An update on AI-DOP: skilful weather forecasts produced directly from observations
McNally, Tony ; Lessig, Christian ; Lean, Peter ; Boucher, Eulalie ; Alexe, Mihai ; Pinnington, Ewan ; Laloyaux, Patrick ; Lang, Simon ; Pinault, Florian ; Chantry, Matt ; Burrows, Chris ; Villeneuve, Ethel ; Chrust, Marcin ; Bormann, Niels ; Healy, Sean
Année de publication
2025
In a previous Newsletter article (McNally et al., 2024a), we described how ECMWF research teams are embarking on a radical and ambitious project to investigate if weather forecasts can be made directly from meteorological observations, harnessing the power of machine learning (ML). We have called the method Artificial Intelligence-Direct Observation Prediction (AI-DOP). In this issue we report on progress and the first-ever skilful medium-range forecasts made purely from observations alone, without any use of a physics-based model, analyses, or reanalyses.</p>
Accès à la notice sur le site du portail documentaire de Météo-France