Story by:
- Michelle Franklin
–
m1franklin@ucsd.edu - Tiffany Fox
–
tmfox@ucsd.edu
Published Date
Story by:
- Michelle Franklin
–
m1franklin@ucsd.edu - Tiffany Fox
–
tmfox@ucsd.edu
Article Content
University of California San Diego researchers will lead one of the Department of Energy’s (DOE) new Genesis Mission projects focused on accelerating fundamental physics and quantum computing by deploying intelligent AI agents.
Aobo Li, an assistant professor in the Department of Physics and the Halıcıoğlu Data Science Institute (HDSI) at the Halıcıoğlu School for Data Science and Computing, is the principal investigator (PI) on the project. A team of experts will build SIDERIUS, an AI scientist that can analyze data, design AI models, and deploy them onto specialized chips for applications in fundamental physics and quantum computing. Associate Professor of Physics Yi-Zhuang You is co-PI on the project.
“The next frontier of AI for science is learning how to translate scientific challenges into a form that AI can solve effectively,” said Li. “This DOE award allows us to bring together an interdisciplinary team in a way that wasn’t previously possible. Our vision is to translate challenges in physics and quantum computing into AI-ready tasks that can be tackled by SIDERIUS, our LLM agent system. Our long-term vision is to build a general AI framework that can be adapted to many other data-intensive scientific domains.”
In addition to this project, Li and several other UC San Diego researchers are co-PIs on four projects led by other institutions. These projects, listed below, will support the creation of AI tools that can meaningfully impact the way science is conducted and the rate at which discoveries are made.
- Co-PIs Javier Duarte (associate professor of physics) and Daniel Diaz (computational data science and research specialist) will work with the University of Colorado Boulder to develop ultra-fast AI tools that can process enormous rates of data input during particle collisions at CERN’s Large Hadron Collider.
- Co-PI Li will work with UNC Chapel Hill to deploy AI agents and surrogate models to automate and speed up optical simulations for LENGED, an experimental collaboration that will lead the effort to search for neutrinoless double beta decay, an extremely rare process that, if discovered, would explain why the universe has more matter than antimatter.
- Co-PIs Liang Yang (professor of physics) and Li will work with the University of Hawaii to build a unified foundation model based on AI-ready datasets from five different neutrinoless double beta decay experiments – CUORE, EXO-200, Majorana Demonstrator, NEXT and SuperNEMO.
- Co-PI Li will collaborate with Pacific Northwest National Laboratory to develop ultra-fast AI tools that identify and preserve neutrinoless double-beta decay signals while rejecting unwanted background noises from the LEGEND detector in real time.
The number of Genesis projects UC San Diego is a part of underscores the university’s deep bench of AI expertise.
“AI is impacting scientific discovery in fundamental ways,” said Rajesh K. Gupta, dean of the Halıcıoğlu School. “The Halıcıoğlu School is proud to assemble a team across Physics, Data Science and Supercomputing at UC San Diego in an institutional architecture that is uniquely matched to The Genesis Mission. SIDERIUS will drive research in physics through new AI tools and methodologies that are bound to significantly advance our understanding of nature and invent new applications.”
Learn more about research and education at UC San Diego in: Artificial Intelligence,
Read more news about: Physical Sciences,
Artificial Intelligence
