mlsanityData to 14 Oct 2026

Precipitation Downscaling with Spatiotemporal Video Diffusion

arXiv 2312.06071 ↗First posted 11 Dec 2023cs.CV cs.LG physics.ao-phcited by 19

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

Abstract (arXiv)

In climate science and meteorology, high-resolution local precipitation (rain and snowfall) predictions are limited by the computational costs of simulation-based methods. Statistical downscaling, or super-resolution, is a common workaround where a low-resolution prediction is improved using statistical approaches. Unlike traditional computer vision tasks, weather and climate applications require capturing the accurate conditional distribution of high-resolution given low-resolution patterns to assure reliable ensemble averages and unbiased estimates of extreme events, such as heavy rain. This work extends recent video diffusion models to precipitation super-resolution, employing a deterministic downscaler followed by a temporally-conditioned diffusion model to capture noise characteristics and high-frequency patterns. We test our approach on FV3GFS output, an established large-scale global atmosphere model, and compare it against six state-of-the-art baselines. Our analysis, capturing CRPS, MSE, precipitation distributions, and qualitative aspects using California and the Himalayas as examples, establishes our method as a new standard for data-driven precipitation downscaling.

Key facts. Cited by 19 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 49 of its 85 references that are in the map. First posted on arXiv 11 Dec 2023.

Builds on

49 of 85 references.

Closest ancestors · 3

Same direction, newest first

  1. 2023SEEDS: Emulation of Weather Forecast Ensembles with Diffusion Models24 Jun
  2. 2023Latent diffusion models for generative precipitation nowcasting with accurate uncertainty quantification25 Apr
  3. 2023Diffusion Models for High-Resolution Solar Forecasts1 Feb

Other references · 46

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  5. 2020Denoising Diffusion Implicit Modelscited by 9,781
  6. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  7. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  8. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  9. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  10. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  11. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,581
  12. 2022Video Diffusion Modelscited by 2,305
34 more
  1. 2020Transformers are RNNs: Fast Autoregressive Transformers with Linear Attentioncited by 2,022
  2. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,908
  3. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,887
  4. 2021Image Super-Resolution via Iterative Refinementcited by 1,511
  5. 2023Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Modelscited by 1,476
  6. 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,264
  7. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,224
  8. 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 903
  9. 2022FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operatorscited by 776
  10. 2017The Perception-Distortion Tradeoffcited by 587
  11. 2019Deep Learning for Image Super-resolution: A Surveycited by 369
  12. 2020PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Modelscited by 358
  13. 2023Denoising Diffusion Models for Plug-and-Play Image Restorationcited by 340
  14. 2021Skillful Precipitation Nowcasting using Deep Generative Models of Radarcited by 311
  15. 2022MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolationcited by 309
  16. 2020BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyondcited by 304
  17. 2022Flexible Diffusion Modeling of Long Videoscited by 294
  18. 2022Diffusion Probabilistic Modeling for Video Generationcited by 238
  19. 2022VRT: A Video Restoration Transformercited by 220
  20. 2022Recurrent Video Restoration Transformer with Guided Deformable Attentioncited by 170
  21. 2018Frame-Recurrent Video Super-Resolutioncited by 160
  22. 2022Rethinking Alignment in Video Super-Resolution Transformerscited by 71
  23. 2020Stochastic Super-Resolution for Downscaling Time-Evolving Atmospheric Fields with a Generative Adversarial Networkcited by 70
  24. 2019Efficient Video Super-Resolution through Recurrent Latent Space Propagationcited by 69
  25. 2022A Generative Deep Learning Approach to Stochastic Downscaling of Precipitation Forecastscited by 66
  26. 2017Towards Deeper Understanding of Variational Autoencoding Modelscited by 56
  27. 2020Video Super Resolution Based on Deep Learning: A Comprehensive Surveycited by 54
  28. 2022Increasing the accuracy and resolution of precipitation forecasts using deep generative modelscited by 35
  29. 2023Fourier Neural Operators for Arbitrary Resolution Climate Data Downscalingcited by 26
  30. 2022Machine learning emulation of a local-scale UK climate modelcited by 20
  31. 2023A Complete Recipe for Diffusion Generative Modelscited by 17
  32. 2023Efficient Integrators for Diffusion Generative Modelscited by 11
  33. 2021Insights from Generative Modeling for Neural Video Compressioncited by 9
  34. 2019Evaluating probabilistic forecasts of extremes using continuous ranked probability score distributionscited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 9; 2026: 8.

19 papers.

Sort:

By area:

  1. 2024Heavy-Tailed Diffusion Modelscited by 40
  2. 2025Elucidated Rolling Diffusion Models for Probabilistic Forecasting of Complex Dynamicscited by 13
  3. 2024A Generative Framework for Probabilistic, Spatiotemporally Coherent Downscaling of Climate Simulationcited by 12
  4. 2025Multimodal Atmospheric Super-Resolution With Deep Generative Modelscited by 8
  5. 2025Kolmogorov Arnold Neural Interpolator for Downscaling and Correcting Meteorological Fields from In-Situ Observationscited by 5
  6. 2025Spatiotemporal Pyramid Flow Matching for Climate Emulationcited by 4
  7. 2026Neural Stochastic Processes for Satellite Precipitation Refinementcited by 2
  8. 2025Control-Augmented Autoregressive Diffusion for Data Assimilationcited by 1
  9. 2025A PDE-Informed Latent Diffusion Model for 2-m Temperature Downscalingcited by 1
  10. 2025STLDM: Spatio-Temporal Latent Diffusion Model for Precipitation Nowcastingcited by 1
  11. 2025Investigating the Robustness of Extreme Precipitation Super-Resolution Across Climatescited by 0
  12. 2025Skillful Subseasonal-to-Seasonal Forecasting of Extreme Events with a Multi-Sphere Coupled Probabilistic Modelcited by 0
7 more
  1. 2026Longwang: Zero-Shot Global Spatiotemporal Precipitation Downscaling with a Latent Generative Priorcited by 0
  2. 2026Physics-Informed Super-Resolution of Atmospheric Datacited by 0
  3. 2026Precipitation Downscaling Using Foundation Model-Conditioned Diffusioncited by 0
  4. 2026Physics-Guided Flow-Map Matching for Precipitation Nowcastingcited by 0
  5. 2026Transformer-based In-Context Score Operator Learning for Diffusion Modelscited by 0
  6. 2026Characterizing and Mitigating Distributional Bias in Physics-Informed Generative Modelscited by 0
  7. 2026Deterministic Prediction as Global Velocity: Flow Matching for Probabilistic Time-Series Forecastcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Downscaling Precipitation with Bias-informed Conditional Diffusion Model
  2. 2025Efficient Kilometer-Scale Precipitation Downscaling with Conditional Wavelet Diffusion
  3. 2024Enhancing Weather Predictions: Super-Resolution via Deep Diffusion Models
  4. 2023Generating High-Resolution Regional Precipitation Using Conditional Diffusion Model
  5. 2024Conditional diffusion models for downscaling and bias correction of Earth system model precipitation
  6. 2026Universal Diffusion-Based Probabilistic Downscaling
  7. 2026A Scale-Adaptive Framework for Joint Spatiotemporal Super-Resolution with Diffusion Models
  8. 2025PrecipDiff: Leveraging image diffusion models to enhance satellite-based precipitation observations