Universal Diffusion-Based Probabilistic Downscaling

• URL: http://arxiv.org/abs/2602.11893v2
• Date: Thu, 19 Feb 2026 10:22:31 GMT
• Title: Universal Diffusion-Based Probabilistic Downscaling
• Authors: Roberto Molinaro, Niall Siegenheim, Henry Martin, Mark Frey, Niels Poulsen, Philipp Seitz, Marvin Vincent Gabler,
• Abstract summary: We introduce a universal diffusion-based downscaling framework that lifts deterministic low-resolution weather forecasts into high-resolution predictions.<n>A single conditional diffusion model is trained on paired coarse-resolution inputs and high-resolution regional reanalysis targets.<n>We evaluate probabilistic forecasts against independent in situ station observations over lead times up to 90 h.
• Score: 3.47037488116399
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We introduce a universal diffusion-based downscaling framework that lifts deterministic low-resolution weather forecasts into probabilistic high-resolution predictions without any model-specific fine-tuning. A single conditional diffusion model is trained on paired coarse-resolution inputs (~25 km resolution) and high-resolution regional reanalysis targets (~5 km resolution), and is applied in a fully zero-shot manner to deterministic forecasts from heterogeneous upstream weather models. Focusing on near-surface variables, we evaluate probabilistic forecasts against independent in situ station observations over lead times up to 90 h. Across a diverse set of AI-based and numerical weather prediction (NWP) systems, the ensemble mean of the downscaled forecasts consistently improves upon each model's own raw deterministic forecast, and substantially larger gains are observed in probabilistic skill as measured by CRPS. These results demonstrate that diffusion-based downscaling provides a scalable, model-agnostic probabilistic interface for enhancing spatial resolution and uncertainty representation in operational weather forecasting pipelines.

Related papers

• Demystifying Data-Driven Probabilistic Medium-Range Weather Forecasting [63.8116386935854]
  We demonstrate that state-of-the-art probabilistic skill requires neither intricate architectural constraints nor specialized trainings.<n>We introduce a scalable framework for learning multi-scale atmospheric dynamics by combining a directly downsampled latent space with a history-conditioned local projector.<n>We find that our framework design is robust to the choice of probabilistic estimators, seamlessly supporting interpolants, diffusion models, and CRPS-based ensemble training.
  arXiv  Detail & Related papers  (2026-01-26T03:52:16Z)
• High-Resolution Probabilistic Data-Driven Weather Modeling with a Stretched-Grid [1.2136581144377903]
  We present a data-driven weather model capable of providing an ensemble of high spatial resolution realizations of 87 variables at arbitrary forecast length and ensemble size.<n>The model is trained using a loss function based on the Continuous Ranked Probability Score (CRPS) evaluated point-wise in real and spectral space.
  arXiv  Detail & Related papers  (2025-11-28T10:08:03Z)
• Quantile Regression, Variational Autoencoders, and Diffusion Models for Uncertainty Quantification: A Spatial Analysis of Sub-seasonal Wind Speed Prediction [0.0]
  This study aims to improve the representation of uncertainties when regressing surface wind speeds from large-scale atmospheric predictors for sub-seasonal forecasting.<n>Probabilistic deep learning models offer promising solutions for capturing complex spatial dependencies.
  arXiv  Detail & Related papers  (2025-10-19T18:26:46Z)
• Diffusion-LAM: Probabilistic Limited Area Weather Forecasting with Diffusion [10.905169282633256]
  This work introduces Diffusion-LAM, a probabilistic limited area weather model leveraging conditional diffusion.<n>By conditioning on boundary data from surrounding regions, our approach generates forecasts within a defined area.<n> Experimental results on the MEPS limited area dataset demonstrate the potential of Diffusion-LAM to deliver accurate probabilistic forecasts.
  arXiv  Detail & Related papers  (2025-02-11T13:15:16Z)
• Weather Prediction with Diffusion Guided by Realistic Forecast Processes [49.07556359513563]
  We introduce a novel method that applies diffusion models (DM) for weather forecasting. Our method can achieve both direct and iterative forecasting with the same modeling framework. The flexibility and controllability of our model empowers a more trustworthy DL system for the general weather community.
  arXiv  Detail & Related papers  (2024-02-06T21:28:42Z)
• Deterministic Guidance Diffusion Model for Probabilistic Weather Forecasting [16.370286635698903]
  We introduce the textbftextitDeterministic textbftextitGuidance textbftextitDiffusion textbftextitModel (DGDM) for probabilistic weather forecasting.
  arXiv  Detail & Related papers  (2023-12-05T15:03:15Z)
• When Rigidity Hurts: Soft Consistency Regularization for Probabilistic Hierarchical Time Series Forecasting [69.30930115236228]
  Probabilistic hierarchical time-series forecasting is an important variant of time-series forecasting. Most methods focus on point predictions and do not provide well-calibrated probabilistic forecasts distributions. We propose PROFHiT, a fully probabilistic hierarchical forecasting model that jointly models forecast distribution of entire hierarchy.
  arXiv  Detail & Related papers  (2023-10-17T20:30:16Z)
• When Rigidity Hurts: Soft Consistency Regularization for Probabilistic Hierarchical Time Series Forecasting [69.30930115236228]
  Probabilistic hierarchical time-series forecasting is an important variant of time-series forecasting. Most methods focus on point predictions and do not provide well-calibrated probabilistic forecasts distributions. We propose PROFHiT, a fully probabilistic hierarchical forecasting model that jointly models forecast distribution of entire hierarchy.
  arXiv  Detail & Related papers  (2022-06-16T06:13:53Z)
• Distributional Gradient Boosting Machines [77.34726150561087]
  Our framework is based on XGBoost and LightGBM. We show that our framework achieves state-of-the-art forecast accuracy.
  arXiv  Detail & Related papers  (2022-04-02T06:32:19Z)
• Learning Interpretable Deep State Space Model for Probabilistic Time Series Forecasting [98.57851612518758]
  Probabilistic time series forecasting involves estimating the distribution of future based on its history. We propose a deep state space model for probabilistic time series forecasting whereby the non-linear emission model and transition model are parameterized by networks. We show in experiments that our model produces accurate and sharp probabilistic forecasts.
  arXiv  Detail & Related papers  (2021-01-31T06:49:33Z)
• A framework for probabilistic weather forecast post-processing across models and lead times using machine learning [3.1542695050861544]
  We show how to bridge the gap between sets of separate forecasts from NWP models and the 'ideal' forecast for decision support. We use Quantile Regression Forests to learn the error profile of each numerical model, and use these to apply empirically-derived probability distributions to forecasts. Second, we combine these probabilistic forecasts using quantile averaging. Third, we interpolate between the aggregate quantiles in order to generate a full predictive distribution.
  arXiv  Detail & Related papers  (2020-05-06T16:46:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.