– Collect the leading datasets in Earth system science, encompassing selected observations, analyses, and reanalyses, as well as the output of conventional Earth system model simulations and ancillary datasets. This will facilitate the understanding of climate-environment-society-economy correlations.

– Build the EarthGenerator as an extension of the WeatherGenerator to longer lead times and more Earth system components, to create a Foundation Model of the Earth system. It will be based on representation

– learning to use the full potential of Europe’s pre-exascale and exascale machines of EuroHPC.

– Validate and apply the EarthGenerator in strategic application domains, at both global and regional scales, over time scales from seasons to a few years. Among the case studies, we will consider extreme events in the ocean and atmosphere, the land carbon cycle, as well as impacts of climate change on food security and human migrations.

– Engage with the broader scientific community to maximize impact and adoption of the EarthGenerator, and to facilitate its application by external groups across Europe for a wide range of scientific and operational uses.

CMCC role
CMCC is the coordinator of the project.

Activities
CMCC is the coordinator of the project and is involved in the following activities:

• WP on Project Management and Coordination, which aims at ensuring the proper execution and implementation of the project.
• WP on Earth System Foundation Model Development and Training, which aims at extending and enhancing the encoder-decoder transformer architecture of the WeatherGenerator to applications on longer time-scales. We will start from the existing developments in the WeatherGenerator and extend them to allow for stable and well-calibrated predictions for time scales from seasonal to multi-annual and decadal. We will also combine the atmosphere, ocean and land components into a holistic model to create a full Earth system foundation model, the EarthGenerator, that provides a generic, task-independent representation of the Earth.
• WP on Communication, Dissemination and Community Engagement, which aims at promoting project results, fostering stakeholder engagement, and supporting the uptake of project outcomes by the wider scientific, policy, and user communities.

CMCC also contributes to the following activities:

Task 1.2 – Data collection, quality control and semantic annotation.
Task 1.4 – Ethical data generation.
Task 3.1 – Development of models for climate extremes and their impacts.
Task 3.3 – Development of models for early warning of food insecurity.
Task 3.4 – Development of models for climate-induced migration and displacement prediction.

Expected results

1. Develop the best Foundation Model of the Earth system to advance the understanding of the planet’s complex dynamics, enabling forecasting, reconstruction, downscaling, and simulation across seasonal to multi-annual timescales and different resolutions.
2. Create a Generative AI-based Foundation Model for the Earth system, building upon the existing WeatherGenerator model.
3. Create a foundation model of the Earth system, analogous to large language models in NLP but tailored to Earth sciences.
4. Improve forecasts for high-impact weather and long-term climate patterns; develop a prototype for early warning systems (EWSs) that predict food (in)security; integrate multimodal datasets to forecast human mobility.
5. Gather diverse datasets spanning atmosphere, ocean, and land; integrate climate data, terrestrial carbon and water cycles, and socio-economic factors.

Partners
ECMWF – European Centre for Medium-Range Weather Forecasts
FZJ – Forschungszentrum Jülich GmbH
DWD – Deutscher Wetterdienst
MPG – Max-Planck-Gesellschaft zur Förderung der Wissenschaften e.V.
Beyond Weather – Beyond Weather BV
AWI – Alfred-Wegener-Institut Helmholtz-Zentrum für Polar- und Meeresforschung
MEEO – Meteorological and Environmental Earth Observation Srl
CELEST – Celest Science
UVEG – Universitat de València
UCPH – Københavns Universitet
CSC – CSC – Tieteen tietotekniikan keskus Oy
McGill – Royal Institution for the Advancement of Learning (McGill University)

Linkedin