Score: 1

A Probabilistic U-Net Approach to Downscaling Climate Simulations

Published: November 5, 2025 | arXiv ID: 2511.03197v1

By: Maryam Alipourhajiagha , Pierre-Louis Lemaire , Youssef Diouane and more

Potential Business Impact:

Makes climate predictions more detailed and accurate.

Business Areas:
Simulation Software

Climate models are limited by heavy computational costs, often producing outputs at coarse spatial resolutions, while many climate change impact studies require finer scales. Statistical downscaling bridges this gap, and we adapt the probabilistic U-Net for this task, combining a deterministic U-Net backbone with a variational latent space to capture aleatoric uncertainty. We evaluate four training objectives, afCRPS and WMSE-MS-SSIM with three settings for downscaling precipitation and temperature from $16\times$ coarser resolution. Our main finding is that WMSE-MS-SSIM performs well for extremes under certain settings, whereas afCRPS better captures spatial variability across scales.

Country of Origin
🇨🇦 Canada

Repos / Data Links

Page Count
7 pages

Category
Computer Science:
Machine Learning (CS)