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

TL;DR

This paper introduces a Hierarchical Diffusion Downscaling (HDD) model that reduces computational costs while maintaining accuracy in high-resolution climate data generation, enabling affordable large-ensemble climate projections.

Contribution

The paper presents a novel hierarchical sampling process within diffusion models for climate downscaling, improving efficiency and transferability across models.

Findings

HDD achieves competitive accuracy on ERA5 and CMIP6 datasets.

HDD reduces computational load by up to 50%.

A single trained model transfers across multiple resolutions.

Abstract

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{\deg} 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.