Abstract Statistical downscaling translates coarse-resolution climate model output into locally relevant information for climate services and impact assessment. Recent advances in artificial intelligence (AI) enable high-resolution, probabilistic, and computationally efficient approaches. This paper provides a perspective on the evolution from classical to AI-driven and hybrid downscaling approaches, assesses key challenges related to interpretability, uncertainty, data availability, and computational requirements, and outlines physically constrained and generative frameworks that support decision-making across sectors.
Chun et al. (Mon,) studied this question.