Advanced Computing in the Age of AI | Sunday, May 26, 2024

Jülich’s New AI Foundation Models Aim to Advance Scientific Applications 

April 22, 2024 -- Together with its partner institutions within the Helmholtz Association, Forschungszentrum Jülich aims to build a new generation of AI foundation models for science. The associated pilot projects are pioneering the development of foundation models to take the application of AI in science to a new level.

Credit: Oselote/Shutterstock

These projects are part of the newly established Helmholtz Foundation Model Initiative (HFMI), which receives funding of around € 23 million (~US$24.5 million) from the Helmholtz Association.

Two of the four selected pilot projects are coordinated by Forschungszentrum Jülich. The researchers aim, for example, to develop one of the first AI foundation models for climate research, which will form the basis for one of the most precise weather and climate models in the world.

The use of AI should also help to pool the huge amount of new data and findings in materials research and thus accelerate the implementation of innovative solar cell concepts. In another pilot project involving Forschungszentrum Jülich, scientists aim to use a new AI foundation model to gain a better understanding of the global carbon cycle.

Foundation models are AI applications that, built upon a very broad knowledge base, are capable of solving a range of complex problems. The well-known chatbot ChatGPT from OpenAI is also based on such a model. Foundation models are significantly more powerful and flexible than traditional AI models, making them suitable for scientific applications. Through targeted training with extensive datasets and the use of generative AI, they can understand complex relationships based on learned patterns, generate new connections, and make predictions.

HClimRep: Capturing Interactions Between the Atmosphere, Ocean, and Sea Ice in a Novel Climate Model

What if we could make predictions about future climate even more accurately, quickly, and efficiently? Could we better combat the causes of climate change and mitigate its consequences as a result? Could we make the impacts of global warming impressively visible to everyone? The HClimRep project aims to answer exactly these questions.

By building one of the first AI foundation models for climate research, which combines data from the atmosphere, ocean, and sea ice, researchers are developing one of the most precise weather and climate models in the world. This deep-learning model, with billions of parameters, will be capable of conducting complex "what-if" experiments and other modeling tasks related to the ocean and atmosphere, thanks to extensive training on Europe's first exascale computer.

Participating Helmholtz Centers: Forschungszentrum Jülich, Alfred Wegener Institute, Helmholtz Center for Polar and Marine Research, Karlsruher Institute for Technology, and Helmholtz-Zentrum Hereon

Source: Forschungszentrum Jülich