IPSL-AID is a high-performance research framework for climate data downscaling based on diffusion models, designed for GPU clusters and HPC systems.
- Kazem Ardaneh
- Kishanthan Kingston
- Pierre Chapel
Developed at IPSL / CNRS / Sorbonne University (2026)
Full documentation is available at: https://ipsl-aid.readthedocs.io/en/latest/
This software is licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
You are free to:
- Share — copy and redistribute the material in any medium or format
- Adapt — remix, transform, and build upon the material
Under the following terms:
- Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made.
- NonCommercial — You may not use the material for commercial purposes.
- ShareAlike — If you remix, transform, or build upon the material, you must distribute your contributions under the same license as the original.
Full license text is available in the LICENSE file or at: http://creativecommons.org/licenses/by-nc-sa/4.0/
For commercial licensing inquiries, please contact the authors.
This work was supported by the project S24JROI011 from the Grantham Foundation.
If you use IPSL-AID in your research, please cite:
BibTeX:
@article{kingston2026ipslaid_arxiv,
title={IPSL-AID: Generative Diffusion Models for Climate Downscaling from Global to Regional Scales},
author={K. Kingston and O. Boucher and F. Bouchet and P. Chapel and R. Eade and J.-F. Lamarque and R. Lguensat and K. Ardaneh},
journal={arXiv preprint},
year={2026},
eprint={arXiv:2604.03275},
note={\url{https://arxiv.org/abs/2604.03275}}
}