Residual corrective diffusion modeling for km-scale atmospheric downscaling

Abstract

State of the art for weather and climate hazard prediction requires expensive km-scale numerical simulations. Here, a generative diffusion model is explored for downscaling global inputs to km-scale, as a cost-effective alternative. The model is trained to predict 2 km data from an operational regional weather model over Taiwan, conditioned on a 25 km reanalysis. To address the large resolution ratio, different physics and synthesize new channels, we employ a two-step approach. A deterministic model first predicts the mean, followed by a generative diffusion model that predicts the residual. The model exhibits encouraging deterministic and probabilistic skills, spectra and distributions that recover power law relationships in the target data. In case studies of coherent weather phenomena, it sharpens gradients in cold fronts and intensifies typhoons while synthesizing rainbands. Calibration of model uncertainty remains challenging. The prospect of unifying such methods with coarser global models implies a potential for global-to-regional machine learning simulation. A physics inspired two-step approach for generative machine learning model that performs stochastic downscaling, trained on three years of weather model data for Taiwan, is able to efficiently reproduce the physics of weather phenomena such as the collocation of rain with surface temperature and winds.