Particle accelerators are powerful tools that have revolutionized research in physics, chemistry, materials science, and biology, and are employed in applications that improve medicine, national security, and manufacturing. The Multi-Office Particle Accelerator Team (MOAT) deploys artificial intelligence tools to optimize and transform the way accelerators are designed and run, making them more efficient and effective.
The effort is part of the Genesis Mission, a new national initiative led by the Department of Energy that aims to accelerate advances and discoveries in AI and provide solutions to science, energy and national security challenges. The cornerstone of the Genesis mission is the Transformative AI Model Consortium (ModCon), which leverages DOE’s unique data, facilities, and expertise to build and deploy self-improving AI models. MOAT is one of three AI modeling teams led or playing a key role at Lawrence Berkeley National Laboratory (Berkeley Lab), building on AI expertise in high-performance computing, managing large datasets, and partnering with industry to pioneer AI models.
The project leverages vast amounts of experimental data, simulations, and expertise from the Department of Energy’s Office of Science’s accelerators and light sources, which make up half of the agency’s user facilities. MOAT builds and extends tools such as digital twins, intelligent assistants, and advanced AI models to simulate complex accelerator physics and behavior. It is also platform agnostic, allowing shared knowledge and improvements to be adopted by national laboratories, universities, and industry partners.
“By creating intelligent AI tools that continuously learn and work across facilities and disciplines, we are accelerating the discoveries that particle accelerators can enable in key applications such as fundamental physics, fission and fusion energy, advanced materials, and advanced medical technology,” said Jean-Luc Bey, director of MOAT and director of the Advanced Modeling Program in Berkeley Lab’s Accelerator Technology and Applied Physics (ATAP) division.
In its early stages, MOAT will build on recent successes led by ATAP and collaborators in bringing an AI “accelerator assistant” to Berkeley Lab’s Advanced Light Source (ALS). Powerful particle accelerators accelerate electrons around a circular ring, where they emit ultraviolet or X-ray light, and are used to conduct hundreds of experiments each year in research in physics, materials science, biology, chemistry, and more. Complex systems have hundreds of thousands of variables.
Researchers have demonstrated for the first time that an AI system driven by a large-scale language model can autonomously prepare and run multi-step physics experiments on a synchrotron light source, and can set up experiments 100 times faster than a human alone. Engineers use natural language to tell the accelerator assistant their goals. The AI can then find different variables, generate and run code to analyze data, visualize results, and safely interact with the accelerator itself.
“We are witnessing the emergence of a new layer of scientific infrastructure: AI systems that can interpret intentions, plan actions, and safely operate complex equipment,” said Torsten Herert, ATAP staff scientist and lead author of a paper on the recent milestone study. “This approach can accelerate experimentation at ALS today and form the foundation for connected, AI-enabled facilities across the DOE complex.”
In the first phase of MOAT, researchers are generalizing the framework and testing it across multiple accelerator facilities to demonstrate interoperability and shared AI infrastructure between sites.
MOAT currently includes collaborators from Argonne, Brookhaven, Fermi, Jefferson, Oak Ridge, and SLAC National Laboratories, as well as industry partners.
###
Lawrence Berkeley National Laboratory (Berkeley Lab) is engaged in groundbreaking research focused on discovery science and solutions for an abundant and reliable energy supply. The laboratory’s expertise spans materials, chemistry, physics, biology, earth and environmental sciences, mathematics, and computing. Researchers from around the world utilize the Institute’s world-class scientific facilities to conduct their own pioneering research. Founded in 1931 on the belief that the biggest problems are best tackled by teams, Berkeley Lab and its scientists have won 17 Nobel Prizes. Berkeley Lab is a multiprogram national laboratory managed by the University of California for the U.S. Department of Energy’s Office of Science.
The DOE Office of Science is the largest supporter of basic research in the physical sciences in the United States, working to address some of the most pressing challenges of our time. For more information, visit energy.gov/science.
