Mosaic introduces mesh-aligned block-sparse attention and learned functional perturbations to preserve spectral fidelity in probabilistic 1.5° weather forecasts, matching or exceeding finer-resolution models while producing well-calibrated ensembles.
Rows 1–2 show RMSE, rows 3–4 show CRPS, and rows 5–6 show the spread-to-skill ratio (values close to 1.0 indicate well-calibrated ensembles)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
(Sparse) Attention to the Details: Preserving Spectral Fidelity in ML-based Weather Forecasting Models
Mosaic introduces mesh-aligned block-sparse attention and learned functional perturbations to preserve spectral fidelity in probabilistic 1.5° weather forecasts, matching or exceeding finer-resolution models while producing well-calibrated ensembles.