Outline
ECMWF will host a live panel on 27 November 2026, under the Destination Earth (#DestinE) initiative of DG-CNECT at the European Commission. The session will explore the opportunities and challenges of developing coupled AI models for climate and Earth system modelling, as part of the online training course Machine Learning for Earth System Modelling: Applications and Future Directions.
This third and last course in ECMWF’s three-course ML learning pathway focuses on the technical foundations of machine learning for weather prediction. It explores how advanced AI-based methods are applied, evaluated and extended across real-world Earth system applications and emerging modelling approaches.
The panel will explore current developments and future directions in coupled AI climate modelling, bringing together different perspectives on the opportunities and challenges of extending AI-based modelling across the Earth system.
The discussion will consider the current state of the field, progress towards representing interactions between different Earth system components, and the scientific and technical challenges involved in developing more integrated AI-based modelling approaches.
The experts will reflect on where the field stands today, which capabilities are beginning to emerge, where important limitations remain, and what directions may shape the next generation of coupled AI models for weather and climate research.
The panel will be recorded and made available as part of Module 12 of the online training course.
Speakers
-
Claire Monteleoni, INRIA
-
Niklas Boers, Potsdam Institute for Climate Impact Research (PIL) and Technical University of Munich (TUM)
-
Nina Raoult, ECMWF
-
William Gregory, University College London (UCL)
Who should attend?
This event is aimed at researchers, practitioners, technical specialists, operational forecasters, climate and weather service professionals, and industry experts interested in coupled AI climate models and the future of AI-based Earth system modelling.
The event is open to the public and to learners of the course Machine Learning for Earth Systems Modelling: Applications and Future Directions. If you are following the course, you will still need to register here to attend the live panel.
Registration
Participation is free of charge. To register for the event, click the "Registration" link on the left side of this page.
More information
To find out more about our ML training under Destination Earth, take a look at our ML training page.
If you are interested, join the free online course Machine Learning for Earth Systems Modelling: Applications and Future Directions.
The panel will be recorded and made available shortly after the event on our YouTube channel, and accessible through our eLearning platform as part of the course.