Climate Downscaling with Stochastic Interpolants (CDSI)

TL;DR

This paper introduces a novel data-driven climate downscaling method using stochastic interpolants, which efficiently produces high-resolution regional climate projections from coarse Earth System Model outputs, reducing computational costs significantly.

Contribution

The paper presents a new probabilistic machine learning approach for climate downscaling that is more efficient than traditional regional climate models.

Findings

Accurately generates high-resolution climate ensembles

Reduces computational costs compared to RCMs

Enhances uncertainty quantification in climate projections

Abstract

Global climate projections rely on computationally demanding Earth System Models (ESMs), which are typically limited to coarse spatial resolutions due to their high cost. To obtain high-resolution projections for regions of interest, it is common to use Regional Climate Models (RCMs), which are driven by data produced by ESMs as boundary conditions. While more efficient than running ESMs at fine resolution, RCMs remain expensive and restrict the size of ensemble simulations. Inspired by recent advances in probabilistic machine learning for weather and climate, we introduce a data-driven climate downscaling method based on stochastic interpolants. Our approach efficiently transforms coarse ESM output into high-resolution regional climate projections at a fraction of the computational cost of traditional RCMs. Through extensive validation, we demonstrate that our method generates accurate regional ensembles, enabling both improved uncertainty quantification and broader use of high-resolution climate information.