Global climatology of submesoscale restratification using machine learning

Submesoscale eddies are important in setting the stratification in the ocean surface mixed layer and transporting energy between large and small scale motions. However, the study of submesoscale on a global scale has been hin- dered by a shortage of global, long-term datasets. To meet this need, we apply an unsupervised machine learning method adapted from the profile classification model (PCM) to density profiles collected by Argo floats over global ocean from 2000-2021, producing the first global observational climatology of submesoscale restratification. The method classifies individual vertical profiles based on the shape of the density profile in the ocean surface mixed layer. The fraction of pro- files which exhibit a shape that is characteristic of the influence of submesoscales is referred to as the submesoscale restratification (SR) index. The SR index peaks in spring in both hemispheres and lags the maxima of mixed layer depth by one month, suggesting that submesoscale eddies play an important role in restrati- fying the mixed layer. Hotspots of SR index can be found in the Norwegian Sea and the Drake Passage in spring. This method enables the study of the spatial and temporal distributions of submesoscale restratification on a global scale.