cs.AIJan 29, 2026

GCD: GCM-consistent Diffusion for Zero-shot Downscaling across Heterogeneous GCMs

Authors: Ruian Tie, Wenbo Xiong, Zhengyu Shi, Xinyu Su, Chenyu jiang, Libo Wu, Hao Li

Organizations: Artificial Intelligence Innovation and Incubation Institute, Fudan University, Shanghai, China · Shanghai Innovation Institute, Shanghai, China · Shanghai Academy of AI for Science, Shanghai, China · School of Data Science, Fudan University, Shanghai, China · 

Abstract

Climate downscaling of General Circulation Models (GCMs) is an ill-posed inverse problem, as GCM outputs and reanalysis fields arise from different dynamical systems and lack fine-scale temporal pairing. Supervised methods thus rely on synthetic degradations or model-specific adaptation, limiting generalization across heterogeneous GCMs. Zero-shot diffusion posterior sampling (DPS) avoids paired supervision by combining a high-resolution climate prior with inference-time constraints from coarse GCM inputs, but faces consistency and efficiency challenges. We propose GCM-consistent Diffusion for Zero-shot Downscaling (GCD), which addresses these challenges with geographic conditioning, spectrally filtered measurement guidance, and distillation-accelerated Conjugate Gradient guidance. GCD reduces inference from 1,000 diffusion steps to 6 while maintaining consistency with the coarse GCM inputs. Across five heterogeneous GCMs, GCD achieves competitive 99th-percentile extreme-event accuracy and reconstructs plausible high-frequency tropical cyclone structures without model-specific retraining. Github: https://github.com/shawnvonbohr/GCD-Climate-Downscaling.git

Figures & tables

Appendix figures & tables14 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Generate the Forest before the Trees - A Hierarchical Diffusion model for Climate Downscaling

    Jun 24, 2025Declan J. Curran, Sanaa Hobeichi, Hira Saleem +2Climate DownscalingClimate Modeling

  2. IPSL-AID: Generative Diffusion Models for Climate Downscaling from Global to Regional Scales

    Mar 23, 2026Kishanthan Kingston, Olivier Boucher, Freddy Bouchet +5Climate DownscalingPrecipitation Downscaling

  3. DySCo: Dynamically consistent data-driven downscaling of extremes in climate projections

    Aug 22, 2026S. Stamatelopoulos, M. Wang, I. Lopez-Gomez +5Climate DownscalingWeather Downscaling