Physics faculty awarded Department of Energy’s Genesis Mission funding for AI-based projects
Six physics faculty from ĢӰ Boulder are leading or contributing to new projects awarded more than $1.6 million in highly competitive U.S. Department of Energy Genesis Mission grants, the agency announced on July 22. Nationwide, only 278 phase-one projects were funded out of over 5,000 proposals.
Yuan Shi and Keith Ulmer are principal investigators on their respective projects, Dennis Perepelitsa is a co-principal investigator on two projects, Jamie Nagle is a co-principal investigator on another, and Xun Gao and Scott Parker are collaborators on the project led by Shi.
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.
“Having six ĢӰ Physics faculty involved across four Genesis Mission projects is incredibly impressive,” says Tobin Munsat, professor and chair of physics. “This reflects the broad strength of our department and demonstrates how our faculty are leading the way in putting AI and quantum technologies to work on some of the most challenging questions in fundamental science.”
AI for analyzing particle collisions at the Large Hadron Collider
Ulmer, with collaborators from the University of California San Diego, Fermi National Accelerator Laboratory and Johns Hopkins University, will use AI to analyze largely untapped datasets of particle collisions from the Large Hadron Collider (LHC) at CERN.
Each day, the LHC produces about 4,000 petabytes, or 4 billion gigabytes, of particle collision data used by physicists around the world to better understand the fundamental nature of the universe. Because of the enormous amount of data, current analyses are limited to roughly one in every 10,000 particle collisions, leaving potential anomalies undetected.
By combining high-energy physics expertise, data science, and industry AI methods, Ulmer and his collaborators will develop a system capable of analyzing the full dataset from the LHC. Called the AI-Inclusive Discovery of Anomalies in Scouting (AIDA-Scout), the system will analyze data in real time, automatically adjust to changing detector conditions, and find anomalies in collision data that could lead to new scientific discoveries.
Using quantum computing technologies and AI to simulate plasma for fusion pilot plants
Shi is leading a project to generate plasma simulations needed for fusion pilot plants. Collaborators on the project include Gao and Parker, as well as colleagues from Lawrence Livermore National Laboratory and Infleqtion.
Even today’s most powerful supercomputers cannot produce certain plasma simulations essential for developing fusion pilot plants.
The team will develop new computational methods combining quantum computing, quantum machine learning, and AI to create more efficient and accurate simulations needed for fusion to become a potential energy source.
“This project seeks to prepare the fusion community for the coming generation of quantum computers by creating algorithms and software that can take advantage of quantum hardware as it matures,” says Shi. “The resulting capabilities could significantly accelerate plasma simulations, supporting advances in fusion energy science and scientific computing.”
AI for understanding quark-gluon plasma
Some of the final collisions captured by the sPHENIX detector at the Relativistic Heavy Ion Collider, a nuclear physics research facility at Brookhaven National Laboratory. (Image Credit: Brookhaven National Laboratory)
A project led by Baruch College, City University of New York involves ĢӰ Boulder physics faculty Jamie Nagle and Dennis Perepelitsa as co-principal investigators. The project’s leadership team includes Yeonju Go, a former postdoctoral researcher in ĢӰ Boulder’s experimental nuclear physics group.
The project is designed to better understand the quark-gluon plasma, a phase of matter which only existed microseconds after the Big Bang at temperatures exceeding two trillion Kelvin. At Brookhaven National Laboratory, scientists recreate tiny droplets of quark-gluon plasma by colliding gold nuclei together at nearly the speed of light. These collisions are analyzed by the sPHENIX detector, which acts as a giant camera, capturing approximately 15,000 particle collisions each second.
When creating the quark-gluon plasma, sometimes there are two high energy quarks that scatter, and this project aims to separate and analyze these specific images by using an unsupervised AI framework known as cycle-consistent generative learning.
“We know how quarks scatter at high energy, but we want to understand how they scatter when they’re inside the plasma,” says Nagle.
AI for enhancing the foundation model for nuclear and particle physics
Dennis Perepelitsa is a co-principal investigator on a project led by colleagues at Lawrence Livermore National Laboratory aimed at enhancing the Foundation Model for Nuclear and Particle Physics (FM4NPP), a large-scale AI model built to extract scientific insights directly from raw detector data.
Foundation models go beyond the more commonly known large language models (LLMs) by being able to perform a variety of tasks. The project will extend the current FM4NPP, which only includes information from one sPHENIX detector subsystem, to include a variety of other detectors, making the model truly multi-modal and enhancing the capability of the detector for quark-gluon plasma measurements. Ultimately, the FM4NPP effort is envisioned as a multi-institution consortium between national labs, universities, and industry to accelerate scientific discovery in a broad set of nuclear and particle physics datasets.
“In modern collider detectors, physics processes leave signatures in multiple subsystems at once, and a comprehensive picture is needed for the highest scientific sensitivity. The foundation model is based on similar principles as commercial LLMs, which is that with enough data and scale, it can make connections beyond the existing non-AI approaches,” says Perepelitsa.