When the U.S. Department of Energy launched the Genesis Mission to supercharge artificial intelligence-driven scientific discovery and innovation, it needed more than supercomputers. It required secure, best-in-class infrastructure to store data so researchers across the country could efficiently access the information.
Enter the Fermi Data Platform, or FDP — a system built on thousands of hard drives that make up Fermilab’s scientific storage infrastructure backbone. Selected as a key partner for the Genesis Mission’s American Science Cloud, Fermilab is providing petabytes of storage, robust data-access tools and deep institutional expertise to ensure the data can be used to its fullest potential for AI-enhanced scientific research.
Fermilab is America’s particle physics laboratory, and decades of working with immense datasets have given its researchers longstanding expertise in scientific data management. Today, the platform supports datasets for multiple experiments and technologies, including measured and simulated data for the CMS experiment at CERN’s Large Hadron Collider; data from Fermilab’s Short Baseline Neutrino program; and data used in quantum research, microelectronics development and advanced theory work. Fermilab is also preparing for the data needs of the upcoming flagship Deep Underground Neutrino Experiment.
“At Fermilab, we orchestrate thousands of disks to provide petabytes of storage space, and we make sure researchers can access their data quickly and securely.”
Oliver Gutsche, lead of the Fermi Data Platform project
With data storage and access tools like the Fermi Data Platform, the Genesis Mission’s American Science Cloud brings together scientific expertise from DOE national laboratories, academic institutions and industry partners. By combining this expertise with advanced AI techniques and the development of new AI models, the American Science Cloud aims to accelerate discovery across disciplines — from high-energy physics to materials science to fusion-energy research.
The American Science Cloud will be an integrated infrastructure with advanced AI services: a system where a researcher can describe what they need and have AI-driven tools tap into national laboratory resources, including supercomputers, scientific datasets and simulation capabilities.
The Genesis Mission’s goal is to reduce the time between asking a scientific question and getting a meaningful answer by automating many of the steps in between — searching relevant scientific publications, running preliminary simulations, filtering results and presenting researchers with a refined picture of where to focus next.
“Give me the 10 most promising materials for batteries — the system does a literature search, runs some simulations to verify, narrows down that list, and presents it as an answer for further research,” said Gutsche. “That is the kind of workflow the Genesis Mission is designed to enable.”
The goal is not to replace researchers or the scientific process — humans still ask the questions and evaluate the answers. Instead, the aim is to enable scientists to work faster and focus on the insights that matter most.
To do any of this at scale, AI systems need data that is accessible, well-organized and what experts call “AI-ready.” Raw scientific data from instruments and detectors often lacks the structure and metadata — the supporting, behind-the-scenes information — that machine learning models require. Part of Fermi Data Platform’s role is to help bridge that gap, storing datasets from Genesis Mission projects and presenting them for model training and inference.
“Data is the common denominator behind major scientific endeavors, and AI is fundamentally data-driven,” said Chin Guok, partner integration level 1 lead for the American Science Cloud. “To train and run AI models, you need large volumes of data. Fermi Data Platform can support AI training and inference on large scientific datasets.”
When the Fermi Data Platform was established as an American Science Cloud infrastructure partner, Fermilab researchers were able to move quickly — offering data storage and data access tools engineered for the kind of active, repeated access that AI-supported research demands. This partnership now allows researchers to leverage DOE resources more seamlessly, laying a powerful foundation for accelerated scientific discovery for the benefit of all.
Fermi National Accelerator Laboratory is America’s national laboratory for particle physics and accelerator research. Fermi Forward Discovery Group manages Fermilab for the U.S. Department of Energy Office of Science. Visit Fermilab’s website at www.fnal.gov and follow us on social media.
Recommended reading
Using AI, Fermilab researcher probes how transistors behave in extreme cold
Olivia Seidel’s work draws on Fermilab’s deep expertise in microelectronics and cryogenic devices to support key goals of the Genesis Mission — a sweeping U.S. Department of Energy artificial intelligence initiative.
Fermilab leads multi-lab AI initiative to accelerate design of chips used in extreme environments
Researchers with Department of Energy national laboratories are working together alongside industry collaborators to support Genesis Mission goals by using the power of artificial intelligence to significantly reduce design times of custom computer chips for use in extreme temperature, high-radiation and ultra-fast environments.
Fermilab’s new director clarifies mission and achieves progress in first 100 days
With a sharp focus on Fermilab’s core scientific mission, Norbert Holtkamp is establishing clear priorities and a disciplined strategy that align the laboratory with the nation’s most ambitious research goals. His leadership is positioning Fermilab for long‑term success.