HomeScienceBerkeley Lab Details AI, Data, and Com
SCIENCE

Berkeley Lab Details AI, Data, and Computing Integration

Lawrence Berkeley National Laboratory Scientific Data Division Director Ana Kupresanin detailed how combining computing, data infrastructure, and statistical methods supports the DOE Genesis Mission.

WHAT YOU NEED TO KNOW
  • Ana Kupresanin joined Berkeley Lab as Scientific Data Division Director in 2023 after over a decade at Lawrence Livermore National Laboratory.
  • Berkeley Lab's Scientific Data Division creates software, workflows, and machine learning methods across the data lifecycle.
  • The Department of Energy's Genesis Mission uses Berkeley Lab infrastructure to advance AI for science, energy, and national security.

Lawrence Berkeley National Laboratory is integrating scientific data, high-performance computing, and statistical methods to support the Department of Energy's Genesis Mission, according to details released by the lab. Ana Kupresanin, director of Berkeley Lab's Scientific Data Division, stated that building reliable artificial intelligence for scientific discovery requires grounding models in domain knowledge, physical constraints, and uncertainty quantification rather than simply using larger models.

Kupresanin leads a team of scientists and engineers who create methods, software, workflows, and infrastructure to manage scientific data across its lifecycle. The division helps researchers organize, curate, access, analyze, and reuse data, while also developing machine learning methods and high-performance computing workflows. Kupresanin, a statistician and Fellow of the American Statistical Association, joined Berkeley Lab in 2023 after spending more than ten years at Lawrence Livermore National Laboratory working on complex data analysis and statistical methods.

Infrastructure and Data

Scientific data carries specific context, including generation methods, assumptions, and uncertainties, Kupresanin explained in a Q&A published by Berkeley Lab. The Genesis Mission, a national initiative, aims to advance AI to address challenges across science, energy, and national security. Berkeley Lab's contribution combines high-performance computing, high-speed networking, user facilities, automated laboratories, simulations, and software to connect AI models directly with scientific workflows.

The lab's technical scientific ecosystem synthesizes experimental facilities with data preparation, model development, and analysis. Kupresanin noted that scientific inputs differ from generic data, requiring researchers to preserve underlying contextual assumptions so AI outputs remain reproducible and trustworthy.

Founded in 1931, Berkeley Lab is a multiprogram national laboratory managed by the University of California for the U.S. Department of Energy’s Office of Science. Scientists associated with the lab have earned 17 Nobel Prizes while advancing research across physics, materials, chemistry, biology, environmental science, mathematics, and computing.

Xentir Media
Xentir Media NewsroomSource-backed AI and technology coverage, drafted by Xentir's automated editorial system under fixed human-set rules. See our editorial policy and AI usage policy.
J
Jomon · Founder & EditorFounder and editor of Xentir Media. Sets the editorial rules the newsroom system runs under, and is accountable for its corrections. About Jomon · hello@xentirmedia.com
The Xentir Brief
The developments worth knowing — one useful email.
Get the Brief →