Varda-single-1.0: deterministic data-driven weather forecasting at 1 km resolution over Switzerland's complex topography

2026-10-01

AI Summary

This study addresses the challenge of high-resolution weather forecasting over Switzerland's complex terrain by developing a 1 km data-driven medium-range prediction system covering the Alpine region. Methodologically, it proposes a stretched-grid dual-model architecture with a multi-stage training strategy. Built upon the Anemoi framework, the approach integrates Graph Transformers within an encoder-processor-decoder structure and combines autoregressive modeling with temporal downscaling to achieve hourly regional and global forecasts. Experimental results demonstrate that the proposed system outperforms the operational MeteoSwiss baseline across most metrics and attains performance comparable to the 1 km ICON control run within a 33-hour forecast horizon. This work establishes an effective paradigm for high-fidelity meteorological simulation in complex topography.

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.

Problem

• data-driven weather forecasting
• complex topography
• high-resolution
• deterministic prediction
• Alpine domain

Innovation

• Graph Transformer
• stretched-grid
• data-driven weather forecasting
• temporal downscaler
• complex topography