mlsanityData to 14 Oct 2026

Efficient Kilometer-Scale Precipitation Downscaling with Conditional Wavelet Diffusion

arXiv 2507.01354 ↗First posted 2 Jul 2025cs.LG physics.ao-phcited by 4

On the map: Diffusion models → Flow matching, time series and science

Abstract (arXiv)

Effective hydrological modeling and extreme weather analysis demand precipitation data at a kilometer-scale resolution, which is significantly finer than the 10 km scale offered by standard global products like IMERG. To address this, we propose the Wavelet Diffusion Model (WDM), a generative framework that achieves 10x spatial super-resolution (downscaling to 1 km) and delivers a 9x inference speedup over pixel-based diffusion models. WDM is a conditional diffusion model that learns the learns the complex structure of precipitation from MRMS radar data directly in the wavelet domain. By focusing on high-frequency wavelet coefficients, it generates exceptionally realistic and detailed 1-km precipitation fields. This wavelet-based approach produces visually superior results with fewer artifacts than pixel-space models, and delivers a significant gains in sampling efficiency. Our results demonstrate that WDM provides a robust solution to the dual challenges of accuracy and speed in geoscience super-resolution, paving the way for more reliable hydrological forecasts.

Key facts. Cited by 4 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 22 of its 70 references that are in the map. First posted on arXiv 2 Jul 2025.

Builds on

22 of 70 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025PrecipDiff: Leveraging image diffusion models to enhance satellite-based precipitation observations13 Jan
  2. 2024Dynamical-generative downscaling of climate model ensembles2 Oct
  3. 2024Diffusion Model-based Probabilistic Downscaling for 180-year East Asian Climate Reconstruction2 Feb
  4. 2023Residual Corrective Diffusion Modeling for Km-scale Atmospheric Downscaling24 Sep

Other references · 18

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2020Denoising Diffusion Implicit Modelscited by 9,781
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  5. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  6. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 3,045
  7. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
  8. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,979
  9. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,908
  10. 2020SRFlow: Learning the Super-Resolution Space with Normalizing Flowcited by 209
  11. 2022FourCastNet: Accelerating Global High-Resolution Weather Forecasting using Adaptive Fourier Neural Operatorscited by 188
  12. 2023Low-Light Image Enhancement with Wavelet-based Diffusion Modelscited by 127
6 more
  1. 2022Wavelet Diffusion Models are fast and scalable Image Generatorscited by 117
  2. 2023Parallel Sampling of Diffusion Modelscited by 112
  3. 2022A Generative Deep Learning Approach to Stochastic Downscaling of Precipitation Forecastscited by 66
  4. 2022Hard-Constrained Deep Learning for Climate Downscalingcited by 32
  5. 2021Fast and accurate learned multiresolution dynamical downscaling for precipitationcited by 18
  6. 2025PINS: Proximal Iterations with Sparse Newton and Sinkhorn for Optimal Transportcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026Bringing Agentic Search to Earth Observation Data Discoverycited by 1
  2. 2026Evaluating Cross-region Generalization for Wavelet-Diffusion Precipitation Downscalingcited by 0
  3. 2026RainAtlas: A Multi-Continental Dataset for Precipitation Downscalingcited by 0
  4. 2026Scale-Recursive Rectified Flows for Few-Step Precipitation Ensemblescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Precipitation Downscaling with Spatiotemporal Video Diffusion
  2. 2026Precipitation Downscaling Using Foundation Model-Conditioned Diffusion
  3. 2024Downscaling Precipitation with Bias-informed Conditional Diffusion Model
  4. 2024Conditional diffusion models for downscaling and bias correction of Earth system model precipitation
  5. 2023Generating High-Resolution Regional Precipitation Using Conditional Diffusion Model
  6. 2026Stress-Testing Dynamical and Generative Downscaling Using Subseasonal Extreme Precipitation Forecasts
  7. 2026Universal Diffusion-Based Probabilistic Downscaling
  8. 2023Unpaired Downscaling of Fluid Flows with Diffusion Bridges