Feature Articles

At Oak Ridge National Laboratory’s Center for Nanophase Materials Sciences, Yongtao Liu is building AI-driven “closed-loop” nanomaterials experiments that can plan measurements, interpret results in real time and choose the next step — accelerating discovery without removing human judgment. His focus is not just speed but trustworthy autonomy: systems must be interpretable, resilient to instrument artifacts and designed to avoid “false novelty,” where noise masquerades as new physics. Drawing on work such as novelty detection in conductive AFM studies of halide perovskites — linking local microstructure to unusual hysteresis behavior — Liu emphasizes that autonomous labs also demand better methods to validate and understand the massive data they produce. He is developing practical tools like AEcroscopy to standardize automated microscopy workflows and a Gated Active Learning Framework to prevent models from confidently learning from out-of-assumption data, while also pushing cross-facility autonomy that links fast measurements with slower synthesis. Ultimately, Liu envisions AI that helps scientists reason and explore vast experimental spaces — freeing researchers from repetitive tasks so they can focus on asking sharper questions.

Researchers at the Department of Energy’s (DOE’s) Oak Ridge National Laboratory (ORNL) will share their discoveries and innovations at DOE’s Advanced Research Projects Agency-Energy (ARPA-E) Energy Innovation Summit in San Diego, California, April 7-9. ARPA-E funds high-risk, high-impact energy technologies that can be quickly and meaningfully advanced to catalyze bleeding-edge energy research.

Labeled glass containers full of liquids stirred by spinning magnets are connected to humming machines with neatly organized tubes. Here in this lab space at the Idaho National Laboratory, scientists are pioneering ways to extract critical materials from recycled waste products.

Idaho teachers leaned into artificial intelligence with a mix of curiosity and caution during a recent professional development session hosted by Idaho National Laboratory.

Oak Ridge National Laboratory (ORNL) has developed Photon, a scalable framework that uses exascale computing to rapidly identify vulnerabilities in artificial intelligence systems. Created by ORNL’s Center for AI Security Research, Photon enables automated, large-scale testing of AI models to uncover risks such as adversarial attacks and system failures before they can be exploited. By combining high-performance computing with advanced AI techniques, the framework significantly accelerates vulnerability discovery and strengthens the security and reliability of AI used in critical applications.

When most people think of tree nuts, they imagine a tasty snack — not the parts of the nut that get left behind. But for Houston-based startup Vaulted Deep, a fibrous byproduct from nut agriculture is one ingredient in a bold new approach to waste management. Thanks to a recent collaboration with the Idaho National Laboratory (INL), that vision is one step closer to realization.

Leah Broussard, a research scientist in the Physics Division of the Department of Energy’s Oak Ridge National Laboratory, has received the inaugural DOE Distinguished Mentor Award for Workforce Development. The DOE Office of Science announced the awards March 10, recognizing scientists who guide and support the next generation of researchers.

Oak Ridge National Laboratory researchers invented a reusable adhesive from waste polymers that is tougher than commercial glues, works underwater as well as in dry environments, and bonds a variety of materials, including wood, glass, metal, paper and polymers. Inspired by the way mussels stick stubbornly to surfaces, the innovative adhesive contains reversible chemical crosslinkers that allow the hardened glue to soften, detach and be reused, unlike current glues, which set permanently after one use.