Fig. 6: The workflow for training and sampling CorrDiff for generative downscaling.
From: Residual corrective diffusion modeling for km-scale atmospheric downscaling
Top: coarse-resolution global weather data at 25 km scale is used to first predict the mean μ using a regression model, which is then stochastically corrected using an Elucidated Diffusion Model (EDM) r, together producing the probabilistic high-resolution 2 km-scale regional forecast. Bottom right: diffusion model is conditioned with the coarse-resolution input to generate the residual r after a few denoising steps. Bottom left: the score function for diffusion is learned based on the UNet architecture.
