Skip to main content
Graphic representation of ai model that identifies proteins

Researchers used the world’s fastest supercomputer, Frontier, to train an AI model that designs proteins, with applications in fields like vaccines, cancer treatments, and environmental bioremediation. The study earned a finalist nomination for the Gordon Bell Prize, recognizing innovation in high-performance computing for science.

Pictured here are 9 scientists standing in a line in front of the frontier supercomputer logo/computer

Researchers at Oak Ridge National Laboratory used the Frontier supercomputer to train the world’s largest AI model for weather prediction, paving the way for hyperlocal, ultra-accurate forecasts. This achievement earned them a finalist nomination for the prestigious Gordon Bell Prize for Climate Modeling.

Members of the target design team pose next to the 2.0-megawatt-capable mercury flow target they developed.

The Proton Power Upgrade project at ORNL's Spallation Neutron Source has achieved its final key performance parameter of 1,250 hours of neutron production at 1.7 megawatts of proton beam power on a newly developed target. 

Pictured is a 3D printed roosting structure for bats.

Oak Ridge National Laboratory researchers are using a new bioderived material to 3D print custom roosting structures for endangered bats.

The left/right columns show a time series of the neutron/proton number densities in log scale for a typical fission trajectory. The bar relates the color to the decimal logarithm of the number density.

Researchers used the Summit supercomputer at ORNL to answer one of fission’s big questions: What exactly happens during the nucleus’s “neck rupture” as it splits in two? Scission neutrons have been theorized to be among those particles emitted during neck rupture, although their exact characteristics have been debated due to a lack of conclusive experimental evidence of their existence.

An observation tower overlooks a Panama rainforest

Plants the world over are absorbing about 31% more carbon dioxide than previously thought. The research, detailed in the journal Nature, is expected to improve Earth system simulations that scientists use to predict the future climate, and spotlights the importance of natural carbon sequestration for greenhouse gas mitigation. 

Image of Giuseppe Barca looking at two computer monitors, representing the team using Frontier to perform the first quantum chemistry calculations to exceed an exaflop.

Researchers led by the University of Melbourne, Australia, have been nominated for the Association for Computing Machinery’s 2024 Gordon Bell Prize in supercomputing for conducting a quantum molecular dynamics simulation 1,000 times greater in size and speed than any previous simulation of its kind.

A large group of attendees are pictured outside of Jackson Center in Huntsville, Alabama

ORNL and NASA co-hosted the fourth iteration of this invitation-only event, which brings together geospatial, computational, data and engineering experts around a theme. This year’s gathering focused on how artificial intelligence foundation models can enable geospatial digital twins. 

Pictured is the IMAGINE instrument at the High Flux Isotope Reactor

Biochemist David Baker — just announced as a recipient of the Nobel Prize for Chemistry — turned to the High Flux Isotope Reactor (HFIR) at Oak Ridge National Laboratory for information he couldn’t get anywhere else. HFIR is the strongest reactor-based neutron source in the United States.  

Larry York is sitting in front of a computer screen showing an image of plant phenotyping

The Advanced Plant Phenotyping Laboratory at ORNL utilizes robotics, multi-modal imaging, and AI to enhance understanding of plant genetics and interactions with microbes. It aims to connect genes to traits for advancements in bioenergy, agriculture, and climate resilience. Senior scientist Larry York highlights the lab's capabilities and the insights from a new digital underground imaging system to improve biomass feedstocks for bioenergy and carbon storage.