U.S. Department of Energy invests in Fermilab projects to accelerate AI-enabled scientific discovery

The Department of Energy announced today the list of projects that will receive funding through the Genesis Mission: Transforming Science and Energy with AI. Fermi National Accelerator Laboratory was selected for a portfolio of initiatives, including the AI/ML project led by Fermilab and eight others in which the lab is a key collaborator. These awards position Fermilab as a strong contributor to the Genesis Mission and demonstrate the lab’s leadership in applying artificial intelligence and advanced technologies to accelerate scientific discovery.

“Fermilab is honored to receive this support for advancing artificial intelligence as part of DOE’s Genesis Mission. This investment strengthens our ability to accelerate scientific discovery, develop next‑generation technologies, and drive innovation at the frontiers of particle physics and advanced technology,” Fermilab Director Norbert Holtkamp said. “We are proud to contribute our expertise to a mission that will help shape the next era of U.S. leadership in science and technology.”

The Fermilab-led project will develop AI/ML-based resonance control algorithms to enable high-reliability, low-cost accelerator operations that will substantially improve the performance of particle accelerators that drive discovery science. Several partner institutions, including national labs, universities and industry partner xLight Inc., are contributing to this project.

The Genesis Mission is a historic national initiative led by the U.S. Department of Energy, which is building the world’s most powerful integrated science discovery platform. By uniting government, industry, academia and philanthropy, it is accelerating breakthroughs in energy, scientific discovery and national security through a new platform that combines AI, supercomputing, quantum systems and advanced scientific instruments.

The projects named today will receive funding through a Request For Applications (RFA) that was announced by DOE in March. The goal of the Phase I RFA awards is to identify promising pathways toward transformative scientific capabilities and establish a foundation for future investment and scale. Fermilab project teams will design and demonstrate research workflows that integrate AI with scientific investigation, while rigorously evaluating whether those approaches can accelerate discovery, improve predictive capabilities, enhance experimentation, or generate new scientific insights.

Fermilab participated in today’s Genesis Mission Summit as a recipient of a first‑round Genesis Mission award, underscoring its leadership in advanced accelerator technologies as the Department of Energy announced the selected projects.

The AI/ML algorithms that will emerge from the Fermilab-led project will increase science reach, improve stability for users, increase radio-frequency amplifier lifetime and reduce operating costs. Superconducting radio-frequency (SRF) cavities are electromagnetic resonators that transfer energy to beams in particle accelerators. Because they are extremely efficient resonators, they can be disturbed by small vibrations and pressure fluctuations. For current and future SRF-based accelerators like Fermilab’s Proton Improvement Plan-II (PIP-II) linear accelerator, SLAC National Laboratory’s Linac Coherent Light Source-SC, Brookhaven National Laboratory’s Electron-Ion Collider (EIC), Michigan State University’s Facility for Rare Isotope Beams, Argonne National Laboratory’s Argonne Tandem Linac Accelerator System, and industrial accelerators, it is vitally important to have precise control of the cavity resonant frequency.

“These awards recognize the tremendous opportunity to combine artificial intelligence with Fermilab’s world-leading expertise in superconducting accelerator technology,” said Anna Grassellino, chief technology officer and associate laboratory director for the Technology Directorate at Fermilab. “By developing AI-driven control of superconducting RF cavities, we can make future accelerators — such as our own PIP-II — more efficient, reliable, and autonomous, enabling higher scientific performance while reducing operational complexity. This is an important step toward a new generation of intelligent accelerator facilities that will power discoveries across particle physics and many other fields of science.” 

Fermilab will contribute as a key collaborator on several other projects aligned with core research areas of the lab such as neutrino and collider physics, the muon-to-electron-conversion experiment (Mu2e), precision frontier, the Electron-Ion Collider and advanced scientific computing. The following projects were selected for funding through the Genesis Mission:

• How AI will expedite discovery in highly complex electron-ion collider data streams
  Lead institution: Purdue University
• Using an AI-driven approach to detect anomalies in the CMS Level-1 Scouting System
  Lead institution: University of Colorado
• Standardizing and advancing high-performance computing workloads using AI
  Lead institution: University of Wisconsin-Madison
• Using agentic workflows for the expedited search and discovery of charged lepton flavor violation in Mu2e
  Lead institution: University of South Carolina
• Deployment of advanced AI accelerated systems to detect, identify, classify and communicate supernova events in real time for the Deep Underground Neutrino Experiment (DUNE)
  Lead institution: Duke University
• The use of AI agents for high-energy physics simulations and analysis operations
  Lead institution: University of Alabama
• Accelerating DUNE physics with AI to discover neutrino interaction uncertainties
  Lead institution: Florida State University
• Physics-driven digital twins simulations for fusion magnet systems
  Lead institution: Lawrence Berkeley National Laboratory

Fermilab is an international leader in particle accelerator science research, which generates massive streams of data for scientific discovery using accelerator and detector technologies. The lab’s high-energy physics research creates unique opportunities for AI innovations. That is why researchers are developing and implementing AI tools to improve the precision of measurements, optimizing operations and accelerating discovery.

Neutrino Day 2026

The U.S. Department of Energy’s Fermi National Accelerator Laboratory (Fermilab) recently achieved an important milestone by safely positioning the first major piece of equipment for the new Proton Improvement Plan (PIP-II) linear accelerator.

The radio-frequency quadrupole, or RFQ, will serve as the heart of the front end of the PIP-II’s state-of-the-art superconducting radio-frequency linear accelerator, or linac. It will power a high-energy particle beam for the Deep Underground Neutrino Experiment at the Long-Baseline Neutrino Facility, Fermilab’s flagship international experiment. Neutrinos in the beam will travel 800 miles through Earth from Batavia, Illinois, to Lead, South Dakota, where DUNE’s massive underground detectors will study the behavior of these elusive particles. DUNE is a world-leading neutrino experiment driving new technologies and capable of pushing the boundaries of scientific discovery.

During the delicate move, the RFQ was placed on a purpose-made transport fixture and driven to the PIP-II site at a careful speed of 5 miles per hour. Once the RFQ reached the newly completed High Bay Building, it was craned down 30 feet to the tunnel level and wheeled into place.

“2026 marks a significant milestone for the PIP-II project. As we accelerate cryomodule production across the United States, U.K. and France, our team is beginning installation of the warm front end in the newly completed facility,” said PIP-II Project Director Cristian Boffo. “The RFQ is the first essential component placed in the pit, marking the beginning of the PIP-II installation phase.”

Because the RFQ is the largest single beamline component in PIP-II’s warm front end, it must be installed first. This allows for maximum space and flexibility.

The PIP-II linac will consist of 23 accelerating devices called cryomodules that gradually power a beam of H-minus ions to 800 million electron volts, or MeV, over its 215-meter length.

“The RFQ handles one of the trickiest regimes, where the beam’s energy is low and the velocity is changing a lot,” said Curt Baffes, linac installation manager for PIP-II. “Seeing this machine come to life is extremely rewarding.”

The 4-meter-long RFQ is made of copper and — unlike the rest of the linac — operates at room temperature.

Next, teams will interface the RFQ with the water-cooling, high-power radio-frequency and vacuum systems, a process expected to take the rest of 2026. In 2027, they will start to apply power to the RFQ to prepare for the first parts of beam commissioning, a slow and steady process that involves turning on one part of the system at a time.

“The last time we built a linac was in the 1960s, and it served the lab for all of this time. What we’re building now will set Fermilab up for the next 50 to 60 years.”

“The last time we built a linac was in the 1960s, and it served the lab for all of this time,” said Steve Dixon, PIP-II conventional facilities manager. “What we’re building now will set Fermilab up for the next 50 to 60 years.”

Other pieces of the PIP-II complex are also progressing. The coldbox and its compressors, key parts of the accelerator’s cryogenic system, arrived at the PIP-II site in January 2025 and were installed and interconnected with piping and electrical wiring. In recent weeks, the team received operational readiness clearance for the cryoplant and compressor room, another major milestone for PIP-II. Soon, they will begin commissioning the coldbox, a process that will take about six months.

Notably, the PIP-II linac is the first particle accelerator in the United States built with significant contributions from international partners, demonstrating the nation’s ability to host and lead major global scientific infrastructure projects. Institutions in France, India, Italy, Poland and the United Kingdom are contributing technologies, instrumentation and expertise to build the accelerator.

Over the next 50 years, the PIP-II linear accelerator will drive a broad physics research program beyond DUNE — and may even lead to benefits beyond physics.

For 70 years, physicists around the world have designed elaborate detectors and experiments to study a mysterious particle called the neutrino, with the U.S. Department of Energy’s Fermi National Accelerator Laboratory playing a leading role in this quest.

Since its founding in 1967, Fermilab scientists have pioneered multiple generations of experiments to learn more about the neutrino, what it could mean for our understanding of physics and its potential benefits for society. Today, Fermilab has embarked on a massive effort to integrate scientists, engineers, technicians, and partners across the globe to safely deliver the most comprehensive neutrino experiment in the world, the Deep Underground Neutrino Experiment at the Long Baseline Neutrino Facility.

Fermilab’s top institutional priority is delivering a neutrino beam to DUNE at LBNF by 2031. Once in operation, this experiment will allow scientists to delve even deeper into the mysteries of the neutrino and understand whether neutrinos could be the reason we live in a matter-dominated universe. DUNE at LBNF could also drive innovation in fields that include detector design, cryogenics, medical imaging and high-performance computing, resulting in benefits far beyond particle physics.

“For more than half a century, Fermilab has been at the forefront of unlocking the secrets of neutrinos — particles that hold some of the deepest clues about our universe.”

“For more than half a century, Fermilab has been at the forefront of unlocking the secrets of neutrinos — particles that hold some of the deepest clues about our universe,” said Fermilab Director Norbert Holtkamp. “Today, that legacy continues as we drive forward DUNE at LBNF. DUNE is the largest science project in our laboratory’s history, and its success will define the future of neutrino research for decades to come.”

Fermilab will produce the world’s most intense beam of neutrinos with the Proton Improvement Plan-II project using the PIP-II linear accelerator to send neutrinos from Fermilab in Illinois to Lead, South Dakota, 800 miles away. Underpinning all of the work on DUNE at LBNF, PIP-II and efforts across the lab to prepare to operate the experiment are disciplined execution and operational focus on safety, quality and schedule.

“The combination of size and precision in DUNE is unlike anything we’ve had before,” said Anne Schukraft, scientist in the Intensity Frontier Division at Fermilab. “I’m actually hoping that we find something that we cannot even think of now — something completely unexpected that changes the way we think about neutrinos and the Standard Model of particle physics.”

Decades of neutrino physics at Fermilab

After Fermilab began operations in 1967, it didn’t take long for it to take up the neutrino cause. Beginning with early experiments, including a 15-foot bubble chamber and the E1A experiment, the stage was set for neutrino research. Scientists at Fermilab discovered the tau neutrino, a third type of neutrino, through the Direct Observation of Nu Tau, or DONUT, experiment in 2000.

Leveraging the strength of Fermilab’s Tevatron —the most powerful particle accelerator in the world at the time — the NuTeV experiment made measurements in the late 1990s using beams of high energy neutrinos and antineutrinos.

“NuTeV was the culmination of a long series of precision neutrino experiments at Fermilab that used neutrinos to probe the structure of matter and the weak interaction,” said Bob Bernstein, Fermilab senior scientist and former NuTeV co-spokesperson. “It also helped train many of the scientists who went on to lead the next generation of neutrino experiments.”

With the completion of the Main Injector in 1999 — a 2-mile circular accelerator — and an intense beam of neutrinos called NuMI, Fermilab launched a new era of neutrino research that brought the MINOS, MINERvA and NOvA experiments.

MINERvA took data to study neutrino-nucleus interactions from 2010 to 2019, and physicists are still analyzing those data and publishing new results today.

MINOS, the lab’s first long-baseline neutrino experiment, provided some of the world’s most precise measurements of a phenomenon called neutrino oscillations, which describes how the neutrino’s flavor changes as it travels over space and time. It also laid the groundwork for future long-baseline neutrino experiments like DUNE.

NOvA, another crucial neutrino experiment hosted by Fermilab, is the only currently operating long-baseline neutrino experiment in the United States and is producing some of the most precise measurements of neutrino behavior. With its near detector at Fermilab and its far detector in Ash River, Minnesota, NOvA is taking data and measuring neutrino oscillations over a 500-mile distance.

“By increasing this travel distance to 800 miles, DUNE will take a giant leap forward in pushing such neutrino exploration into a new era of precision and discovery potential.”

“By increasing this travel distance to 800 miles, DUNE will take a giant leap forward in pushing such neutrino exploration into a new era of precision and discovery potential,” said Sam Zeller, Fermilab senior scientist and deputy project director for the DUNE at LBNF near detector.

Fermilab is the only facility in the world that simultaneously also operates a second accelerator-based beamline. This low energy Booster Neutrino Beam was born with MiniBooNE and has since expanded into the Short-Baseline Neutrino program, consisting of SBND, MicroBooNE and ICARUS. The short-baseline trio of experiments produces high-precision measurements, and it is designed to investigate the possible existence of a theorized fourth type of neutrino called sterile neutrino.

“We are one of the only facilities in the world that can produce neutrinos in an accelerator beam — in a controlled environment with high intensity,” said Schukraft.

While MicroBooNE stopped taking data in 2021, SBND and ICARUS are still active today. Future combined results promise to shed more light on the fourth-neutrino mystery.

Paving the way for innovation

All of Fermilab’s previous neutrino research and detector development has not only established the laboratory as a global leader in neutrino science, but also significantly contributed to DUNE. For example, MINOS paved the way as the world’s first long-baseline neutrino experiment. The SBN program’s liquid-argon time projection chambers provided a proving ground for the same technology that will be used in DUNE’s detectors.

“We are one of the only facilities in the world that can produce neutrinos in an accelerator beam — in a controlled environment with high intensity.”

Going forward, Fermilab researchers will continue to use neutrino research to drive innovation. For example, at DUNE, artificial intelligence tools will rapidly analyze millions of particle interactions, help identify rare signals such as early supernova signatures and support detector operations. Seventy years after neutrinos were first detected, Fermilab continues to lead the world in neutrino science. Through DUNE at LBNF, PIP-II and the expertise built through generations of discovery, Fermilab is delivering the scientific capabilities that will define the next era of particle physics and strengthen America’s leadership in discovery and innovation.

The U.S. Department of Energy’s Fermi National Accelerator Laboratory, host lab for the international Deep Underground Neutrino Experiment at the Long-Baseline Neutrino Facility, recently welcomed about 50 DUNE early-career researchers, facilitators and instructors for the first-ever Neutrino Physics Center-hosted DUNE Data Analysis School. The school is a major new initiative designed to prepare the next generations of scientists for the upcoming flagship experiment.

“DUNE has officially moved from vision to reality as installation at the underground site in South Dakota kicks off, and a critical parallel focus for the collaboration is ensuring we are absolutely ready to analyze our very first data.”

“DUNE has officially moved from vision to reality as installation at the underground site in South Dakota kicks off, and a critical parallel focus for the collaboration is ensuring we are absolutely ready to analyze our very first data,” said DUNE co-spokesperson Sowjanya Gollapinni. “This inaugural DUNE Data Analysis School hosted by NPC plays a key role in training our early-career members in the software and analysis tools needed to handle that initial data head on. Plus, a fantastic bonus outcome is that we now have our first-ever official curriculum that future schools can build upon!”

Modeled on Fermilab’s long-running CMS Data Analysis School, which is hosted by the LHC Physics Center at Fermilab, the weeklong program marked an important milestone in building the future scientific expertise needed as DUNE takes shape.

The school curriculum focuses on data analysis training tailored specifically for DUNE. Graduate students and postdoctoral researchers in DUNE, including new collaborators, are provided with hands-on training in the experiment’s software, including artificial intelligence and machine learning techniques, computing infrastructure and modern analysis workflows. Through lectures, tutorials and collaborative team projects, participants gain practical experience in simulation, reconstruction, event selection and the core tools essential for DUNE physics analyses.

Participants received intensive instruction from DUNE software, computing and analysis experts with preparatory computing sessions offered in advance. The program of practical, structured lessons allowed early-career DUNE scientists to get up to speed faster so that they can rapidly begin preparing impactful analyses within the collaboration.

“Developments in computing continue to move at an incredible speed, and it is essential to have opportunities for new DUNE members to quickly learn the computing and software concepts of DUNE software,” said Mike Kirby of Brookhaven National Laboratory, who serves as Core Software and Computing Consortium lead in DUNE and lectured during the school. “The DUNE Data Analysis School hosted by the Neutrino Physics Center brought together experts from across the collaboration to help young DUNE members establish a foundation in computing, software and analysis, and accelerate their contributions to the exciting science that DUNE will deliver in the coming years.”

Neutrino Physics Center coordinators, organizers and the DUNE collaboration envision the school becoming an annual program and a cornerstone of software and analysis workforce development and training for DUNE — helping ensure that the next generation of DUNE physicists is equipped to maximize the experiment’s unprecedented scientific potential.

“None of this would have been possible without the tireless work of the NPC, the local organizing committee and the program committee,” added Gollapinni. “Building a brand-new curriculum from scratch and keeping the whole event running smoothly is no small feat.”

Fermilab editor’s note: This press release was originally posted by NSF NOIRLab and DOE’s SLAC National Accelerator Laboratory on June 30, 2026.

Fermilab plays an important role in the operation of the NSF–DOE Vera C. Rubin Observatory’s Legacy Survey of Space and Time (LSST), leveraging the lab’s operational experience and extensive expertise from the Sloan Digital Sky Survey, the Dark Energy Survey, and the Dark Energy Spectroscopic Instrument. LSST aims to better understand the fundamental physics of the universe. 

As part of the LSST Dark Energy Science Collaboration funded by DOE, Fermilab is deeply involved in Rubin science by supporting Rubin Observatory data management, data processing, survey strategy, scientific validation and verification, and community science. 

The launch of LSST marks an exciting milestone in Fermilab’s more than 35-year history of enabling groundbreaking optical and near-infrared survey experiments of the cosmos.

From a mountaintop in Chile, under clear dark skies, NSF–DOE Vera C. Rubin Observatory has begun the revolutionary Legacy Survey of Space and Time (LSST). The ten-year survey is Rubin’s signature campaign to create the most comprehensive, cinematic record of the Universe in history.

Rubin Observatory is a U.S. government facility jointly operated by NSF NOIRLab and DOE’s SLAC National Accelerator Laboratory. NOIRLab is managed by the Association of Universities for Research in Astronomy (AURA).

Over the next ten years, Rubin will relentlessly observe the entire southern sky every few nights to create an ultra-wide, ultra-high-definition time-lapse record of our Universe. This long-awaited milestone is the culmination of years of effort by thousands of people around the world. It follows the celebratory Rubin First Look event that took place in June 2025, which was followed by final commissioning work, an operational readiness review, and the beginning of the alert stream.

“Today, we begin filming the greatest cosmic movie ever made,” says Brian Stone, performing the duties of the NSF Director. “This moment reflects decades of vision, innovation, and the power of federal investment in science through the U.S. National Science Foundation and the Department of Energy. Every night, NSF–DOE Rubin Observatory will expand the frontiers of knowledge and strengthen America’s global leadership in science and innovation.”

“With the launch of the ten-year Legacy Survey of Space and Time, NSF–DOE Rubin Observatory is opening a new window on the Universe. It is embarking on a mission that will redefine modern cosmology and astrophysics,” says Darío Gil, Under Secretary for Science at the U.S. Department of Energy. “With its world-class design and tools, Rubin Observatory will capture the dynamic nature of our cosmos and reveal unimagined insights into our Universe’s biggest mysteries, from our own Solar System to the very structure of the Universe. By seeking to understand the enigmatic phenomena of dark energy and dark matter, we are not just observing the stars; we are striving to grasp the fundamental laws that govern our existence.”

“It is amazing and humbling to be here at this time and place as we start the Legacy Survey of Space and Time, after more than two decades of incredible work by our dedicated team,” says Bob Blum, Director of Rubin Observatory at NSF NOIRLab. “Rubin Observatory is for everyone; the LSST will change how we do astronomy and astrophysics, allowing researchers anywhere to participate in cutting-edge science.”

“It’s taken 20 years of hard science, engineering, and more to get to the point where we can call ‘action’ as we start rolling on this blockbuster movie of the Universe,” says Phil Marshall, Deputy Director of Rubin Operations for SLAC.“Millions of alerts in just the last couple of months show that Rubin is up and running as a discovery machine. Now we’re putting it all together.”

“The decision to officially begin the LSST was made after a period of system optimization and a careful operational review of technical readiness, data system performance, and scientific validation,” says Željko Ivezić, Head of LSST. Important factors that played a role in this decision included image quality, effective survey speed, system uptime and reliability, and calibration accuracy.

Rubin Observatory’s unique design combines enormous light-collecting power, the ability to move rapidly across the sky, and a wide field of view. Its 3200-megapixel camera — the largest digital camera in the world — is now capturing a new, detailed image approximately every 40 seconds. Operating with this speed and sensitivity, Rubin functions as a unified, well-tuned system capable of catching faint objects and fleeting events with remarkable reliability and consistency every night. Visit rubinobservatory.org to follow the status of the LSST in real time (and visit the real-time Alert Dashboard).

Rubin is bringing the Universe to life, illuminating a treasure trove of discoveries: pulsating stars, supernova explosions, the fossil record of galaxies, clues to the mysteries of dark energy and dark matter, and entirely new phenomena we’ve never seen before. Some cosmic processes unfold slowly, unpredictably, or incredibly rarely, which is why a ten-year survey is essential. By returning to each point in the sky about 800 times over a decade, Rubin data is providing the scientific community with deep, time-rich views needed to uncover subtle events, capture moving objects, and study the accelerating expansion of the Universe.

Not only is Rubin helping to unlock the mysteries of the distant Universe, it is also the most powerful Solar System discovery machine ever built. By taking about a thousand images every night, Rubin is compiling an astonishingly detailed census of our Solar System, including millions of asteroids and comets. In just a month and a half, during early optimization surveys, Rubin discovered over 11,000 never-before-seen asteroids, including 33 near-Earth objects and 380 trans-Neptunian objects [1].

Rubin will also advance opportunities for multi-messenger astronomy, which is the study of cosmic events using multiple signals such as light, gravitational waves, and cosmic rays. The observatory’s rapid, color-rich observations of transients such as stellar explosions, actively feeding black holes, and collisions between compact objects will guide telescopes around the world to follow up on these fleeting events.

Each night, Rubin is collecting approximately ten terabytes of data and producing as many as seven million alerts of changes in the night sky. These alerts stream to alert brokers — automated systems that sort and classify these changes so scientists can act quickly.

When the LSST is complete, the final dataset will contain billions of objects with trillions of measurements, all accessible through regular data releases. This is the first time so much astronomical data will be available to so many people, opening the door to new kinds of discovery by both scientists and the public. Rubin invites anyone in the world to engage with its data and explore the dynamic Universe in ways never before possible.