ai for knowledge and discovery
Pioneering the future of scientific and engineering progress
UT researchers are using AI to advance science and engineering, collaborating across domains to develop and apply AI systems that are transforming how we work by increasing speed and removing bottlenecks. They also work to advance AI models by training them in the physical laws that govern our world.
AI systems including machine learning–enabled microscopy, real-time analysis via neural networks, and simulations enable rapid discovery of new physical laws, high-performing materials, and chemical properties. These discoveries generate advancements in fields ranging from medicine and smart manufacturing to hypersonics and nuclear energy.
UT’s Approach
UT researchers are transforming the way knowledge is created and applied by deploying AI across every stage of discovery. They are building self-driving laboratories that integrate machine learning with automated experimentation, accelerating the pace of science and enabling real-time insights. Physics-augmented AI approaches refine digital twins, discover new quantum materials, and extend the limits of simulation and modeling.
Faculty at UT are applying hybrid quantum–machine learning models and large language frameworks to chemical and molecular discovery, forging new pathways in polymers, drug design, and complex molecular systems. At the systems scale, UT teams harness AI to model fusion reactors, evaluate thousands of nuclear designs, and shape the next generation of hypersonics and intelligent manufacturing. Anchored by the National Science Foundation Materials Research Science and Engineering Center and the university’s science-informed AI faculty cluster, these efforts are expanding the frontiers of knowledge and redefining what is possible.
“With AI, now we can accelerate discoveries in the rules of chemistry. By harnessing AI tools and large databases, we can systematically screen and examine not just dozens or hundreds but even millions of molecules, reactions, and materials. We’re a university, and we’re a state, that can convert basic science into world-changing, society-changing projects.”
—Konstantinos Vogiatzis, Associate Professor of Chemistry
Highlights
Facilities & Initiatives
Faculty study and build AI systems in state-of-the-art facilities on and off campus. Centers and research groups receive support from and partner with organizations including the National Science Foundation, the US Department of Energy, and industry leaders.
- Advanced Materials and Manufacturing
- Center for Materials Processing
- Center for Nanophase Materials Sciences at Oak Ridge National Laboratory
- Hybrid Autonomous Manufacturing, Moving from Evolution to Revolution (HAMMER) Engineering Research Center
- Infrastructure for Scientific Applications and Advanced Computing (ISAAC)
- Materials Research Science Center, Center for Advanced Materials and Manufacturing
- Shull Wollan Center
- Tennessee Ion Beam Materials Laboratory
- Tennessee Quantum Center
- UT-Oak Ridge Innovation Institute
Researchers
-
Associate Professor, Chemical and Biomolecular Engineering
Computation, simulation, theory, cell biology, immunology, intracellular transport, synthetic biology, systems biology, biomembrane, cytoskeleton, nanoparticle, biophysics, machine learning
-
Professor, Physics and Astronomy, Electrical Engineering and Computer Science
Algorithm development, quantum materials, condensed matter physics, entanglement, quantum information, machine learning for science, human-machine teaming
-
Professor, Mechanical, Aerospace and Biomedical Engineering
Adjoint methods, design optimization, reduced-order models (ROM), machine learning (ML), CFD
-
Assistant Professor, Industrial and Systems Engineering
Quantum optimization algorithms; graph theory games
-
UT–ORNL Governor’s Chair for Power Electronics
Power systems, smart grid, micro grid, infrastructure reliance, energy policy
-
Associate Professor, Mathematics
Machine learning, AI, topological data analysis, differential geometry, graph theory, drug discovery, mathematical biology, quantitative systems pharmacology, numerical methods for PDEs
-
Dan Doulet Faculty Fellow & Professor, Industrial & Systems Engineering
Integer programming, stochastic programming, non-linear programming, combinatorial optimization, power systems, scheduling problems, energy markets
-
Associate Professor, Mechanical, Aerospace and Biomedical Engineering
Scientific machine learning, decision intelligence, digital twin, fluid dynamics, data assimilation, numerical methods, high performance computing.
-
UT–ORNL Governor’s Chair for Advanced Composites Manufacturing
Composites manufacturing, design and product development, recycling and sustainable technologies, hybrids, engineered plastics and high performance materials
-
Associate Professor, Chemistry
Theoretical and computational chemistry, machine learning, electronic structure theory, catalysis, noncovalent interactions, molecular topology, chemoinformatics
-
Governor’s Chair Professor, Nuclear Engineering
Gas behavior in solids, neutron irradiation effects, plasma surface interactions, nuclear fuel performance
-
Assistant Professor, Industrial and Systems Engineering
Big data analytics, physics-informed machine learning, computer simulation and optimization, biomedical and health informatics, data mining and signal processing, sequential decision making, sensor-based modeling and control
-
UT/ORNL Governors Chair Professor, Nuclear Engineering and Materials Science and Engineering
Materials science, microstructural characterization, advanced manufacturing, materials by design, radiation effects, extreme environments
