarking of machine learning ocean subgrid parameterizations in an idealized model
Andrew Ross, Ziwei Li, Pavel Perezhogin, Carlos Fernandez-Granda and Laure Zanna’s article is out in JAMES!
The work is a comprehensive framework for developing and testing ocean turbulence parametrizations. In addition to using physics parameterizations (e.g., backscatter, Smagorinsky) and common machine learning techniques (convolutional neural networks), they developed a hybrid equation-discovery method, leading to interpretable parametrizations that are also easily implementable online.
Laure Zanna
Joseph B. Keller and Herbert B. Keller Professor in Applied Mathematics; Professor of Mathematics and Data Science
My research interests include Climate Dynamics, Physical Oceanography, Applied Math, Numerical Methods, and Data Science.