Emulating Climate Across Scales with Conditional Spherical Fourier Neural Operators

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.