AIFS ENS becomes operational
AIFS ENS devient opérationnel
Lang, Simon ; Magnusson, Linus
Année de publication
2025
In recent years, machine-learned (ML) weather forecasting systems such as FourCastNet, Pangu-Weather, GraphCast and the Artificial Intelligence Forecasting System (AIFS) have shown that they can produce highly skilful deterministic predictions that match or exceed those from physics-based models. These forecast models learn how to forecast by advancing the atmospheric state from one analysis date to the next during training. When in forecast mode, they run autoregressively - they evolve the atmospheric state forward in time from their own predictions.</p>
Accès à la notice sur le site du portail documentaire de Météo-France