mlsanityData to 7 Oct 2026

Unpaired Downscaling of Fluid Flows with Diffusion Bridges

arXiv 2305.01822 ↗First posted 2 May 2023cs.LG physics.flu-dyn physics.geo-phcited by 21

Not on the map. Why?

Abstract (arXiv)

We present a method to downscale idealized geophysical fluid simulations using generative models based on diffusion maps. By analyzing the Fourier spectra of images drawn from different data distributions, we show how one can chain together two independent conditional diffusion models for use in domain translation. The resulting transformation is a diffusion bridge between a low resolution and a high resolution dataset and allows for new sample generation of high-resolution images given specific low resolution features. The ability to generate new samples allows for the computation of any statistic of interest, without any additional calibration or training. Our unsupervised setup is also designed to downscale images without access to paired training data; this flexibility allows for the combination of multiple source and target domains without additional training. We demonstrate that the method enhances resolution and corrects context-dependent biases in geophysical fluid simulations, including in extreme events. We anticipate that the same method can be used to downscale the output of climate simulations, including temperature and precipitation fields, without needing to train a new model for each application and providing a significant computational cost savings.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). Builds on 32 of its 73 references that are in the map. First posted on arXiv 2 May 2023.

Builds on

32 of 73 references.

References · 32

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  5. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  6. 2022Generative Adversarial Networkscited by 5,603
  7. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  8. 2017Non-local Neural Networkscited by 2,290
  9. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  10. 2022Imagen Video: High Definition Video Generation with Diffusion Modelscited by 1,765
  11. 2018Group Normalizationcited by 1,514
  12. 2021Image Super-Resolution via Iterative Refinementcited by 1,506
20 more
  1. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,339
  2. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,315
  3. 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,036
  4. 2020Improved Techniques for Training Score-Based Generative Modelscited by 1,036
  5. 2019An Introduction to Variational Autoencoderscited by 997
  6. 2021Maximum Likelihood Training of Score-Based Diffusion Modelscited by 670
  7. 2020Contrastive Learning for Unpaired Image-to-Image Translationcited by 637
  8. 2021CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputationcited by 577
  9. 2021Solving Inverse Problems in Medical Imaging with Score-Based Generative Modelscited by 514
  10. 2019Deep Learning for Image Super-resolution: A Surveycited by 368
  11. 2022Understanding Diffusion Models: A Unified Perspectivecited by 337
  12. 2022Perception Prioritized Training of Diffusion Modelscited by 301
  13. 2022Dual Diffusion Implicit Bridges for Image-to-Image Translationcited by 212
  14. 2021Conditional Image Generation with Score-Based Diffusion Modelscited by 195
  15. 2022Generative Modelling With Inverse Heat Dissipationcited by 164
  16. 2022A Generative Deep Learning Approach to Stochastic Downscaling of Precipitation Forecastscited by 64
  17. 2022Verifying the Union of Manifolds Hypothesis for Image Datacited by 62
  18. 2022Increasing the accuracy and resolution of precipitation forecasts using deep generative modelscited by 35
  19. 2020ClimAlign: Unsupervised statistical downscaling of climate variables via normalizing flowscited by 25
  20. 2022Contrastive Learning for Climate Model Bias Correction and Super-Resolutioncited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 5; 2025: 7; 2026: 5.

21 papers.

Sort:

By area:

  1. 2023Residual Corrective Diffusion Modeling for Km-scale Atmospheric Downscalingcited by 103
  2. 2023Debias Coarsely, Sample Conditionally: Statistical Downscaling through Optimal Transport and Probabilistic Diffusion Modelscited by 33
  3. 2024Fast, Scale-Adaptive, and Uncertainty-Aware Downscaling of Earth System Model Fields with Generative Machine Learningcited by 26
  4. 2024Generative Diffusion-based Downscaling for Climatecited by 25
  5. 2023When Geoscience Meets Foundation Models: Towards General Geoscience Artificial Intelligence Systemcited by 13
  6. 2024A Generative Framework for Probabilistic, Spatiotemporally Coherent Downscaling of Climate Simulationcited by 11
  7. 2025Satellite Observations Guided Diffusion Model for Accurate Meteorological States at Arbitrary Resolutioncited by 9
  8. 2023Easing Color Shifts in Score-Based Diffusion Modelscited by 5
  9. 2024A probabilistic framework for learning non-intrusive corrections to long-time climate simulations from short-time training datacited by 5
  10. 2026Universal Diffusion-Based Probabilistic Downscalingcited by 5
  11. 2025GEN2: A Generative Prediction-Correction Framework for Long-time Emulations of Spatially-Resolved Climate Extremescited by 4
  12. 2026SerpentFlow: Generative Unpaired Domain Alignment via Shared-Structure Decompositioncited by 4
9 more
  1. 2024Response Theory via Generative Score Modelingcited by 3
  2. 2025Predicting Forced Responses of Probability Distributions via the Fluctuation-Dissipation Theorem and Generative Modelingcited by 3
  3. 2025Reframing Generative Models for Physical Systems using Stochastic Interpolantscited by 2
  4. 2025Data-driven Mesoscale Weather Forecasting Combining Swin-Unet and Diffusion Modelscited by 0
  5. 2025Physics-constrained generative machine learning-based high-resolution downscaling of Greenland's surface mass balance and surface temperaturecited by 0
  6. 2025AODDiff: Probabilistic Reconstruction of Aerosol Optical Depth via Diffusion-based Bayesian Inferencecited by 0
  7. 2026Generative Unsupervised Downscaling of Climate Models via Domain Alignment: Application to Wind Fieldscited by 0
  8. 2026Longwang: Zero-Shot Global Spatiotemporal Precipitation Downscaling with a Latent Generative Priorcited by 0
  9. 2026Stress-Testing Dynamical and Generative Downscaling Using Subseasonal Extreme Precipitation Forecastscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025A PDE-Informed Latent Diffusion Model for 2-m Temperature Downscaling
  2. 2024Conditional diffusion models for downscaling and bias correction of Earth system model precipitation
  3. 2024TAUDiff: Highly efficient kilometer-scale downscaling using generative diffusion models
  4. 2023Generating High-Resolution Regional Precipitation Using Conditional Diffusion Model
  5. 2025Guided Unconditional and Conditional Generative Models for Super-Resolution and Inference of Quasi-Geostrophic Turbulence
  6. 2025Km-scale dynamical downscaling through conformalized latent diffusion models
  7. 2026PODiff: Latent Diffusion in Proper Orthogonal Decomposition Space for Scientific Super-Resolution
  8. 2024Can AI be enabled to dynamical downscaling? A Latent Diffusion Model to mimic km-scale COSMO5.0CLM9 simulations