摘要：The Subpolar North Atlantic is known for rapid reversals of decadal temperature trends, with ramifications encompassing the large-scale meridional overturning and gyre circulations, Arctic heat and mass balances, or extreme continental weather. Here, we combine datasets derived from sustained ocean observing systems (satellite and in situ), idealized observation-based modelling (advection-diffusion of a passive tracer), and a machine learning technique (ocean profile clustering) to document and explain the most-recent and ongoing cooling-to-warming transition of the Subpolar North Atlantic. Following a gradual cooling of the region that was persisting since 2006, a surface-intensified and large-scale warming sharply emerged in 2016 following an ocean circulation shift that enhanced the northeastward penetration of warm and saline waters from the western subtropics. The long ocean memory of the Subpolar North Atlantic implies that this advection-driven warming is likely to persist in the near-future with possible implications for the Atlantic multidecadal variability and its global impacts. The subpolar North Atlantic Ocean warmed sharply after 2016 as the transport of warm saline waters from the western subtropics was enhanced - following a period of cooling between 2006 and 2016 - according to analyses of observations via idealized modelling and machine-learning techniques.
