Conditional Flow Matching for Probabilistic Downscaling of Maximum 3-day Snowfall in Alaska

TL;DR

WxFlow is a flow-matching generative model that efficiently produces calibrated probabilistic high-resolution snowfall forecasts from coarse climate data, significantly improving spectral fidelity over traditional methods.

Contribution

The paper introduces WxFlow, a novel flow-matching model that enables fast, accurate probabilistic downscaling of snowfall, incorporating topography and reducing computational costs.

Findings

Achieves 87.8% spectral fidelity improvement over bicubic downscaling.

Generates 50-member ensembles in seconds on a laptop.

Produces physically plausible, topography-governed uncertainty.

Abstract

Precipitation in complex terrain is governed by orographic processes operating at scales of a few kilometers, yet climate models typically run at resolutions of 50--100~km where this topographic detail is absent. Dynamical downscaling with high-resolution regional models such as WRF can resolve these processes, but the computational cost -- months of wall-clock time per scenario -- precludes the large ensembles needed for uncertainty quantification. We present WxFlow, a conditional generative model based on flow matching that learns to map coarse-resolution climate model output and high-resolution topography to calibrated probabilistic ensembles of fine-scale precipitation fields. Applied to 4~km WRF simulations of maximum 3-day snowfall over southeast Alaska, WxFlow achieves 87.8\% improvement in spectral fidelity and dramatically lower Continuous Ranked Probability Scores relative to conventional lapse-rate-corrected bicubic downscaling, while generating 50-member ensembles in seconds on a laptop. Ensemble spread is spatially coherent and governed by topography, reflecting physically plausible uncertainty structure. All code is available at https://github.com/glide-ism/wrf-flow.