Articles | Volume 18, issue 6
https://doi.org/10.5194/gmd-18-2051-2025
https://doi.org/10.5194/gmd-18-2051-2025
Development and technical paper
 | 
01 Apr 2025
Development and technical paper |  | 01 Apr 2025

Can AI be enabled to perform dynamical downscaling? A latent diffusion model to mimic kilometer-scale COSMO5.0_CLM9 simulations

Elena Tomasi, Gabriele Franch, and Marco Cristoforetti

Related authors

GPTCast: a weather language model for precipitation nowcasting
Gabriele Franch, Elena Tomasi, Rishabh Wanjari, Virginia Poli, Chiara Cardinali, Pier Paolo Alberoni, and Marco Cristoforetti
Geosci. Model Dev., 18, 5351–5371, https://doi.org/10.5194/gmd-18-5351-2025,https://doi.org/10.5194/gmd-18-5351-2025, 2025
Short summary

Cited articles

Abdalla, S., Isaksen, L., Janssen, P., and Wedi, N.: Effective spectral resolution of ECMWF atmospheric forecast models, ECMWF Newsletter, 137, 19–22, https://doi.org/10.21957/rue4o7ac, 2013. a
Addison, H., Kendon, E., Ravuri, S., Aitchison, L., and Watson, P. A.: Machine learning emulation of a local-scale UK climate model, arXiv [preprint], https://doi.org/10.48550/arXiv.2211.16116, 2022. a
Adinolfi, M., Raffa, M., Reder, A., and Mercogliano, P.: Investigation on potential and limitations of ERA5 Reanalysis downscaled on Italy by a convection-permitting model, Clim. Dynam., 61, 4319–4342, https://doi.org/10.1007/s00382-023-06803-w, 2023. a, b
Arjovsky, M. and Bottou, L.: Towards Principled Methods for Training Generative Adversarial Networks, in: International Conference on Learning Representations, Toulon, France, 24–26 April 2017, https://openreview.net/forum?id=Hk4_qw5xe (last access: 26 March 2025), 2017. a
ARPAE-SIMC: COSMO ARPAE-SIMC, http://www.cosmo-model.org/content/tasks/operational/cosmo/arpae-simc/default.htm, last access: 20 May 2024. a
Download
Short summary
High-resolution weather data are crucial for many applications, typically generated via resource-intensive numerical models through dynamical downscaling. We developed an AI model using latent diffusion models (LDMs) to mimic this process, increasing weather data resolution over Italy from 25 to 2 km. LDM outperforms other methods, accurately capturing local patterns and extreme events. This approach offers a cost-effective alternative, with potential disruptive application in climate sciences.
Share