Diagnosing Two-Way Coupling in Decadal North Atlantic SST Variability Using Time-Evolving Self-Organizing Maps

Decadal variability in the North Atlantic plays a critical role in modulating regional and global climate. To identify the complex spatiotemporal patterns associated with decadal variability and diagnose mechanisms responsible spatially and over time simultaneously, we debut a novel application of a machine learning method—evolution self-organizing maps. This time-evolving framework is applied to a Community Earth System Model pre-industrial simulation to identify 10-year consecutive spatiotemporal evolutions of winter sea surface temperature (SST). Here we focus on a single evolution that transitions from SST patterns typically associated with a positive North Atlantic Oscillation (NAO) to a positive Atlantic Multidecadal Variability to a weak negative NAO and find that it can occur over just a 10-year period. This method facilitates a new examination of buoyancy-driven and wind-driven ocean circulations as well as ocean-atmosphere transient-eddy feedbacks that confirms the importance of coupled atmosphere-ocean dynamics in producing this decadal variability.