Emulating Climate Across Scales with Conditional Spherical Fourier Neural Operators (Papers Track)
Jeremy McGibbon (Allen Institute for Artificial Intelligence); Troy Arcomano (Allen Institute for Artificial Intelligence); Spencer Clark (Allen Institute for Artificial Intelligence); James Duncan (Allen Institute for Artificial Intelligence); Brian Henn (Allen Institute for Artificial Intelligence); Anna Kwa (Allen Institute for Artificial Intelligence); W. Andre Perkins (Allen Institute for Artificial Intelligence); Oliver Watt-Meyer (Allen Institute for Artificial Intelligence); Elynn Wu (Allen Institute for Artificial Intelligence); Christopher Bretherton (Allen Institute for Artificial Intelligence)
Abstract
Estimating local impacts of climate change is critical for informing adaptation methods. The ACE2 climate emulator successfully reproduces changes in historically observed climate, but poorly represents variability of key variables, such as surface precipitation, at small scales. We demonstrate that by adapting ACE2 to use conditional layer normalization and conditioning on isotropic Gaussian noise with a probabilistic loss function, we can successfully reproduce these small-scale features. This is a crucial step towards the goal of applying climate emulator predictions to inform real-world decisions.