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.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/gmd-18-2051-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
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
Data Science for Industry and Physics, Fondazione Bruno Kessler, via Sommarive 18, 38123 Trento (TN), Italy
Gabriele Franch
Data Science for Industry and Physics, Fondazione Bruno Kessler, via Sommarive 18, 38123 Trento (TN), Italy
Marco Cristoforetti
Data Science for Industry and Physics, Fondazione Bruno Kessler, via Sommarive 18, 38123 Trento (TN), Italy
Related authors
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
Short summary
Our research introduces GPTCast, a novel method for very short term precipitation forecasting using radar data. By applying advanced machine learning techniques inspired by large language models, we developed a system that generates accurate and realistic weather predictions. We trained the model using 6 years of radar data from northern Italy, demonstrating its superior performance over leading ensemble extrapolation methods.
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
Short summary
Our research introduces GPTCast, a novel method for very short term precipitation forecasting using radar data. By applying advanced machine learning techniques inspired by large language models, we developed a system that generates accurate and realistic weather predictions. We trained the model using 6 years of radar data from northern Italy, demonstrating its superior performance over leading ensemble extrapolation methods.
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
Baño-Medina, J., Manzanas, R., and Gutiérrez, J. M.: Configuration and intercomparison of deep learning neural models for statistical downscaling, Geosci. Model Dev., 13, 2109–2124, https://doi.org/10.5194/gmd-13-2109-2020, 2020. a
Baldauf, M., Seifert, A., Förstner, J., Majewski, D., Raschendorfer, M., and Reinhardt, T.: Operational Convective-Scale Numerical Weather Prediction with the COSMO Model: Description and Sensitivities, Mon. Weather Rev., 139, 3887–3905, https://doi.org/10.1175/MWR-D-10-05013.1, 2011. a
Bell, R., Spring, A., Brady, R., Andrew, Squire, D., Blackwood, Z., Sitter, M. C., and Chegini, T.: xarray-contrib/xskillscore: Release v0.0.23, Zenodo [code], https://doi.org/10.5281/zenodo.5173153, 2021. a, b
Buchhorn, M., Smets, B., Bertels, L., De Roo, B., Lesiv, M., Tsendbazar, N. E., Herold, M., and Fritz, S.: Copernicus Global Land Service: Land Cover 100m: collection 3: epoch 2015: Globe (V3.0.1), Zenodo [data set], https://doi.org/10.5281/zenodo.3939038, 2020. a
Carpentieri, A., Folini, D., Leinonen, J., and Meyer, A.: Extending intraday solar forecast horizons with deep generative models, Appl. Energ., 377, 124186, https://doi.org/10.1016/j.apenergy.2024.124186, 2023. a
CMCC: ERA5 downscaling @2.2 km over Italy, CMCC DDS [data set], https://doi.org/10.25424/cmcc/era5-2km_italy (last access: 23 February 2023), 2021. a
Copernicus: Copernicus Digital Elevation Model, AWS [data set], https://registry.opendata.aws/copernicus-dem (last access: 2 February 2023), 2023. a
Csiszar, I.: I-Divergence Geometry of Probability Distributions and Minimization Problems, Ann. Probab., 3, 146–158, https://doi.org/10.1214/aop/1176996454, 1975. a
De, A., Nandi, A., Mallick, A., Middya, A. I., and Roy, S.: Forecasting chaotic weather variables with echo state networks and a novel swing training approach, Knowl.-Based Syst., 269, 110506, https://doi.org/10.1016/j.knosys.2023.110506, 2023. a
Esser, P., Rombach, R., and Ommer, B.: Taming Transformers for High-Resolution Image Synthesis, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 12873–12883, https://doi.org/10.48550/arXiv.2012.09841, 2021. a, b, c
Falcon, W. and The PyTorch Lightning team: PyTorch Lightning, Zenodo [code], https://doi.org/10.5281/zenodo.3828935, 2019. a
Franch, G., Tomasi, E., and Cristoforetti, M.: DSIP-FBK/DiffScaler: LDM_res v1.0, Zenodo [code], https://doi.org/10.5281/zenodo.13356322, 2024. a
Giorgi, F., Jones, C., and Asrar, G. R.: Addressing climate information needs at the regional level: the Cordex framework, World Meteorological Organization (WMO) Bulletin, 58, 175, https://cordex.org/wp-content/uploads/2012/11/cordex_giorgi_wmo-1.pdf (last access: 26 March 2025), 2009. a
Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y.: Generative Adversarial Networks, arXiv [preprint], https://doi.org/10.48550/arXiv.1406.2661, 2014. a, b
Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y.: Generative adversarial networks, Commun. ACM, 63, 139–144, https://doi.org/10.1145/3422622, 2020. a, b, c
Goyal, P., Dollár, P., Girshick, R., Noordhuis, P., Wesolowski, L., Kyrola, A., Tulloch, A., Jia, Y., and He, K.: Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour, arXiv [preprint], https://doi.org/10.48550/arXiv.1706.02677, 2018. a
Guibas, J., Mardani, M., Li, Z., Tao, A., Anandkumar, A., and Catanzaro, B.: Efficient Token Mixing for Transformers via Adaptive Fourier Neural Operators, in: International Conference on Learning Representations, online, 25 April 2022, https://openreview.net/forum?id=EXHG-A3jlM (last access: 26 March 2025), 2022. a
Hersbach, H., Bell, B., Berrisford, P., Hirahara, S., Horányi, A., Muñoz-Sabater, J., Nicolas, J., Peubey, C., Radu, R., Schepers, D., Simmons, A., Soci, C., Abdalla, S., Abellan, X., Balsamo, G., Bechtold, P., Biavati, G., Bidlot, J., Bonavita, M., De Chiara, G., Dahlgren, P., Dee, D., Diamantakis, M., Dragani, R., Flemming, J., Forbes, R., Fuentes, M., Geer, A., Haimberger, L., Healy, S., Hogan, R. J., Hólm, E., Janisková, M., Keeley, S., Laloyaux, P., Lopez, P., Lupu, C., Radnoti, G., de Rosnay, P., Rozum, I., Vamborg, F., Villaume, S., and Thépaut, J.-N.: The ERA5 global reanalysis, Q. J. Roy. Meteor. Soc., 146, 1999–2049, https://doi.org/10.1002/qj.3803, 2020. a, b
Hersbach, H., Bell, B., Berrisford, P., Biavati, G., Horányi, A., Muñoz Sabater, J., Nicolas, J., Peubey, C., Radu, R., Rozum, I., Schepers, D., Simmons, A., Soci, C., Dee, D., and Thépaut, J.-N.: ERA5 hourly data on pressure levels from 1940 to present, Climate Data Store [data set], https://doi.org/10.24381/cds.bd0915c6, 2023a. a
Hersbach, H., Bell, B., Berrisford, P., Biavati, G., Horányi, A., Muñoz Sabater, J., Nicolas, J., Peubey, C., Radu, R., Rozum, I., Schepers, D., Simmons, A., Soci, C., Dee, D., and Thépaut, J.-N.: ERA5 hourly data on single levels from 1940 to present, Climate Data Store [data set], https://doi.org/10.24381/cds.adbb2d47, 2023b. a
Hewitson, B. and Crane, R.: Climate downscaling: techniques and application, Clim. Res., 7, 85–95, https://doi.org/10.3354/cr007085, 1996. a
Höhlein, K., Kern, M., Hewson, T., and Westermann, R.: A comparative study of convolutional neural network models for wind field downscaling, Meteorol. Appl., 27, e1961, https://doi.org/10.1002/met.1961, 2020. a, b, c
Ioffe, S., and Szegedy, C.: Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift, arXiv [preprint], https://doi.org/10.48550/arXiv.1502.03167, 2015. a
Isola, P., Zhu, J.-Y., Zhou, T., and Efros, A. A.: Image-To-Image Translation With Conditional Adversarial Networks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, 21–26 July 2017, https://openaccess.thecvf.com/content_cvpr_2017/papers/Isola_Image-To-Image_Translation_With_CVPR_2017_paper.pdf (last access: 26 March 2025), 2017. a, b
Jacob, D., Petersen, J., Eggert, B., Alias, A., Christensen, O. B., Bouwer, L. M., Braun, A., Colette, A., Déqué, M., Georgievski, G., Georgopoulou, E., Gobiet, A., Menut, L., Nikulin, G., Haensler, A., Hempelmann, N., Jones, C., Keuler, K., Kovats, S., Kröner, N., Kotlarski, S., Kriegsmann, A., Martin, E., van Meijgaard, E., Moseley, C., Pfeifer, S., Preuschmann, S., Radermacher, C., Radtke, K., Rechid, D., Rounsevell, M., Samuelsson, P., Somot, S., Soussana, J. F., Teichmann, C., Valentini, R., Vautard, R., Weber, B., and Yiou, P.: EURO-CORDEX: new high-resolution climate change projections for European impact research, Reg. Environ. Change, 14, 563–578, https://doi.org/10.1007/s10113-013-0499-2, 2014. a
Kingma, D. P. and Ba, J.: Adam: A Method for Stochastic Optimization, arXiv [preprint], https://doi.org/10.48550/arXiv.1412.6980, 2017. a, b
Kullback, S. and Leibler, R. A.: On Information and Sufficiency, Ann. Math. Stat., 22, 79–86, https://doi.org/10.1214/aoms/1177729694, 1951. a
Leinonen, J., Nerini, D., and Berne, A.: Stochastic Super-Resolution for Downscaling Time-Evolving Atmospheric Fields With a Generative Adversarial Network, IEEE T. Geosci. Remote, 59, 7211–7223, https://doi.org/10.1109/TGRS.2020.3032790, 2021. a, b
Li, L., Carver, R., Lopez-Gomez, I., Sha, F., and Anderson, J.: Generative emulation of weather forecast ensembles with diffusion models, Science Advances, 10, eadk4489, https://doi.org/10.1126/sciadv.adk4489, 2024. a
Maraun, D. and Widmann, M.: Statistical Downscaling and Bias Correction for Clim. Res., Cambridge University Press, https://doi.org/10.1017/9781107588783, 2018. a, b
Mardani, M., Brenowitz, N., Cohen, Y., Pathak, J., Chen, C.-Y., Liu, C.-C., Vahdat, A., Nabian, M. A., Ge, T., Subramaniam, A., Kashinath, K., Kautz, J., and Pritchard, M.: Residual corrective diffusion modeling for km-scale atmospheric downscaling, Commun. Earth Environ., 6, 124, https://doi.org/10.1038/s43247-025-02042-5, 2025. a, b, c, d, e, f, g, h
Mearns, L. O., Bukovsky, M., Pryor, S. C., and Magaña, V.: Downscaling of Climate Information, Springer International Publishing, Cham, 199–269, ISBN 978-3-319-65058-6, https://doi.org/10.1007/978-3-319-65058-6_8, 2018. a
Merizzi, F., Asperti, A., and Colamonaco, S.: Wind speed super-resolution and validation: from ERA5 to CERRA via diffusion models, Neural Comput. Appl., 36, 21899–21921, https://doi.org/10.1007/s00521-024-10139-9, 2024. a
Mescheder, L., Geiger, A., and Nowozin, S.: Which Training Methods for GANs do actually Converge?, arXiv [preprint], https://doi.org/10.48550/arXiv.1801.04406, 2018. a
Moser, B. B., Shanbhag, A. S., Raue, F., Frolov, S., Palacio, S., and Dengel, A.: Diffusion Models, Image Super-Resolution, and Everything: A Survey, IEEE T. Neur. Net. Lear., 1–21, https://doi.org/10.1109/tnnls.2024.3476671, 2024. a
Panofsky, H. and Brier, G.: Some Applications of Statistics to Meteorology, Earth and Mineral Sciences Continuing Education, College of Earth and Mineral Sciences, 224 pp., 1968. a
Pathak, J., Subramanian, S., Harrington, P., Raja, S., Chattopadhyay, A., Mardani, M., Kurth, T., Hall, D., Li, Z., Azizzadenesheli, K., Hassanzadeh, P., Kashinath, K., and Anandkumar, A.: FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators, arXiv [preprint], https://doi.org/10.48550/arXiv.2202.11214, 2022. a
Peifer, H.: European Environmental Agency Reference Grid, https://www.eea.europa.eu/data-and-maps/data/eea-reference-grids-2 (last access: 26 March 2025), 2018. a
Price, I. and Rasp, S.: Increasing the accuracy and resolution of precipitation forecasts using deep generative models, arXiv [preprint], https://doi.org/10.48550/arXiv.2203.12297, 2022. a
Pryor, S. and Hahmann, A.: Downscaling Wind, Oxford University Press, https://doi.org/10.1093/acrefore/9780190228620.013.730, 2019. a
Pulkkinen, S., Nerini, D., Pérez Hortal, A. A., Velasco-Forero, C., Seed, A., Germann, U., and Foresti, L.: Pysteps: an open-source Python library for probabilistic precipitation nowcasting (v1.0), Geosci. Model Dev., 12, 4185–4219, https://doi.org/10.5194/gmd-12-4185-2019, 2019. a, b, c
Raffa, M., Reder, A., Marras, G. F., Mancini, M., Scipione, G., Santini, M., and Mercogliano, P.: VHR-REA_IT Dataset: Very High Resolution Dynamical Downscaling of ERA5 Reanalysis over Italy by COSMO-CLM, Data, 6, 88, https://doi.org/10.3390/data6080088, 2021. a, b, c
Rampal, N., Gibson, P. B., Sood, A., Stuart, S., Fauchereau, N. C., Brandolino, C., Noll, B., and Meyers, T.: High-resolution downscaling with interpretable deep learning: Rainfall extremes over New Zealand, Weather and Climate Extremes, 38, 100525, https://doi.org/10.1016/j.wace.2022.100525, 2022. a, b
Ronneberger, O., Fischer, P., and Brox, T.: U-Net: Convolutional Networks for Biomedical Image Segmentation, in: Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, edited by: Navab, N., Hornegger, J., Wells, W. M., and Frangi, A. F., Springer International Publishing, Cham, 234–241, ISBN 978-3-319-24574-4, 2015. a
Rotach, M. W. and Zardi, D.: On the boundary-layer structure over highly complex terrain: Key findings from MAP, Q. J. Roy. Meteor. Soc., 133, 937–948, https://doi.org/10.1002/qj.71, 2007. a
Saharia, C., Ho, J., Chan, W., Salimans, T., Fleet, D. J., and Norouzi, M.: Image Super-Resolution via Iterative Refinement, IEEE T. Pattern Anal., 45, 4713–4726, https://doi.org/10.1109/TPAMI.2022.3204461, 2023. a, b
Salimans, T. and Ho, J.: Progressive Distillation for Fast Sampling of Diffusion Models, CoRR, abs/2202.00512, arXiv [preprint], https://doi.org/10.48550/arXiv.2202.00512., 2022. a
Seity, Y., Brousseau, P., Malardel, S., Hello, G., Bénard, P., Bouttier, F., Lac, C., and Masson, V.: The AROME-France Convective-Scale Operational Model, Mon. Weather Rev., 139, 976–991, https://doi.org/10.1175/2010MWR3425.1, 2011. a
Serafin, S., Adler, B., Cuxart, J., De Wekker, S. F. J., Gohm, A., Grisogono, B., Kalthoff, N., Kirshbaum, D. J., Rotach, M. W., Schmidli, J., Stiperski, I., Večenaj, Z., and Zardi, D.: Exchange Processes in the Atmospheric Boundary Layer Over Mountainous Terrain, Atmosphere, 9, 102, https://doi.org/10.3390/atmos9030102, 2018. a
Sharifi, E., Saghafian, B., and Steinacker, R.: Downscaling Satellite Precipitation Estimates With Multiple Linear Regression, Artificial Neural Networks, and Spline Interpolation Techniques, J. Geophys. Res.-Atmos., 124, 789–805, https://doi.org/10.1029/2018JD028795, 2019. a
Skamarock, W. C., Park, S.-H., Klemp, J. B., and Snyder, C.: Atmospheric Kinetic Energy Spectra from Global High-Resolution Nonhydrostatic Simulations, J. Atmos. Sci., 71, 4369–4381, https://doi.org/10.1175/JAS-D-14-0114.1, 2014. a
Sohl-Dickstein, J., Weiss, E. A., Maheswaranathan, N., and Ganguli, S.: Deep Unsupervised Learning using Nonequilibrium Thermodynamics, arXiv [preprint], https://doi.org/10.48550/arXiv.1503.03585, 2015. a, b
Sperati, S., Alessandrini, S., D'Amico, F., Cheng, W., Rozoff, C. M., Bonanno, R., Lacavalla, M., Aiello, M., Airoldi, D., Amaranto, A., Decimi, G., and Vergata, M. A.: A new Wind Atlas to support the expansion of the Italian wind power fleet, Wind Energy, 27, 298–316, https://doi.org/10.1002/we.2890, 2024. a
Stengel, K., Glaws, A., Hettinger, D., and King, R. N.: Adversarial Super-resolution of Climatological Wind and Solar Data, P. Natl. Acad. Sci. USA, 117, 16805–16815, https://doi.org/10.1073/pnas.1918964117, 2020. a, b
Stephan, K., Klink, S., and Schraff, C.: Assimilation of radar-derived rain rates into the convective-scale model COSMO-DE at DWD, Q. J. Roy. Meteor. Soc., 134, 1315–1326, https://doi.org/10.1002/qj.269, 2008. a
Thorarinsdottir, T. L., Gneiting, T., and Gissibl, N.: Using Proper Divergence Functions to Evaluate Climate Models, SIAM/ASA Journal on Uncertainty Quantification, 1, 522–534, https://doi.org/10.1137/130907550, 2013. a, b
Tomasi, E., Franch, G., and Cristoforetti, M.: Sample dataset for the models trained and tested in the paper “Can AI be enabled to dynamical downscaling? Training a Latent Diffusion Model to mimic km-scale COSMO-CLM downscaling of ERA5 over Italy”, Zenodo [data set], https://doi.org/10.5281/zenodo.12934521, 2024a. a
Tomasi, E., Franch, G., and Cristoforetti, M.: Pretrained models presented in the paper “Can AI be enabled to dynamical downscaling? Training a Latent Diffusion Model to mimic km-scale COSMO-CLM downscaling of ERA5 over Italy”, Zenodo [data set], https://doi.org/10.5281/zenodo.12941117, 2024b. a
Tomasi, E., Franch, G., and Cristoforetti, M.: 2000–2002 Dataset [1/7] for the models trained and tested in the paper “Can AI be enabled to dynamical downscaling? Training a Latent Diffusion Model to mimic km-scale COSMO-CLM downscaling of ERA5 over Italy”, Zenodo [data set], https://doi.org/10.5281/zenodo.12944960, 2024c. a
Tomasi, E., Franch, G., and Cristoforetti, M.: 2003–2005 Dataset [2/7] for the models trained and tested in the paper “Can AI be enabled to dynamical downscaling? Training a Latent Diffusion Model to mimic km-scale COSMO-CLM downscaling of ERA5 over Italy”, Zenodo [data set], https://doi.org/10.5281/zenodo.12945014, 2024d. a
Tomasi, E., Franch, G., and Cristoforetti, M.: 2006–2008 Dataset [3/7] for the models trained and tested in the paper “Can AI be enabled to dynamical downscaling? Training a Latent Diffusion Model to mimic km-scale COSMO-CLM downscaling of ERA5 over Italy”, Zenodo [data set], https://doi.org/10.5281/zenodo.12945028, 2024e. a
Tomasi, E., Franch, G., and Cristoforetti, M.: 2009–2011 Dataset [4/7] for the models trained and tested in the paper “Can AI be enabled to dynamical downscaling? Training a Latent Diffusion Model to mimic km-scale COSMO-CLM downscaling of ERA5 over Italy”, Zenodo [data set], https://doi.org/10.5281/zenodo.12945040, 2024f. a
Tomasi, E., Franch, G., and Cristoforetti, M.: 2012–2014 Dataset [5/7] for the models trained and tested in the paper “Can AI be enabled to dynamical downscaling? Training a Latent Diffusion Model to mimic km-scale COSMO-CLM downscaling of ERA5 over Italy”, Zenodo [data set], https://doi.org/10.5281/zenodo.12945050, 2024g. a
Tomasi, E., Franch, G., and Cristoforetti, M.: 2015–2017 Dataset [6/7] for the models trained and tested in the paper “Can AI be enabled to dynamical downscaling? Training a Latent Diffusion Model to mimic km-scale COSMO-CLM downscaling of ERA5 over Italy”, Zenodo [data set], https://doi.org/10.5281/zenodo.12945058, 2024h. a
Tomasi, E., Franch, G., and Cristoforetti, M.: 2018–2020 Dataset [7/7] for the models trained and tested in the paper “Can AI be enabled to dynamical downscaling? Training a Latent Diffusion Model to mimic km-scale COSMO-CLM downscaling of ERA5 over Italy”, Zenodo [data set], https://doi.org/10.5281/zenodo.12945066, 2024i. a
Vandal, T., Kodra, E., Ganguly, S., Michaelis, A., Nemani, R., and Ganguly, A. R.: DeepSD: Generating High Resolution Climate Change Projections through Single Image Super-Resolution, in: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD '17, Association for Computing Machinery, New York, NY, USA, 1663–1672, ISBN 9781450348874, https://doi.org/10.1145/3097983.3098004, 2017. a
von Storch, H., Zorita, E., and Cubasch, U.: Downscaling of Global Climate Change Estimates to Regional Scales: An Application to Iberian Rainfall in Wintertime, J. Climate, 6, 1161–1171, https://doi.org/10.1175/1520-0442(1993)006<1161:DOGCCE>2.0.CO;2, 1993. a
Wang, J., Liu, Z., Foster, I., Chang, W., Kettimuthu, R., and Kotamarthi, V. R.: Fast and accurate learned multiresolution dynamical downscaling for precipitation, Geosci. Model Dev., 14, 6355–6372, https://doi.org/10.5194/gmd-14-6355-2021, 2021. a
Wilby, R. and Wigley, T.: Downscaling general circulation model output: a review of methods and limitations, Prog. Phys. Geog., 21, 530–548, https://doi.org/10.1177/030913339702100403, 1997. a
Yadan, O.: Hydra – A framework for elegantly configuring complex applications, GitHub, https://github.com/facebookresearch/hydra (last access: 26 March 2025), 2019. a
Zhong, X., Du, F., Chen, L., Wang, Z., and Li, H.: Investigating transformer-based models for spatial downscaling and correcting biases of near-surface temperature and wind-speed forecasts, Q. J. Roy. Meteor. Soc., 150, 275–289, https://doi.org/10.1002/qj.4596, 2024. a
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.
High-resolution weather data are crucial for many applications, typically generated via...