UPTAKE aims to facilitate the sustainable upscaling of carbon dioxide removal (CDR) methods by developing a set of robust strategies through technical, theoretical, and practical analysis accompanied by interactive dialogue within a CDR stakeholder forum. As a result, UPTAKE will develop a harmonised, comprehensive, inclusive, integrated, and transparent CDR knowledge inventory to evaluate a wide range of CDR technologies and methods, quantifying their national, European, and global costs, effectiveness, and removal potential as well as risks, constraints, and side-effects at different scales, and their prospects of technological progress. The UPTAKE approach will allow the assessment of geographical, sectoral, socioeconomic, demographic, and temporal trade-offs, co-benefits, and opportunities emerging from portfolios of different CDR methods. The enhanced socio-technical understanding of CDR methods will feed into an ensemble of state-of-the-art integrated assessment models (IAMs), which will help improve the integration of CDR methods given the EU policy objectives set for 2030, 2050, and beyond climate neutrality. UPTAKE will assess CDR governance and policy frameworks considering social acceptance, accountability, monitoring, and regulations for sustainable CDR rollout at scale. As a result, UPTAKE will generate an open and interactive CDR roadmap explorer to investigate strategies that are resilient to risks of failure and disruption, and minimise adverse impacts on society, economy, and the environment, aiming for a just, inclusive, and sustainable transition.

---

The project will build the WeatherGenerator – the world’s best generative Foundation Model of the Earth system – that will serve as a new Digital Twin for Destination Earth. The WeatherGenerator will be based on representation learning and create a general and versatile tool that models the dynamics of the Earth system based on a large variety of Earth system data. The WeatherGenerator will be task-independent and will improve results for a wide range of machine learning applications when compared to task specific machine learning tools. It will also be more resilient for climate applications when the underlying data distributions are changing, and it will lead to a significant reduction in computational costs and faster turnaround times. To achieve this, the project will: (1) Collect and use the most important datasets of Earth system science including data from Digital Twins of Destination Earth, selected observations, analysis and reanalysis datasets, and output of conventional Earth system models. (2) Build the WeatherGenerator as a novel representation learning- based machine learning tool that exploits the full potential of Europe’s largest supercomputers. (3) Engage with the wider community via services and apply the WeatherGenerator for 22 selected applications that can be integrated into the Destination Earth framework. The applications include global and local predictions, local downscaling, data assimilation, model post-processing, and impact applications in the domains of renewable energy, water, health and food. The project consortium that will build the WeatherGenerator consists of experts in machine learning, supercomputing and Earth system sciences, and includes