Skip to main content
The illustration depicts ocean surface currents simulated by MPAS-Ocean. Credit: Los Alamos National Laboratory, E3SM, U.S. Dept. of Energy

A team from DOE’s Oak Ridge, Los Alamos and Sandia National Laboratories has developed a new solver algorithm that reduces the total run time of the Model for Prediction Across Scales-Ocean, or MPAS-Ocean, E3SM’s ocean circulation model, by 45%. 

Photo by James Wainscoat on Unsplash.

A team of researchers from the University of Southern California, the Renaissance Computing Institute at the University of North Carolina, and Oak Ridge, Lawrence Berkeley and Argonne National Laboratories have received a grant from the U.S. Department of Energy to develop the fundamentals of a computational platform that is fault tolerant, robust to various environmental conditions and adaptive to workloads and resource availability.

A researcher plays checkers against an AI-powered robotic arm in 1984. Credit: ORNL, U.S. Dept. of Energy

Despite its futuristic essence, artificial intelligence has a history that can be traced through several decades, and the ORNL has played a major role. From helping to drive fundamental and applied AI research from the field’s early days focused on expert systems, computer programs that rely on AI, to more recent developments in deep learning, a form of AI that enables machines to make evidence-based decisions, the lab’s AI research spans the spectrum.

The AI agent, incorporating a language model-based molecular generator and a graph neural network-based molecular property predictor, processes a set of user-provided molecules (green) and produces/suggests new molecules (red) with desired chemical/physical properties (i.e. excitation energy). Image credit: Pilsun You, Jason Smith/ORNL, U.S. DOE

A team of computational scientists at ORNL has generated and released datasets of unprecedented scale that provide the ultraviolet visible spectral properties of over 10 million organic molecules. 

Image of circuitry representing AI.

Research performed by a team, including scientists from ORNL and Argonne National Laboratory, has resulted in a Best Paper Award at the 19th IEEE International Conference on eScience.

Frontier’s exascale power enables the Simple Cloud-Resolving E3SM Atmosphere Model to run years’ worth of climate simulations at unprecedented speed and scale. Credit: Ben Hillman/Sandia National Laboratories, U.S. Dept. of Energy

A 19-member team of scientists from across the national laboratory complex won the Association for Computing Machinery’s 2023 Gordon Bell Special Prize for Climate Modeling for developing a model that uses the world’s first exascale supercomputer to simulate decades’ worth of cloud formations.

Gina Tourassi. Credit: Genevieve Martin/ORNL, U.S. Dept. of Energy 

Effective Dec. 4, Gina Tourassi will assume responsibilities as associate laboratory director for the Computing and Computational Sciences Directorate at the Department of Energy’s Oak Ridge National Laboratory.

ORNL researchers are establishing a digital thread of data, algorithms and workflows to produce a continuously updated model of earth systems.

Digital twins are exactly what they sound like: virtual models of physical reality that continuously update to reflect changes in the real world.

 

A small droplet of water is suspended in midair via an electrostatic levitator that lifts charged particles using an electric field that counteracts gravity. Credit: Iowa State University/ORNL, U.S. Dept. of Energy

How do you get water to float in midair? With a WAND2, of course. But it’s hardly magic. In fact, it’s a scientific device used by scientists to study matter.

Frontier, the fastest supercomputer in the world, provides expansive and energy-efficient power, which gives scientists the capability to train large AI models in a responsible way.

ORNL is home to the world's fastest exascale supercomputer, Frontier, which was built in part to facilitate energy-efficient and scalable AI-based algorithms and simulations.