# Residual corrective diffusion modeling for km-scale atmospheric downscaling

“Residual corrective diffusion modeling for km-scale atmospheric downscaling” (2025), by Morteza Mardani et al. Earth and Planetary Sciences research paper. Original abstract below, unchanged. A free PDF is available.

- Authors: Morteza Mardani, Noah Brenowitz, Yair Cohen, Jaideep Pathak, Chieh-Yu Chen, Cheng-Chin Liu, Arash Vahdat, Mohammad Amin Nabian, Tao Ge, Akshay Subramaniam et al.
- Published: February 24, 2025
- Field: Earth and Planetary Sciences
- DOI: https://doi.org/10.1038/s43247-025-02042-5
- Free PDF: https://www.researchsquare.com/article/rs-3673869/latest.pdf

## Abstract

Predictions of weather hazard require expensive km-scale simulations driven by coarser global inputs. Here, a cost-effective stochastic downscaling model is trained from a high-resolution 2-km weather model over Taiwan conditioned on 25-km ERA5 reanalysis. To address the multi-scale machine learning challenges of weather data, we employ a two-step approach Corrector Diffusion ( CorrDiff ), where a UNet prediction of the mean is corrected by a diffusion step. Akin to Reynolds decomposition in fluid dynamics, this isolates generative learning to the stochastic scales. CorrDiff exhibits skillful RMSE and CRPS and faithfully recovers spectra and distributions even for extremes. Case studies of coherent weather phenomena reveal appropriate multivariate relationships reminiscent of learnt physics: the collocation of intense rainfall and sharp gradients in fronts and extreme winds and rainfall bands near the eyewall of typhoons. Downscaling global forecasts successfully retains many of these benefits, foreshadowing the potential of end-to-end, global-to- km-scales machine learning weather predictions.

Canonical page: https://nerdi.pages.dev/paper/W4407884014
Read three real papers a day in Nerdi (iPhone): https://apps.apple.com/app/apple-store/id6813826387?pt=128757794&ct=web-paper&mt=8