# Downscaling weather forecasts from Low- to High-Resolution with Diffusion Models

arXiv: https://arxiv.org/abs/2604.03303 · HTML: https://mlsanity.com/paper/2604.03303/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Flow matching, time series and science, one of 14 directions in Diffusion models.
- Builds on 11 of its 25 references that are in the map.
- First posted on arXiv 30 Mar 2026.

## Placed in

- Diffusion models / [Flow matching, time series and science](https://mlsanity.com/diffusion/flow-matching-time-series-and-science/)

## Builds on (most cited first, 11 of 11)

- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [Understanding Diffusion Models: A Unified Perspective](https://mlsanity.com/paper/2208.11970/) (2022)
- [GraphCast: Learning skillful medium-range global weather forecasting](https://mlsanity.com/paper/2212.12794/) (2022)
- [Forecasting Global Weather with Graph Neural Networks](https://mlsanity.com/paper/2202.07575/) (2022)
- [Pangu-Weather: A 3D High-Resolution Model for Fast and Accurate Global Weather Forecast](https://mlsanity.com/paper/2211.02556/) (2022)
- [A Generative Deep Learning Approach to Stochastic Downscaling of Precipitation Forecasts](https://mlsanity.com/paper/2204.02028/) (2022)
- [Regional data-driven weather modeling with a global stretched-grid](https://mlsanity.com/paper/2409.02891/) (2024)
- [EnScale: Temporally-consistent multivariate generative downscaling via proper scoring rules](https://mlsanity.com/paper/2509.26258/) (2025)
- [Regional climate risk assessment from climate models using probabilistic machine learning](https://mlsanity.com/paper/2412.08079/) (2024)
- [RainShift: A Benchmark for Precipitation Downscaling Across Geographies](https://mlsanity.com/paper/2507.04930/) (2025)
- [A comparison of stretched-grid and limited-area modelling for data-driven regional weather forecasting](https://mlsanity.com/paper/2507.18378/) (2025)

## Built on by (most cited first, 2 of 2)

- [Precipitation Downscaling Using Foundation Model-Conditioned Diffusion](https://mlsanity.com/paper/2608.25858/) (2026)
- [Efficient Analog-Initialized Latent Transport for Spatially Coherent Probabilistic Downscaling from Global to Kilometer Scales](https://mlsanity.com/paper/2610.03736/) (2026)

## Abstract (arXiv)

We introduce a probabilistic diffusion-based method for global atmospheric downscaling implemented within the Anemoi framework. The approach transforms low-resolution ensemble forecasts into high-resolution ensembles by learning the conditional distribution of finer-scale residuals, defined as the difference between the high-resolution fields and the interpolated low-resolution inputs. The system is trained on reforecast pairs from ECMWF IFS, using coarse fields at 100 km to reconstruct fine-scale variability at 30 km resolution. The bulk of the training focuses on recovering small-scale structures, while fine-tuning in high-noise regimes enables the generation of extremes. Evaluation against the medium-range IFS ensemble target shows that the model increases probabilistic skill (FCRPS) for surface variables, reproduces target power spectra at small scales, captures physically consistent multivariate relationships such as wind-pressure coupling, and generates extreme values consistent with those of the target ensemble in tropical cyclones.