SwAIther-Precip: Lead-Time-Aware Bias Correction Enables Kilometer-Scale Downscaling of Global AI Precipitation Forecasts over Switzerland

Dan Assouline; Erwan Koch; Federico Amato; Filippo Quarenghi; Daniele Nerini; Thibaut Loiseau; Kyle van de Langemheen; Tom Beucler

arXiv · 2605.16163

SwAIther-Precip: Lead-Time-Aware Bias Correction Enables Kilometer-Scale Downscaling of Global AI Precipitation Forecasts over Switzerland

Dan Assouline·Erwan Koch·Federico Amato·Filippo Quarenghi·Daniele Nerini·Thibaut Loiseau·Kyle van de Langemheen·Tom Beucler

View original source ↗Read source document ↗Export metadata ↓

Abstract

Skillful medium-range precipitation forecasting at kilometer scale remains challenging over complex terrain because precipitation arises from multiscale nonlinear processes that global models cannot explicitly resolve at affordable cost. Global AI weather models can produce skillful medium-range forecasts, but their native 0.25 degrees resolution limits direct use for local hazard applications. Statistical downscaling can help bridge this gap, yet existing approaches often struggle with state-dependent, and especially lead-time-dependent, biases in global forecasts. We introduce SwAIther-Precip, a lead-time-aware downscaling framework that converts coarse-resolution AIFS forecasts into probabilistic km-scale precipitation fields over Switzerland. First, a U-Net conditioned on lead time via feature-wise linear modulation deterministically corrects systematic biases at coarse resolution. This targeted correction enables a cheaper super-resolution stage conditioned only on corrected precipitation, allowing direct training on observations rather than on the full atmospheric state. A diffusion-based model then generates fine-scale spatial variability independently of lead time. Using AIFS forecasts and CombiPrecip radar-gauge observations, SwAIther-Precip reduces CRPS by 48% relative to raw AIFS. The generated fields reproduce observed spatial variability with spectral fidelity above 0.85 at large scales and 0.88 at small scales, corresponding to an effective resolution of approximately 4 km on a 1 km grid for lead times up to 5 days. Training across lead times further improves long-range performance, yielding a 13% CRPS reduction at 6 days relative to lead-time-specific models. These results show that explicitly correcting lead-time-dependent biases before generative super-resolution is key to efficient km-scale probabilistic downscaling of global AI precipitation forecasts.

Explore related subjects

physics.ao-ph cs.LG

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Dan Assouline, Erwan Koch, Federico Amato, Filippo Quarenghi, Daniele Nerini, Thibaut Loiseau, Kyle van de Langemheen, Tom Beucler. 2026-06-08. SwAIther-Precip: Lead-Time-Aware Bias Correction Enables Kilometer-Scale Downscaling of Global AI Precipitation Forecasts over Switzerland. https://arxiv.org/abs/2605.16163

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Conservation Constraints and Distributed Advective Memory in a Reduced Model of Atlantic Overturning Hysteresis

Interbasin exchange through the Indo-Pacific gateway supplies salt to the Atlantic and is widely invoked as a control on the stability of the Atlantic overturning circulation. We ask whether that control can act on the equilibrium structure of a conceptual thermohaline model. A closed five-box model with an exact salt invariant is constructed, comprising North Atlantic, upper-limb, Indian, Pacific, and deep reservoirs, with the return flow split between a warm route through the Indian reservoir and a cold route, together with an Indonesian Throughflow branch and an Agulhas retroflection. Adding the steady-state budgets of the gateway reservoirs shows that every internal exchange cancels, so the salt they export to the Atlantic is fixed by the net Atlantic freshwater export alone. This holds independently of the warm-route fraction, the throughflow, the retroflection, and how the export is apportioned among gateway reservoirs; across a parameter sweep the largest departure is of order ten to the minus eleven. The gateway therefore enters as a purely additive forcing and cannot renormalize the salt-advection feedback. Replacing the discrete transit lag by a gamma memory kernel leaves the equilibria unchanged but yields a closed-form threshold for oscillatory instability depending only on kernel shape. Broad memory is strongly stabilizing, and a discrete lag is the least stable member of the family. Because the instantaneous feedback vanishes at the fold, oscillatory instability always precedes the saddle-node, over an interval widening more than tenfold as memory sharpens. Gateways therefore appear to act on transient rather than equilibrium dynamics

physics.ao-ph↗

arXiv2026

Forecasting threshold exceedance of atmospheric variables at a specific location

Accurate short-term forecasting of extreme weather events is important for early warning and risk mitigation. We compare two approaches for predicting site-specific threshold exceedances of weather variables: direct binary probabilistic models trained on thresholded outcomes and full-distribution parametric models trained on the continuous target. Using an analytically tractable Gaussian random-location model, in which the distribution is predictably shifted by the covariates, we quantify the consequences of the information loss induced by thresholding and derive the rare-event behavior of prediction errors and forecast skill. The analysis predicts an increasing relative advantage of the full-distribution approach as event probability decreases, because binarization progressively discards information contained in the continuous response. We then compare the two approaches to forecast wind speed and accumulated rainfall at various weather station sites over southeastern France using the same hybrid neural-network architecture. Although wind speed and rainfall depart from the toy-model assumptions, its main qualitative predictions are recovered for both variables: the relative advantage of distributional modeling increases toward rarer thresholds. This agreement further suggests that a substantial fraction of the forecastable signal associated with extreme events arises from predictable shifts in the conditional distribution. For the reasonably suitable parametric families examined, the results show limited sensitivity to the selected class of distribution. Overall, the results highlight the statistical advantage of training on continuous observations rather than on thresholded binary outcomes when forecasting rare threshold exceedances.

physics.ao-ph↗

arXiv2026

Blinded Evaluation of Oceanic Sound Source Locations via Sequential Bound Estimation

A non-linear, non-Bayesian method called sequential bound estimation (SBE) derived 100% confidence intervals of location (CIL) for 219 explosions in the ocean from measurements of their time differences of arrivals among five widely-spaced time-unsynchronized receivers on the ocean bottom. The explosion's locations were measured with the global positioning system. A blind evaluation revealed all 219 explosions were within their CIL. The probability this could happen by chance is $4 \times 10^{-116}$. The explosions were detonated in shallow water on the eastern continental shelf of the U.S. over the so-called New England Mud Patch.

physics.ao-ph↗