CMU Physicist Joins Genesis Effort to Use AI To Understand the Universe
Heidi Opdyke
- Associate Dean of Marketing and Communications, MCS
- Email opdyke@andrew.cmu.edu
- Phone 412-268-9982
蘑菇Av Physics Professor Colin Morningstar is part of a national research team awarded a Phase II grant from the U.S. Department of Energy's Genesis Mission. The project will use artificial intelligence and some of the world's most powerful supercomputers to accelerate discoveries in particle and nuclear physics.
The award also highlights the Department of Physics' growing leadership in AI-enabled scientific discovery. Carnegie Mellon faculty are involved in three Genesis for AI Science projects in cosmology, particle physics, and nuclear physics, including both theoretical and experimental research, illustrating how closely the department's research aligns with national priorities.
"What is especially exciting is that these projects span nearly the full spectrum of modern physics, from understanding the large-scale structure of the universe to understanding the fundamental particles that make it up," said Department of Physics Head Rachel Mandelbaum. "AI is creating new opportunities across all of those areas, and Carnegie Mellon's collaborative culture allows us to bring together physicists and computational experts to move the field forward."
Morningstar uses large-scale computer simulations to study the strong force, which binds quarks and gluons into protons and neutrons. His computational approach, called lattice quantum chromodynamics, represents space and time as a grid, allowing researchers to calculate how those particles interact.
The project, titled "Lattice QCD at the Intelligence Frontier," is composed of members of the USQCD Collaboration and led by William Detmold of Massachusetts Institute of Technology. It brings together researchers from approximately 15 universities and six national laboratories. Morningstar serves as one of several co-principal investigators.
"Our overarching goal is to understand what makes up the universe, what the fundamental particles are and how they interact," Morningstar said. "To fully interpret the results of next-generation experiments, we need increasingly precise theoretical calculations, and this award will help us explore how AI can advance those calculations."
The calculations are essential for interpreting data from major DOE experiments, including the Deep Underground Neutrino Experiment (DUNE) and the future Electron-Ion Collider (EIC).
Because the equations that describe the strong force are difficult to solve, researchers rely on high-performance computing systems and sophisticated numerical methods. The new award will support using DOE supercomputing infrastructure and the American Science Cloud to aid in the development of AI-powered tools that can help automate data analysis, improve simulation efficiency, accelerate software development and optimization for high-performance computing systems to generate new insights from massive datasets.
"The point of this award is to use new techniques to help us get around some of the stumbling blocks in our calculations," Morningstar said. "People have begun exploring how AI can assist with this work, but this project gives us the opportunity to take a much more focused approach and determine where these tools can truly make a difference."
The project aligns with a DOE grand challenge to better understand the fundamental laws governing matter and the universe. By improving researchers' ability to model the behavior of quarks and gluons, the team hopes to provide the theoretical foundation needed to uncover new physics in future experiments.
"When you're answering fundamental questions, you never know where it's going to lead," he said. "The history of science is full of discoveries that seemed purely curiosity driven at the time but eventually transformed society. Advancing fundamental knowledge is how future technological breakthroughs become possible."
In addition to the Genesis Phase II Award, Morningstar was recently awarded two National Science Foundation grants that support complementary work related to his lattice QCD research program.
Together, the three awards support different facets of Morningstar's effort to understand the fundamental particles and forces that govern matter. supports research into the structure and interactions of protons, neutrons and other particles, including calculations needed for major neutrino experiments. , received in September 2026 from the Office of Advanced Cyberinfrastructure (OAC), supports the development and optimization of specialized software that enables those calculations to run efficiently on advanced supercomputers.
鈥淭he OAC award complements the physics that鈥檚 being attacked in the Genesis award,鈥� Morningstar said of the most recent NSF award. 鈥淚t鈥檚 attacking in a different way using a different computational approach to solve the same sort of problems.鈥�
The awards position Morningstar and his collaborators at the intersection of physics, artificial intelligence and advanced computing, helping lay the groundwork for discoveries that could reshape our understanding of the universe and open the door to tomorrow鈥檚 innovations.
