A Southern Ocean Supergyre As A Unifying Dynamical Framework Identified By Physics-informed Machine Learning

This article discusses the use of a physics-informed unsupervised machine learning framework to study the dynamics of the general circulation and upwelling pathways in the Southern Ocean. It proposes a semi-circumpolar supergyre south of the Antarctic circumpolar current, which is connected and maintained via rough topography. The framework challenges the conventional view of having separate circulation structures in the Weddell and Ross seas and could aid observational and modelling efforts to study this climatologically key region.