University of Tennessee secures $20 million NSF grant for AI-powered materials lab

ATHENA will connect automated experiments, microscopy and artificial intelligence as part of a 20-hub U.S. network of remotely accessible laboratories. Sergei Kalinin is leading ATHENA, a $20 million NSF-backed laboratory for AI-enabled materials experimentation The University of Tennessee, Knoxville has received a $20 million National Science Foundation grant to establish an AI -enabled laboratory intended to accelerate the testing and development of advanced materials. Known as ATHENA, or the Advanced Testbed for High-throughput Experimentation in Nano- and Atomic Science, the facility will be one of 20 research hubs forming a national network of AI-powered laboratories across the United States. The project is led by Sergei Kalinin, Weston Fulton Professor in UT’s Tickle College of Engineering, alongside Mahshid Ahmadi, Associate Professor of Materials Science and Engineering, and Hairong Qi, Gonzalez Family Professor of Electrical Engineering and Computer Science. Twelve UT faculty members are involved, with collaborators from Northwestern University and Johns Hopkins University . Their work will cover materials design, synthesis, characterization and autonomous optimization. AI can help researchers identify potentially useful materials, but the physical work required to synthesize and test those candidates remains a constraint. “Predictions alone don’t create new technologies,” Kalinin says. “At some point, those materials have to be synthesized, measured and understood in the real world. ATHENA is about dramatically accelerating that process.” Self-driving laboratories will select experimental steps Materials research can require scientists to prepare samples, operate microscopes and analyze the resulting data manually. According to UT, a single experiment can take hours or days. ATHENA will use what the university describes as self-driving laboratories. These systems are intended to conduct experiments, interpret the results and decide what should happen next with minimal human intervention. The team expects the platform to make some materials characterization experiments between 10 and 30 times faster. This is a projected capability rather than a result already demonstrated by ATHENA. Researchers will study materials at the atomic and nanoscale, evaluating thousands of combinations before identifying candidates for potential real-world applications. The project builds on UT research in autonomous microscopy, automated materials synthesis and artificial intelligence. Kalinin and other researchers at the university have previously developed machine learning tools that connect microscopes and other scientific instruments directly with intelligent software. “This proposal reflects years of investment by the university and an exceptional team of researchers,” Kalinin says. “Many of the technologies that make self-driving laboratories possible were developed here at UT long before this became a national priority.” NSF network will provide remote laboratory access ATHENA forms part of the NSF’s Platform for Cloud Laboratories initiative, which is creating remotely accessible, AI-enabled facilities for materials science and biotechnology research. The laboratories are designed to plan, run and refine experiments autonomously, while allowing researchers in different parts of the country to access scientific instruments remotely. As one of the network’s nodes, ATHENA will develop open software standards, cloud-accessible laboratory workflows and digital tools for remote access. It will also work with other participating laboratories on common standards and training for scientists working across AI and experimental research. “We believe the future isn’t simply about computing faster,” Kalinin says. “It’s about discovering, making and understanding new materials faster. If we can dramatically shorten the time between an idea and a new material, we can accelerate innovation across nearly every industry.”