ARTIFICIAL INTELLIGENCE FOR ENHANCED REPRESENTATION OF PROCESSES AND EXTREMES IN EARTH SYSTEM MODELS (AI4PEX)

The overarching goal of AI4PEX is to deliver enhanced knowledge on the Earth system by integrating Earth Observations, Artificial Intelligence, and Machine Learning into Earth system modelling and analysis in a yet unprecedented way to pave the way towards more reliable climate projections at global and regional scale.
AI4PEX aims to advance our collective understanding by improving the representation of processes in three domains – atmosphere, ocean and land – underpinning the main uncertainties in Earth system feedbacks and through this, support the development of robust climate mitigation and adaptation strategies from multi-decadal to longer time scales. AI4PEX will develop innovative techniques, model-data integration strategies and data-driven models to accurately and efficiently assess and study Earth system feedbacks and extremes.

AI4PEX will follow a synergistic approach to achieve this goal through the following objectives:

Advancing process representation. Improve the understanding and representation of key processes underpinning the most uncertain feedbacks in the Earth system by maximising observational data utilisation via AI-enhanced physically-aware ESM development.
Assessing future risks of extremes. Project future changes in climate extremes and associated risks based on the most up-to-date projections and ML-based approaches, supported by a better understanding of the links between climate variability and extremes, and their impacts on land and coastal waters.
Delivering tools for resilience. Develop robust, agile, fast and exchangeable workflows for the integration of EO and ML into Earth system science, modelling and analysis, including support for capacity building, transferability, and clear and engaging dissemination of new knowledge to society.

AI4PEX brings together an interdisciplinary team of experts from 20 European institutions to bridge Earth Observation and ESMs via advanced data science approaches. This will deliver improved knowledge and representation of future warming rates and climate sensitivity in the Earth system, with cascading effects in the regimes of climate extremes.