$300 Million DOE Initiative Makes Fermilab a Leader in AI Science

The investment from the U.S. Department of Energy’s Genesis Mission will position Fermilab as a central hub for artificial intelligence-driven scientific advances and will fund a range of initiatives, including the Fermilab-led AI/ML project and eight other projects in which the institute is a key collaborator. Fermilab scientists will develop AI/ML-based resonance control algorithms designed to enable reliable, low-cost operation of particle accelerators, significantly improve performance, and advance discovery science. “Fermilab is honored to receive this support for advances in artificial intelligence as part of the Department of Energy’s Genesis Mission,” said Fermilab Director Norbert Holtkamp. “This investment strengthens our ability to accelerate scientific discovery, develop technology, and drive innovation.” The Genesis mission aims to unite government, industry, and academia to accelerate breakthroughs in energy, science, and national security through AI and advanced technologies.

AI/ML resonance control for accelerator performance

The Genesis Mission is an initiative of the U.S. Department of Energy. Beyond the broad application of AI, Fermilab is spearheading a focused effort to develop an AI/ML-based resonance control algorithm designed to improve the performance and reduce operating costs of particle accelerators. This effort is not just about speeding discovery. The goal is to provide reliable, low-cost accelerator operations across a variety of facilities. This project directly addresses critical challenges in superconducting radio frequency (SRF) accelerators, such as Fermilab’s Proton Improvement Program II (PIP-II). These powerful machines used to accelerate particles for research are susceptible to disturbances from vibrations and pressure fluctuations that affect the cavity’s resonant frequency. Precise control of this frequency is important for current and future accelerators, such as the Linac Coherent Light Source SC at SLAC National Laboratory and the Electron-Ion Collider (EIC) at Brookhaven National Laboratory. New algorithms promise to increase scientific output, extend the lifespan of key components, and streamline operations.

Anna Grassellino, chief technology officer and deputy laboratory director for Fermilab’s technology division, explained the potential impact: “Developing AI-powered controls for superconducting RF cavities can make future accelerators, such as our own PIP-II, more efficient, reliable, and autonomous, enabling higher scientific performance while reducing operational complexity.” Fermilab’s involvement extends beyond this lead project. The lab is a key collaborator on eight additional Genesis mission initiatives spanning neutrino physics, collider research, and advanced computing, expanding its impact across the national scientific community.

This investment strengthens our ability to accelerate scientific discovery, develop next-generation technologies and drive innovation at the forefront of particle physics and advanced technology.

Norbert Holtkamp, ​​Director of Fermilab

Fermilab is expanding its decades of leadership in particle physics through a series of projects funded by the Department of Energy’s Genesis mission aimed at integrating artificial intelligence and scientific discovery. Fermilab’s Tracy Marc confirmed the lab’s selection for a portfolio of initiatives that includes an AI/ML project led by Fermilab and eight other projects in which the lab is a key collaborator, placing the lab at the center of its mission objectives. These algorithms address the critical challenge of maintaining precise control of superconducting radio frequency (SRF) cavities that are essential components of accelerators such as Fermilab’s PIP-II, SLAC’s Linac Coherent Light Source SC, and Brookhaven National Laboratory’s Electron-Ion Collider (EIC). Microscopic vibrations and pressure fluctuations can destroy these cavities, and AI control is expected to alleviate these problems. These include projects focused on accelerating the analysis of electron-ion collider data, detecting anomalies in the CMS experiment, and accelerating discoveries with the Deep Neutrino Experiment (DUNE). Fermilab’s extensive data storage infrastructure, the Fermi Data Platform, also plays a critical role, providing the secure, large-scale data environment needed to support advanced AI research across American Science Cloud.

These awards recognize the significant opportunity to combine artificial intelligence and Fermilab’s world-leading expertise in superconducting accelerator technology.

Anna Grassellino, Chief Technology Officer and Deputy Director, Fermilab Technology Division

The lab extends decades of leadership in neutrino and collider physics by spearheading projects aimed at not just applying AI to existing workflows but fundamentally changing how scientific data is collected, analyzed, and used. The main focus is to improve the reliability and reduce the cost of particle accelerators. The Fermilab-led project will develop AI/ML-based resonance control algorithms to address the delicate balance required within superconducting radiofrequency cavities, which are susceptible to disruption by even the slightest environmental fluctuations.

Fermilab is honored to receive this support for advances in artificial intelligence as part of DOE’s Genesis Mission.

Norbert Holtkamp, ​​Director of Fermilab

Developing AI-driven controls for superconducting RF cavities can make future accelerators, such as our own PIP-II, more efficient, reliable, and autonomous, enabling higher scientific performance while reducing operational complexity.