loading page

Deep ocean learning of wave-induced turbulence
  • +4
  • Ali Mashayek,
  • Fangming Zhai,
  • Nick Reynard,
  • Adam Jelley,
  • Colm Caulfield,
  • Alberto C. Naveira Garabato,
  • Kashik Srinivasan
Ali Mashayek
Imperial College London, Imperial College London

Corresponding Author:mashayek@ic.ac.uk

Author Profile
Fangming Zhai
Imperial College, Imperial College
Author Profile
Nick Reynard
Imperial College, Imperial College
Author Profile
Adam Jelley
University of Edinburgh, University of Edinburgh
Author Profile
Colm Caulfield
University of Cambridge, University of Cambridge
Author Profile
Alberto C. Naveira Garabato
University of Southampton, University of Southampton
Author Profile
Kashik Srinivasan
University of California Los Angeles
Author Profile


Turbulent mixing at centimetre scales is an essential component of the ocean’s meridional overturning circulation and its associated global redistribution of heat, carbon, nutrients, pollutants and other tracers. Whereas direct turbulence observations in the ocean interior are limited to a modest collection of field programs, basic information such as temperature, salinity and depth ($T,S,Z$) is available globally. Here, we show that supervised (deep) machine learning algorithms, informed by physical understanding, can be trained on the existing turbulence data to develop skillful predictions of the key properties of turbulence from $T,S,Z$ and topographic data. This constitutes a promising first step toward a hybrid physics - artificial intelligence approach to parameterize turbulent mixing in climate-scale ocean models.