Skip to main content
Illustration of melting point of lithium chloride, which is shown with green and blue structures in two rows.

Scientists have developed a new machine learning approach that accurately predicted critical and difficult-to-compute properties of molten salts, materials with diverse nuclear energy applications. 

A color-enhanced 3D laser scan of a large concrete slab in a housing development, showing surface variations in shades of blue, green, yellow, and purple. Surrounding structures and terrain are rendered in black and white. The image was captured using the FLAT tool’s 360-degree scanning technology.

Researchers at ORNL have developed a tool that gives builders a quick way to measure, correct and certify level foundations. FLAT, or the Flat and Level Analysis Tool, examines a 360-degree laser scan of a construction site using ORNL-developed segmentation algorithms and machine learning to locate uneven areas on a concrete slab. 

Illustration of the GRETA detector, a spherical array of metal cylinders. The detector is divided into two halves to show the inside of the machine. Both halves are attached to metal harnesses, displayed against a black and green cyber-themed background.

Analyzing massive datasets from nuclear physics experiments can take hours or days to process, but researchers are working to radically reduce that time to mere seconds using special software being developed at the Department of Energy’s Lawrence Berkeley and Oak Ridge national laboratories.  

Photo is a high aerial view of lake superior through the clouds

Researchers at Stanford University, the European Center for Medium-Range Weather Forecasts, or ECMWF, and ORNL used the lab’s Summit supercomputer to better understand atmospheric gravity waves, which influence significant weather patterns that are difficult to forecast. 

Mengya Li is pictured here sitting at a computer in a lab.

Scientists at ORNL are studying the failure mechanisms of a new solid electrolyte battery to enhance long-term storage for renewable energy, aiming to make wind and solar power more reliable for the electric grid.

A graphic representation of AI

The Department of Energy announced a $67 million investment in several AI projects from institutions in both government and academia as part of its AI for Science initiative. Six ORNL-led (or co-led) projects received funding.

This illustration demonstrates how atomic configurations with an equiatomic concentration of niobium (Nb), tantalum (Ta) and vanadium (V) can become disordered. The AI model helps researchers identify potential atomic configurations that can be used as shielding for housing fusion applications in a nuclear reactor. Credit: Massimiliano Lupo Pasini/ORNL, U.S. Dept. of Energy

A study led by the Department of Energy’s Oak Ridge National Laboratory details how artificial intelligence researchers created an AI model to help identify new alloys used as shielding for housing fusion applications components in a nuclear reactor. The findings mark a major step towards improving nuclear fusion facilities.

Moe Khaleel, left, associate laboratory director for national security sciences, and Maurice Singleton, chief executive officer of U2opia Technology, celebrate the partnership between Oak Ridge National Laboratory and U2opia Technology. Credit: Carlos Jones/ORNL, U.S. Dept. of Energy

U2opia Technology has licensed Situ and Heartbeat, a package of technologies from the Department of Energy’s Oak Ridge National Laboratory that offer a new method for advanced cybersecurity monitoring in real time. 

pulsed laser deposition setup

In a game-changing study, ORNL scientists developed a deep learning model — a type of artificial intelligence that mimics human brain function — to analyze high-speed videos of plasma plumes during a process called pulsed laser deposition.

ORNL scientists used molecular dynamics simulations, exascale computing, lab testing and analysis to accelerate the development of an energy-saving method to produce nanocellulosic fibers.

A team led by scientists at ORNL identified and demonstrated a method to process a plant-based material called nanocellulose that reduced energy needs by a whopping 21%, using simulations on the lab’s supercomputers and follow-on analysis.