Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain
the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in
Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles
and JavaScript.
This report provides a summary of the main outcomes of the 3rd edition of the workshop on Machine Learning (ML) for Earth System Observation and Prediction (ESOP/ML4ESOP) co-organised by the European Centre for Medium-Range Weather Forecasts (ECMWF) and European Space Agency (ESA). The 4-day workshop was held on 14-17 November 2022 in hybrid format, with an in-person component at the ECMWF Reading site and an interactive online component, attracting a record number of submissions and over 700 registrations. The workshop aimed to document the current state-of-the-art, progress and challenges in the rapidly evolving field of the integration of ML technologies in ESOP and to provide a venue for discussion and collaboration for ESOP and ML specialists. The workshop was structured along five main thematic areas covering the principal components of standard ESOP workflows. Highlights from the presentations and a discussion of the most promising development directions from the workshop Working Groups in all the different thematic areas are provided in this Report.
