Varda-single-1.0: deterministic data-driven weather forecasting at 1 km resolution over Switzerland's complex topography
Year: 2026
Type: preprint
Abstract: We present Varda-single-1.0, a medium-range data-driven weather prediction system built for the Alpine domain. It provides hourly deterministic regional forecasts on a mesh of 1 km resolution and global forecasts on a 31 km mesh. The system comprises two independently trained stretched-grid Graph Transformer models with encoder-processor-decoder architecture, developed in the Anemoi framework: a 6-hourly autoregressive forecaster and a temporal downscaler reconstructing hourly forecasts between the forecaster's steps. Its training curriculum includes pre-training on ERA5 reanalysis data, followed by training on a 20-year kilometre-scale regional reanalysis, and finally fine-tuning on operational kilometre-scale analyses. Verified over one year against operational analyses and surface station observations, Varda-single is competitive with or improves on MeteoSwiss' operational numerical weather prediction baselines for most headline scores and variables. It broadly matches the skill of the high-resolution 1 km ICON-CH1-EPS control at lead times up to +33 h and generally outperforms the 2 km ICON-CH2-EPS control at lead times up to +120 h. Despite competitive aggregate scores, Varda-single underestimates some local wind maxima and produces overly smooth convective precipitation fields, consistent with the smoothing associated with squared-error training. To gain insight into the model's behaviour, we investigate three case studies beyond the aggregated headline scores, and find particular weaknesses in Varda-single's representation of local winds over complex terrain. Varda-single represents an important step in the development of high-resolution ML forecasting over complex terrain, in complementing the operational regional numerical weather prediction models of MeteoSwiss with data-driven models and in providing a pretrained model for researchers and user-specific applications.
Source: arXiv (Cornell University)
Authors: Pennino, Alberto, Zanetta, Francesco, Cattaneo, Michele, Merker, Claire, Radev, Radi, Bhend, Jonas, Frey, Louis, de Laroussilhe, Hugues, Miralles, Ophélia, Osuna, Carlos, Nerini, Daniele, Pauling, Andreas, Hupp, Daniel, Hamann, Ulrich, McGlohon, Mary, Bosch, Marti, Lanzilao, Luca, Arpagaus, Marco, Jansing, Lukas, Leuenberger, Daniel, Liniger, Mark A., Ehlert, Katrin, Chantry, Matthew, Haugen, Håvard Homleid, Mertes, Gert, Nemesio, Ana Prieto, Cruz, Mario Santa, Wijnands, Jasper, Moldovan, Gabriel, Cook, Harrison, Fuhrer, Oliver
Institutions: Federal Office of Meteorology and Climatology MeteoSwiss, ETH Zurich, Swiss Data Science Center, Center for Climate Systems Modeling, European Centre for Medium-Range Weather Forecasts, Norwegian Meteorological Institute, Royal Netherlands Meteorological Institute, Institute for Atmospheric and Climate Science
Language: English
Subfield: Atmospheric Science
Field: Earth and Planetary Sciences
Domain: Physical Sciences
SDG: Climate action
Open Access status: green
OpenAlex ID: W7215945999