mlsanityData to 7 Oct 2026

Machine learning emulation of precipitation from km-scale UK regional climate simulations using a diffusion model

arXiv 2407.14158 ↗First posted 19 Jul 2024physics.ao-ph cs.LGcited by 15

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

Abstract (arXiv)

High-resolution climate simulations are valuable for understanding climate change impacts. This has motivated use of regional convection-permitting climate models (CPMs), but these are very computationally expensive. We present a convection-permitting model generative emulator (CPMGEM), to skilfully emulate precipitation simulations by a 2.2km-resolution regional CPM at much lower cost. This utilises a generative machine learning approach, a diffusion model. It takes inputs at the 60km resolution of the driving global climate model and downscales these to 8.8km, with daily-mean time resolution, capturing the effect of convective processes represented in the CPM at these scales. The emulator is trained on simulations over England and Wales from the United Kingdom Climate Projections Local product, covering years between 1980 and 2080 following a high emissions scenario. The output precipitation has a similar spatial structure and intensity distribution as in the CPM simulations. The emulator is stochastic, which improves the realism of samples. We include some evidence about the emulator's skill for extreme events with return times up to ~100 years. We demonstrate successful transfer from a "perfect model" training setting to application using GCM variable inputs. It captures the main features of the simulated 21st century climate change, but exhibits some error in the magnitude. We also show that the method can be useful in situations with limited amounts of high-resolution data. Potential applications include producing high-resolution precipitation predictions for large-ensemble climate simulations and producing output based on different GCMs and climate change scenarios to better sample uncertainty.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 25 of its 90 references that are in the map. First posted on arXiv 19 Jul 2024.

Builds on

25 of 90 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024Can AI be enabled to dynamical downscaling? A Latent Diffusion Model to mimic km-scale COSMO5.0CLM9 simulations19 Jun
  2. 2024Conditional diffusion models for downscaling and bias correction of Earth system model precipitation5 Apr
  3. 2024Fast, Scale-Adaptive, and Uncertainty-Aware Downscaling of Earth System Model Fields with Generative Machine Learning5 Mar
  4. 2023Residual Corrective Diffusion Modeling for Km-scale Atmospheric Downscaling24 Sep

Other references · 21

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  5. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  6. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  7. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  8. 2023Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Modelscited by 1,465
  9. 2017Generative Adversarial Networks: An Overviewcited by 588
  10. 2024Lumiere: A Space-Time Diffusion Model for Video Generationcited by 450
  11. 2021SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Modelscited by 415
  12. 2021Skillful Precipitation Nowcasting using Deep Generative Models of Radarcited by 308
9 more
  1. 2022Flexible Diffusion Modeling of Long Videoscited by 294
  2. 2023Patch Diffusion: Faster and More Data-Efficient Training of Diffusion Modelscited by 131
  3. 2020Stochastic Super-Resolution for Downscaling Time-Evolving Atmospheric Fields with a Generative Adversarial Networkcited by 68
  4. 2022A Generative Deep Learning Approach to Stochastic Downscaling of Precipitation Forecastscited by 64
  5. 2022Physically Constrained Generative Adversarial Networks for Improving Precipitation Fields from Earth System Modelscited by 28
  6. 2017Intercomparison of Machine Learning Methods for Statistical Downscaling: The Case of Daily and Extreme Precipitationcited by 24
  7. 2022Machine learning emulation of a local-scale UK climate modelcited by 20
  8. 2023Algorithmic Hallucinations of Near-Surface Winds: Statistical Downscaling with Generative Adversarial Networks to Convection-Permitting Scalescited by 13
  9. 2023Transferability and explainability of deep learning emulators for regional climate model projections: Perspectives for future applicationscited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 4; 2026: 8.

15 papers.

Sort:

By area:

  1. 2024Kilometer-Scale Convection Allowing Model Emulation using Generative Diffusion Modelingcited by 32
  2. 2024A Generative Framework for Probabilistic, Spatiotemporally Coherent Downscaling of Climate Simulationcited by 11
  3. 2025RainShift: A Benchmark for Precipitation Downscaling Across Geographiescited by 5
  4. 2024TCP-Diffusion: A Multi-modal Diffusion Model for Global Tropical Cyclone Precipitation Forecasting with Change Awarenesscited by 4
  5. 2025DiffScale: Continuous Downscaling and Bias Correction of Subseasonal Wind Speed Forecasts using Diffusion Modelscited by 3
  6. 2026Physics-Constrained Adaptive Flow Matching for Climate Downscalingcited by 2
  7. 2026Diffusion models recover accurate mixture weights despite score function insensitivitycited by 2
  8. 2025On Global Applicability and Location Transferability of Generative Deep Learning Models for Precipitation Downscalingcited by 1
  9. 2026Assessing the Robustness of Climate Foundation Models under No-Analog Distribution Shiftscited by 1
  10. 2025Generating time-consistent dynamics with discriminator-guided image diffusion modelscited by 0
  11. 2026How Can Machine Learning Emulators Best Support Climate Science?cited by 0
  12. 2026Flow Matching for Convective-Scale Precipitation Downscalingcited by 0
3 more
  1. 2026Regional Climate Model Emulation with Diffusion Approaches: What is the Added Value of Generative Machine Learning?cited by 0
  2. 2026Precipitation Downscaling Using Foundation Model-Conditioned Diffusioncited by 0
  3. 2026Lightweight Probabilistic Downscaling from a Deterministic Base Modelcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024DiffESM: Conditional Emulation of Temperature and Precipitation in Earth System Models with 3D Diffusion Models
  2. 2024Diffusion-Based Joint Temperature and Precipitation Emulation of Earth System Models
  3. 2025Generating realistic global precipitation fields from modelled atmospheric circulation
  4. 2023DiffESM: Conditional Emulation of Earth System Models with Diffusion Models
  5. 2024Dynamical-generative downscaling of climate model ensembles
  6. 2023SEEDS: Emulation of Weather Forecast Ensembles with Diffusion Models
  7. 2023Generating High-Resolution Regional Precipitation Using Conditional Diffusion Model
  8. 2025HRRRCast: a data-driven emulator for regional weather forecasting at convection allowing scales