Investigating Atmospheric and Oceanic drivers of Multidecadal North Atlantic Sea Surface Temperature Variability using Explainable Neural Networks

North Atlantic sea surface temperatures (NASST), particularly in the subpolar region, are among the most predictable in the world's oceans. However, the relative importance of atmospheric and oceanic controls on their variability at multidecadal timescales remain uncertain. In this talk, I explore the potential of applying explainable artificial intelligence approaches to investigating the contributions of both components by asking: do neural networks (NNs) trained with either atmospheric or oceanic predictors perform better at predicting NASST? In the presence of external forcings, oceanic predictors outperform atmospheric predictors, persistence, and random chance baselines out to 25-year lead times. Layer-wise relevance propagation is used to unveil the sources of predictability, and reveal that NNs consistently rely upon the Gulf Stream-North Atlantic Current region for accurate predictions. Additionally, NNs trained on output from the Community Earth System Model 1 (CESM1) successfully predict the phasing of multidecadal variability in an observational data set, suggesting consistency in physical processes driving NASST variability between CESM1 and observations.