
Consensus Study Report
NATIONAL ACADEMIES PRESS 500 Fifth Street, NW Washington, DC 20001
This project was supported by Award DE-SC0002220 between the National Academy of Sciences and the Department of Energy. Any opinions, findings, conclusions, or recommendations expressed in this publication do not necessarily reflect the views of any organization or agency that provided support for the project.
This report was prepared as an account of work sponsored by an agency of the United States Government. Neither the United States Government nor any agency thereof, nor any of their employees, makes any warranty, express or implied, or assumes any legal liability or responsibility for the accuracy, completeness, or usefulness of any information, apparatus, product, or process disclosed, or represents that its use would not infringe privately owned rights. Reference herein to any specific commercial product, process, or service by trade name, trademark, manufacturer, or otherwise does not necessarily constitute or imply its endorsement, recommendation, or favoring by the United States Government or any agency thereof. The views and opinions of authors expressed herein do not necessarily state or reflect those of the United States Government or any agency thereof.
International Standard Book Number-13: 978-0-309-99500-9
Digital Object Identifier: https://doi.org/10.17226/29212
This publication is available from the National Academies Press, 500 Fifth Street, NW, Keck 360, Washington, DC 20001; (800) 624-6242; https://nap.nationalacademies.org.
The manufacturer’s authorized representative in the European Union for product safety is Authorised Rep Compliance Ltd., Ground Floor, 71 Lower Baggot Street, Dublin D02 P593 Ireland; www.arccompliance.com.
Copyright 2025 by the National Academy of Sciences. National Academies of Sciences, Engineering, and Medicine and National Academies Press and the graphical logos for each are all trademarks of the National Academy of Sciences. All rights reserved.
Printed in the United States of America.
Suggested citation: National Academies of Sciences, Engineering, and Medicine. 2025. Foundation Models for Scientific Discovery and Innovation: Opportunities Across the Department of Energy and the Scientific Enterprise. Washington, DC: National Academies Press. https://doi.org/10.17226/29212.
The National Academy of Sciences was established in 1863 by an Act of Congress, signed by President Lincoln, as a private, nongovernmental institution to advise the nation on issues related to science and technology. Members are elected by their peers for outstanding contributions to research. Dr. Marcia McNutt is president.
The National Academy of Engineering was established in 1964 under the charter of the National Academy of Sciences to bring the practices of engineering to advising the nation. Members are elected by their peers for extraordinary contributions to engineering. Dr. Tsu-Jae Liu is president.
The National Academy of Medicine (formerly the Institute of Medicine) was established in 1970 under the charter of the National Academy of Sciences to advise the nation on medical and health issues. Members are elected by their peers for distinguished contributions to medicine and health. Dr. Victor J. Dzau is president.
The three Academies work together as the National Academies of Sciences, Engineering, and Medicine to provide independent, objective analysis and advice to the nation and conduct other activities to solve complex problems and inform public policy decisions. The National Academies also encourage education and research, recognize outstanding contributions to knowledge, and increase public understanding in matters of science, engineering, and medicine.
Learn more about the National Academies of Sciences, Engineering, and Medicine at www.nationalacademies.org.
Consensus Study Reports published by the National Academies of Sciences, Engineering, and Medicine document the evidence-based consensus on the study’s statement of task by an authoring committee of experts. Reports typically include findings, conclusions, and recommendations based on information gathered by the committee and the committee’s deliberations. Each report has been subjected to a rigorous and independent peer-review process and it represents the position of the National Academies on the statement of task.
Proceedings published by the National Academies of Sciences, Engineering, and Medicine chronicle the presentations and discussions at a workshop, symposium, or other event convened by the National Academies. The statements and opinions contained in proceedings are those of the participants and are not endorsed by other participants, the planning committee, or the National Academies.
Rapid Expert Consultations published by the National Academies of Sciences, Engineering, and Medicine are authored by subject-matter experts on narrowly focused topics that can be supported by a body of evidence. The discussions contained in rapid expert consultations are considered those of the authors and do not contain policy recommendations. Rapid expert consultations are reviewed by the institution before release.
For information about other products and activities of the National Academies, please visit www.nationalacademies.org/about/whatwedo.
DONA L. CRAWFORD, Lawrence Livermore National Laboratory (retired), Chair
SYED BAHAUDDIN ALAM, University of Illinois Urbana-Champaign
MARTA D’ELIA, Atomic Machines and Stanford University
KRISHNA GARIKIPATI, University of Southern California
SHIRLEY HO, Flatiron Institute
SCOTT H. HOLAN, University of Missouri
MICHAEL KEARNS (NAS), University of Pennsylvania
PETROS KOUMOUTSAKOS (NAE), Harvard University
BRIAN KULIS, Boston University
DANIEL I. MEIRON, California Institute of Technology
NATHANIEL TRASK, University of Pennsylvania
BLAKE REICHMUTH, Associate Program Officer, Board on Mathematical Sciences and Analytics (BMSA), Study Director
MICHELLE SCHWALBE, Director, BMSA and National Materials and Manufacturing Board (NMMB)
ERIK SVEDBERG, Deputy Director, BMSA and NMMB
JON EISENBERG, Director, Computer Science and Telecommunications Board (CSTB)
THƠ H. NGUYỄN, Senior Program Officer, CSTB
SAM KORETSKY, Research Associate, BMSA
HEATHER LOZOWSKI, Senior Finance Business Partner
JOE PALMER, Senior Project Assistant, BMSA
JILL C. PIPHER, Brown University, Co-Chair
KAREN E. WILLCOX, Oden Institute for Computational Engineering and Sciences, Co-Chair
BRENT APPLEBY, Draper Laboratory
HÉLÈNE BARCELO, Mathematical Sciences Research Institute
RUSSEL E. CAFLISCH, New York University
A. ROBERT CALDERBANK, Duke University
DUANE COOPER, Morehouse College
SARA Y. DEL VALLE, Los Alamos National Laboratory
RONALD D. FRICKER, JR., Virginia Polytechnic Institute and State University
SKIP GARIBALDI, Center for Communications Research, Institute for Defense Analyses
JULIE SIMMONS IVY, University of Michigan
PETROS KOUMOUTSAKOS (NAE), Harvard University
RACHEL KUSKE, Georgia Institute of Technology
YANN A. LECUN, Facebook
AARTI SINGH, Carnegie Mellon University
KAREN E. SMITH, University of Michigan
BRANI VIDAKOVIC, Texas A&M University
JUDY WALKER, University of Nebraska–Lincoln
MICHELLE K. SCHWALBE, Director
ERIK SVEDBERG, Deputy Director
HEATHER LOZOWSKI, Senior Finance Business Partner
BRITTANY SEGUNDO, Program Officer
BLAKE REICHMUTH, Associate Program Officer
SAMANTHA KORETSKY, Research Assistant
JOE PALMER, Senior Project Assistant
LAURA M. HAAS, University of Massachusetts Amherst, Chair
DAVID DANKS, University of California, San Diego
ECE KAMAR, Microsoft Research
JAMES F. KUROSE, University of Massachusetts Amherst (emeritus)
DAVID LUEBKE, NVIDIA
DAWN C. MEYERRIECKS, The MITRE Corporation
WILLIAM L. SCHERLIS, Carnegie Mellon University
HENNING G. SCHULZRINNE, Columbia University
NAMBIRAJAN SESHADRI, University of California, San Diego
KENNETH E. WASHINGTON, Medtronic
JOHN L. MANFERDELLI, Independent Consultant (ex officio member)
JON EISENBERG, Senior Board Director
AARYA SHRESTHA, Senior Financial Business Partner
THƠ H. NGUYỄN, Senior Program Officer
GABRIELLE RISICA, Program Officer
SHANAE BRADLY, Administrative Coordinator
This page intentionally left blank.
This Consensus Study Report was reviewed in draft form by individuals chosen for their diverse perspectives and technical expertise. The purpose of this independent review is to provide candid and critical comments that will assist the National Academies of Sciences, Engineering, and Medicine in making each published report as sound as possible and to ensure that it meets the institutional standards for quality, objectivity, evidence, and responsiveness to the study charge. The review comments and draft manuscript remain confidential to protect the integrity of the deliberative process.
We thank the following individuals for their review of this report:
Although the reviewers listed above provided many constructive comments and suggestions, they were not asked to endorse the conclusions or recommendations of this report nor did they see the final draft before its release. The review of this report was overseen by REBECCA WILLET, University of Chicago,
and ROBERT F. SPROULL, University of Massachusetts Amherst. They were responsible for making certain that an independent examination of this report was carried out in accordance with the standards of the National Academies and that all review comments were carefully considered. Responsibility for the final content rests entirely with the authoring committee and the National Academies.
We are grateful to the many scholars and leaders who contributed their time and expertise to the committee’s information-gathering efforts. Special thanks go to all the speakers who briefed the committee: William Collins, Lawrence Berkeley National Laboratory; Kevin Dixon, Sandia National Laboratories; Omar Ghattas, University of Texas at Austin; Hendrik Hamann, Brookhaven National Laboratory; Tzanio Kolev, Lawrence Livermore National Laboratory; Rémi Lam, Google DeepMind; Earl Lawrence, Los Alamos National Laboratory; Michael Mahoney, Lawrence Berkeley National Laboratory; Vivek Natarajan, Google DeepMind; Sabastian Nowozin, Google DeepMind; Chris Ritter, Idaho National Laboratory; Kelly Rose, National Energy Technology Laboratory; Brian Spears, Lawrence Livermore National Laboratory; Ann Speed, Sandia National Laboratories; Rick Stevens, Argonne National Laboratory; Georgia Tourassi, Oak Ridge National Laboratory; James Warren, National Institute of Standards and Technology; and Bin Yu, University of California, Berkeley.
Additionally, we appreciate the collaborative efforts of every member of the staff team. This report was the product of the committee’s thoughtful deliberation and dedication on the topic. We extend our gratitude to the broader community for their engagement with this project.
This page intentionally left blank.
Significance of Foundation Models
2 FOUNDATION MODELS AND TRADITIONAL MODELING
Defining the Scope and Use of Foundation Models
Benefits of Only Using Foundation Models
Benefits of Using “Traditional Modeling” Over Foundation Models
Benefits of Using Traditional Modeling with Foundation Models
3 EXEMPLAR USE CASES OF FOUNDATION MODELS
Department of Energy’s Role in Foundation Model Development
Human in the Loop and Artificial Intelligence Foundation Model Autonomy
4 STRATEGIC CONSIDERATIONS AND DIRECTIONS FOR DEPARTMENT OF ENERGY FOUNDATION MODELS
Material Informatics and Near-Autonomous Scientific Platforms
Federated Computing and Department of Energy Facilities
Curation and Translation of Specialized Knowledge
Multimodal Artificial Intelligence for Physics-Based Prediction
Integrating the Department of Energy Scientific Software Stack
Agentic Artificial Intelligence
Challenges of Industrial Collaboration
Foundation models represent a potentially transformative technology for progressing scientific discovery and innovation. However, their rapid adoption has raised questions and concerns about their reliability, validity, and reproducibility. In 2024, the Department of Energy (DOE) requested that the National Academies of Sciences, Engineering, and Medicine conduct a study to consider current foundation models’ capabilities, and future possibilities and challenges.
The National Academies established the Committee on Foundation Models for Scientific Discovery and Innovation to conduct this study. The study compares foundation models with more traditional computational methods, addresses exemplar use cases of foundation models, specifies strategic considerations, and outlines challenges for the development and use of foundation models. The full statement of the committee’s task is shown in Appendix A.
The committee met in person in March 2025 and met virtually 15 times to receive briefings from experts and stakeholders (for a list of presentations, see Appendix B), review relevant reports and technical literature, deliberate, and develop this report.
The committee is grateful for the support of DOE’s Office of Science, Office of Biological and Environmental Research, and National Nuclear Security Administration. The committee also extends its sincere thanks to the following National Academies’ staff for their assistance throughout the study: Blake Reichmuth, Thơ Nguyễn, Erik Svedberg, Sam Koretsky, Jon Eisenberg, and Michelle Schwalbe.
Dona Crawford, Chair
Committee on Foundation Models for Scientific Discovery and Innovation
October 2025
This page intentionally left blank.