Improved representation of ocean mesoscale turbulence using Machine Learning

The role of mesoscale eddies is crucial for ocean circulation and its energy budget. At scales of 10 to 300 km, the mesoscale eddies transfer hydrographic properties and energy at different spatial and temporal scales, hence contributing to equilibrating large scale ocean dynamics and thermodynamics, which is paramount for long-term climate modelling [Olbers et al., 2012]. They also affect biogeochemical tracers, which in return influence ocean thermodynamics (through light penetration), climate and ecosystems, hence representing correctly their effect in ocean models is of greatest importance.

The important mesoscale processes, which can not be captured by satellite and are not well represented by numerical models that do not have eddy resolution, can now be provided by machine learning methods. A deep neural network is used to represent all subgrid atmospheric processes in a climate model and successively replaces traditional subgrid parameterizations in a global general circulation model [Rasp et al., 2018].

Source data: eNATL60 simulation courtesy Julien Le Sommer and Aurélie Albert, Université de Grenoble and Ocean Next Consortium.

Current speed in eNATL60 simulation with explicit tidal motion. from Ocean Next on Vimeo.

Read full report here.