The United Kingdom Atomic Energy Authority (UKAEA) and the United States Department of Energy’s Princeton Plasma Physics Laboratory (PPPL) have signed a Joint Declaration of Intent to explore linking their advanced fusion supercomputing platforms. This partnership, known as the SUNRISE–STELLAR-AI Federation, aims to use artificial intelligence to accelerate the development of fusion energy.
The agreement was made today, 14 September 2026, at the Global Fusion Policy Summit in London. The federation would connect UKAEA’s SUNRISE supercomputer with PPPL’s STELLAR-AI platform, allowing researchers to train AI models using results from both national laboratories and develop AI tools for future fusion power plants.
This collaboration would draw on experiments from UKAEA’s MAST Upgrade facility in Oxfordshire and PPPL’s NSTX-U facility in New Jersey. The goal is to combine supercomputing power and expertise to shorten the design cycle for future fusion power plants and make better use of existing experiments.
Joe Milnes, Executive Director for Engineering and Computing at UKAEA, stated that fusion needs partnerships to solve its scientific and engineering challenges. Jonathan Menard, Chief Scientist at PPPL, added that no single laboratory or nation will design a fusion power plant alone, highlighting the benefit of federating the computer platforms to accelerate the path to a compact fusion power plant.
Both MAST Upgrade and NSTX-U are compact spherical tokamaks with similar designs, which makes them well-suited for joint AI training. Combining data from different facilities can lead to more powerful machine-learning models that better capture underlying physics and help accelerate future fusion projects, including the UK’s Spherical Tokamak for Energy Production (STEP Fusion) and US concepts like PPPL’s Spherical Tokamak Advanced Reactor (STAR).
The federation also plans to develop the next generation of fusion and AI experts through training, workshops, research opportunities, and other international collaborations. Rob Akers, Director of Computing Programmes and Senior Fellow at UKAEA, noted that the collaboration would involve developing digital twins of both machines to support the design of future fusion power plants.