Articles | Volume 18, issue 6
https://doi.org/10.5194/gmd-18-2051-2025
© Author(s) 2025. This work is distributed under the Creative Commons Attribution 4.0 License.
Can AI be enabled to perform dynamical downscaling? A latent diffusion model to mimic kilometer-scale COSMO5.0_CLM9 simulations
Download
- Final revised paper (published on 01 Apr 2025)
- Preprint (discussion started on 18 Sep 2024)
Interactive discussion
Status: closed
Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor
| : Report abuse
-
RC1: 'Comment on egusphere-2024-2646', Anonymous Referee #1, 08 Oct 2024
- AC1: 'Reply on RC1', Elena Tomasi, 13 Nov 2024
- AC3: 'Reply on RC1', Elena Tomasi, 20 Dec 2024
-
RC2: 'Comment on egusphere-2024-2646', Michael Langguth, 07 Nov 2024
- AC2: 'Reply on RC2', Elena Tomasi, 13 Nov 2024
- AC4: 'Reply on RC2', Elena Tomasi, 20 Dec 2024
Peer review completion
AR – Author's response | RR – Referee report | ED – Editor decision | EF – Editorial file upload
AR by Elena Tomasi on behalf of the Authors (22 Dec 2024)
Author's response
Author's tracked changes
Manuscript
ED: Publish as is (19 Jan 2025) by Fabien Maussion
AR by Elena Tomasi on behalf of the Authors (29 Jan 2025)
Author's response
Manuscript
General Comments
This study explores the use of Latent Diffusion Models (LDM_res) for downscaling low-resolution meteorological data, comparing it with UNET and GAN models. They Use ERA5 reanalysis data as input and COSMO_CLM high-resolution data as reference truth. The LDM_res model incorporates a residual approach, allowing it to focus on small-scale features while using a simpler model for large-scale patterns. The results show that LDM_res outperforms other models in reconstructing fine-scale details, spatial distributions, and frequency distributions, particularly for wind speed and temperature. A key innovation lies in the model's use of diffusion processes combined with the residual framework, which enhances accuracy while maintaining computational efficiency compared to traditional numerical models like COSMO_CLM. However, some questions remain regarding the experimental design and the analysis of results. Further analysis and clarification are required before publication.
Specific Comments
Minor Comments