Km-scale dynamical downscaling through conformalized latent diffusion models
This work improves reliability for operational weather forecasting and renewable energy modeling by providing more trustworthy probabilistic downscaling, though it is incremental as it builds on existing diffusion models.
The paper addresses the problem of miscalibrated uncertainty estimates in diffusion models for meteorological downscaling by augmenting them with a conformal prediction framework, resulting in grid-point-level uncertainty estimates with improved coverage and stable probabilistic scores on ERA5 reanalysis data downscaled to a 2-km grid.
Dynamical downscaling is crucial for deriving high-resolution meteorological fields from coarse-scale simulations, enabling detailed analysis for critical applications such as weather forecasting and renewable energy modeling. Generative Diffusion models (DMs) have recently emerged as powerful data-driven tools for this task, offering reconstruction fidelity and more scalable sampling supporting uncertainty quantification. However, DMs lack finite-sample guarantees against overconfident predictions, resulting in miscalibrated grid-point-level uncertainty estimates hindering their reliability in operational contexts. In this work, we tackle this issue by augmenting the downscaling pipeline with a conformal prediction framework. Specifically, the DM's samples are post-processed to derive conditional quantile estimates, incorporated into a conformalized quantile regression procedure targeting locally adaptive prediction intervals with finite-sample marginal validity. The proposed approach is evaluated on ERA5 reanalysis data over Italy, downscaled to a 2-km grid. Results demonstrate grid-point-level uncertainty estimates with markedly improved coverage and stable probabilistic scores relative to the DM baseline, highlighting the potential of conformalized generative models for more trustworthy probabilistic downscaling to high-resolution meteorological fields.