FuXi cascaded short-to-long-range weather prediction

What changed

Cascades separately fine-tuned forecast models for0–5,5–10 and10–15-day windows, using joint space-time embedding and a U-Transformer to reduce long-range autoregressive errors.

Scientific scope

Cascades separately fine-tuned forecast models for0–5,5–10 and10–15-day windows, using joint space-time embedding and a U-Transformer to reduce long-range autoregressive errors. First two authors equal, final two correspondence. Original deterministic cascade is not the later FuXi ensemble/probabilistic system. Comparability with ECMWF ensemble mean concerns selected evaluation metrics, not equivalent calibrated uncertainty or every field. Error accumulation persists; reference datasets and ERA5 split constrain comparisons.

Evidence

The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. First two authors equal, final two correspondence. Original deterministic cascade is not the later FuXi ensemble/probabilistic system. Comparability with ECMWF ensemble mean concerns selected evaluation metrics, not equivalent calibrated uncertainty or every field. Error accumulation persists; reference datasets and ERA5 split constrain comparisons.

Contributors

• Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.

• FuXi: A cascade machine learning forecasting system for 15-day global weather forecast

Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.

Full scientific record · Browse contribution grades · Request a correction