The following brings together announcements from Pratt School of Engineering and Trinity College of Arts & Sciences .
Four Duke-led teams - two from the Pratt School of Engineering and two from Trinity College of Arts & Sciences - have been selected for the U.S. Department of Energy's (DOE) Genesis Mission .
These teams will use artificial intelligence to build better models of atomic nuclei, react to stellar explosions faster, imbue robots with more brain-like circuitry and design new DNA-based materials.
The Genesis Mission is a national initiative led by the DOE, 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.
The projects below have received Phase I awards ranging from $500,000 to $750,000 and will be supported for nine months.
From Data to Equation of State: AI-Driven Discovery of Optimal Observables in Heavy-Ion Collisions
Duke Project Lead: Steffen Bass , Trinity College of Arts & Sciences
Bass and the team will use AI to connect experimental data with simulations of high-energy collisions of heavy ions. This will help refine our understanding of atomic nuclei, shedding light on fundamental structures of atoms, the extreme environment within stars and the early state of the universe. Collaborators include Trinity's Berndt Mueller as well as researchers at Michigan State University, Lawrence Livermore National Laboratory, and the University of California, Davis.
"We are excited to bring the power of artificial intelligence and machine learning to bear on determining the nuclear equation of state using DOE's flagship accelerator facilities," Bass said. Learn more in the announcement from Trinity College of Arts & Sciences .
AI-Accelerated Supernova Burst Response with DUNE
Duke Project Lead: Kate Scholberg , Trinity College of Arts & Sciences
Scholberg and the team will be developing AI-accelerated methods of parsing through the reams of data collected when tracking neutrinos, a tiny, hard-to-detect particle often produced in large quantities when a massive star collapses into a supernova. This speeds up detection of stellar explosions, allowing astronomers to quickly pivot their instruments to the sky sliver of interest. Collaborators include researchers at Fermi National Accelerator Laboratory and Columbia University.
"I'm excited to develop ultra-fast AI methods to pinpoint the explosion immediately using the neutrino burst, so the scientific community can make the most of a once-in-a-career fireworks event," Scholberg said. Learn more in the announcement from Trinity College of Arts & Sciences .
Neuromorphic Circuit Primitives for Robotic Embodied Physical AI
Duke Project Lead: Yiran Chen , Pratt School of Engineering
Chen and the team are developing new hardware for AI-powered robots that is 10 times faster and 100 times more efficient than current designs. The team is designing neuromorphic processors that mimic the way our brain and nervous system are structured. Currently, the speed of processing data from cameras and other sensors is a bottleneck to making AI robots useful beyond niche applications. Collaborators include Pratt's Tania Roy and researchers at Georgia Tech and Brookhaven National Laboratory.
"The completed system will resemble a steel-born Centaur - a synthetic organism whose fundamental neuromorphic computing components and abilities form its muscles, skeleton and nervous system," Chen said. Learn more in the announcement from Pratt School of Engineering .
AI-Driven Inverse Design of Patchy DNA Origami for Assembly of Programmable Superlattices
Duke Project Lead: Gaurav Arya , Pratt School of Engineering
Arya and the team will design AI-driven models for DNA origami, an emerging approach to precisely designing materials with nanoscale structures for a variety of energy applications. Folding DNA in various ways can create many different kinds of materials but planning those designs is a big computational challenge for which AI is a promising solution. Collaborators include Pratt's Stefan Zauscher and researchers at Georgia Tech, Emory University and Lawrence Berkeley National Laboratory.
"We're just beginning to tap into this enormous design space, and we expect the novel biomaterials that result from this effort will greatly impact industries such as energy production, chemical manufacturing and even quantum computing," Arya said. Learn more in the announcement from Pratt School of Engineering .
Learn more about how federally funded research drives innovation for all of society at Duke Research Saves Lives .
