Advancing the assimilation of Earth system observations with new methodology and Machine Learning
Data Assimilation continues to underpin all operational weather forecasting, initialising physics-based models as well as initialising and training data-driven models. The 2026 Annual Seminar will look at how the deployment of Machine Learning (ML) technology and innovative methodology is changing the way we assimilate observations for numerical weather prediction, atmospheric composition and climate reanalysis. Presentations will explore how highly efficient and accurate ML emulation is allowing a greater volume and variety of observations to be assimilated and an improved characterisation of uncertainty. Learning techniques which make better use of measurements with particularly challenging geophysical relationships will be demonstrated and how these can be used to improve our understanding of more complex physical processes. Finally, the seminar will look at innovative so-called end-to-end ML approaches which learn the entire assimilation process in a single step, latent space Data Assimilation and the production of forecasts directly from observations.
Attendance
The seminar is part of ECMWF's educational programme and is aimed at early career scientists as well as more established scientists.
Registration is now closed.
The talks will be livestreamed. The link will be published on this page closer to the time.