Overview

Climate downscaling estimates local weather and climate patterns from coarse global models or reanalysis, helping assess regional impacts such as extreme heat, heavy precipitation, and infrastructure risk. Approaches range from statistical correction and U-Net-style convolutional networks to continuous-field operators and probabilistic diffusion or flow-matching models, sometimes guided by terrain or physical constraints. Evaluation commonly uses ERA5, regional climate simulations, and station or satellite observations, measuring not only pointwise errors but also extremes, spatial structure, uncertainty, and consistency across variables. A central challenge is that methods that improve average accuracy or fine-scale texture may still misrepresent extremes, dynamics, or future climates, and results can vary across regions and evaluation metrics.

Latest papers

32 papers3 papers in the last four weeks, down 57% on the four weeks before. 0.0% of all new papers.

Jan 29, 2026

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

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
Jun 24, 2025

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

Downscaling is essential for generating the high-resolution climate data needed for local planning, but traditional methods remain computationally demanding. Recent years have seen impressive results from AI downscaling models, particularly diffusion models, which have attracted attention due to their ability to generate ensembles and overcome the smoothing problem common in other AI methods. However, these models typically remain computationally intensive. We introduce a Hierarchical Diffusion Downscaling (HDD) model, which introduces an easily-extensible hierarchical sampling process to the diffusion framework. A coarse-to-fine hierarchy is imposed via a simple downsampling scheme. HDD achieves competitive accuracy on ERA5 reanalysis datasets and CMIP6 models, significantly reducing computational load by running on up to half as many pixels with competitive results. Additionally, a single model trained at 0.25° resolution transfers seamlessly across multiple CMIP6 models with much coarser resolution. HDD thus offers a lightweight alternative for probabilistic climate downscaling, facilitating affordable large-ensemble high-resolution climate projections. See a full code implementation at: https://github.com/HDD-Hierarchical-Diffusion-Downscaling/HDD-Hierarchical-Diffusion-Downscaling.