Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

IPSL-AID: Generative Diffusion Models for Climate Downscaling from Global to Regional Scales

Kishanthan Kingston, Olivier Boucher, Freddy Bouchet, Pierre Chapel, Rosemary Eade, Jean-Francois Lamarque, Redouane Lguensat, Kazem Ardaneh

Abstract

Effective adaptation and mitigation strategies for climate change require high-resolution projections to inform strategic decision-making. Conventional global climate models, which typically operate at resolutions of 150 to 200 kilometers, lack the capacity to represent essential regional processes. IPSL-AID is a global to regional downscaling tool based on a denoising diffusion probabilistic model designed to address this limitation. Trained on ERA5 reanalysis data, it generates 0.25 degree resolution fields for temperature, wind, and precipitation using coarse inputs and their spatiotemporal context. It also models probability distributions of fine-scale features to produce plausible scenarios for uncertainty quantification. The model accurately reconstructs statistical distributions, including extreme events, power spectra, and spatial structures. This work highlights the potential of generative diffusion models for efficient climate downscaling with uncertainty

IPSL-AID: Generative Diffusion Models for Climate Downscaling from Global to Regional Scales

Abstract

Effective adaptation and mitigation strategies for climate change require high-resolution projections to inform strategic decision-making. Conventional global climate models, which typically operate at resolutions of 150 to 200 kilometers, lack the capacity to represent essential regional processes. IPSL-AID is a global to regional downscaling tool based on a denoising diffusion probabilistic model designed to address this limitation. Trained on ERA5 reanalysis data, it generates 0.25 degree resolution fields for temperature, wind, and precipitation using coarse inputs and their spatiotemporal context. It also models probability distributions of fine-scale features to produce plausible scenarios for uncertainty quantification. The model accurately reconstructs statistical distributions, including extreme events, power spectra, and spatial structures. This work highlights the potential of generative diffusion models for efficient climate downscaling with uncertainty

Paper Structure

This paper contains 28 sections, 4 equations, 12 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Methodology overview
  3. Data, sampling strategy, and metrics
  4. Metrics
  5. Results and discussion
  6. Conclusions and limitations
  7. Acknowledgments
  8. Funding Statement
  9. Competing Interests
  10. Data Availability Statement
  11. Ethical Standards
  12. Author Contributions
  13. Generative diffusion model
  14. Preconditioning
  15. Architecture
  16. ...and 13 more sections

Figures (12)

  • Figure 1: An example of randomly sampled spatial blocks used during training of the global model
  • Figure 2: Surface plots are shown for T2m, 10U, 10V, and TP (columns 1 to 4). The rows, from top to bottom, represent the CU ERA5 input, the HR ERA5 reference, the model prediction, and the difference between the prediction and the HR reference. All panels correspond to 2021-01-01 06:00 UTC
  • Figure 3: Model evaluation for the complete 2021 evaluation dataset. Columns represent T2m, 10U, 10V, and TP, respectively. Rows display density scatter plots (top), PDFs (middle), and PSDs (bottom)
  • Figure 4: Spatial distribution of the MAE, averaged over the 2021 dataset, for the downscaled variables: T2m, 10U, 10V, and TP
  • Figure 5: Rank histograms for the 10-member diffusion ensemble. Columns show T2m, 10U, 10V, and TP. Red dashed lines mark the expected uniform frequency
  • ...and 7 more figures