We introduce GraphDOP, a new data-driven, end-to-end forecast system developed at the European Centre for Medium-Range Weather Forecasts (ECMWF) that is trained and initialised exclusively from Earth System observations, with no physics-based (re)analysis inputs or feedbacks. GraphDOP learns the correlations between observed quantities - such as brightness temperatures from polar orbiters and geostationary satellites - and geophysical quantities of interest (that are measured by conventional observations), to form a coherent latent representation of Earth System state dynamics and physical processes, and is capable of producing skilful predictions of relevant weather parameters up to five days into the future.
@article{arxiv.2412.15687,
title = {GraphDOP: Towards skilful data-driven medium-range weather forecasts learnt and initialised directly from observations},
author = {Mihai Alexe and Eulalie Boucher and Peter Lean and Ewan Pinnington and Patrick Laloyaux and Anthony McNally and Simon Lang and Matthew Chantry and Chris Burrows and Marcin Chrust and Florian Pinault and Ethel Villeneuve and Niels Bormann and Sean Healy},
journal= {arXiv preprint arXiv:2412.15687},
year = {2024}
}