Skip to main content
Coronavirus graphic

In the race to identify solutions to the COVID-19 pandemic, researchers at the Department of Energy’s Oak Ridge National Laboratory are joining the fight by applying expertise in computational science, advanced manufacturing, data science and neutron science.

The image visualizes how the team’s multitask convolutional neural network classifies primary cancer sites. Image credit: Hong-Jun Yoon/ORNL

As the second-leading cause of death in the United States, cancer is a public health crisis that afflicts nearly one in two people during their lifetime.

A new computational approach by ORNL can more quickly scan large-scale satellite images, such as these of Puerto Rico, for more accurate mapping of complex infrastructure like buildings. Credit: Maxar Technologies and Dalton Lunga/Oak Ridge National Laboratory, U.S. Dept. of Energy

A novel approach developed by scientists at ORNL can scan massive datasets of large-scale satellite images to more accurately map infrastructure – such as buildings and roads – in hours versus days. 

This simulation of a fusion plasma calculation result shows the interaction of two counter-streaming beams of super-heated gas. Credit: David L. Green/Oak Ridge National Laboratory, U.S. Dept. of Energy

The prospect of simulating a fusion plasma is a step closer to reality thanks to a new computational tool developed by scientists in fusion physics, computer science and mathematics at ORNL.

Materials—Polymer-theory-problem

Scientists at Oak Ridge National Laboratory have conducted a series of breakthrough experimental and computational studies that cast doubt on a 40-year-old theory describing how polymers in plastic materials behave during processing.

ORNL’s Steven Young (left) and Travis Johnston used Titan to prove the design and training of deep learning networks could be greatly accelerated with a capable computing system.

A team of researchers from the Department of Energy’s Oak Ridge National Laboratory has married artificial intelligence and high-performance computing to achieve a peak speed of 20 petaflops in the generation and training of deep learning networks on the