Coupled Climate Simulations with ACE and Samudra

We present a coupling of the Ai2 Climate Emulator (ACE) 3D global atmosphere emulator to the Samudra 3D global ocean emulator, both of which are large autoregressive ML models with a combined total of nearly 600 million parameters. A coupled emulator has the potential advantage of accelerating climate change projections under different future scenarios, enabling more iterative and insightful strategies for climate policy, adaptation, and mitigation. The coupled emulator facilitates the exchange of boundary conditions between separate models of the atmosphere and ocean, with prognostic sea ice included among Samudra’s outputs. The coupled emulator produces a stable climate with remarkably small climate biases, a good seasonal cycle of sea ice, insignificant temporal climate drift, and realistic ENSO variability. The coupled emulator marks a significant step toward enabling fully coupled climate modeling with emulators.