Researchers at PNNL are building a proof-in-concept agent-based platform that incorporates different commercially available AI models and several tools to accelerate innovation in an area of chemistry known as catalysis.
‘Sparsification’: PNNL Preps Data for Quantum
April 23, 2025 by
Quantum computing holds great promise in such such as computational chemistry and high-speed networking. But they’re so different from classical HPC systems that scientists are working out how to feed them ….
DOE Announces System for Searching DOE IP
July 31, 2024 by
RICHLAND, Wash., July 31, 2024 — The US Department of Energy has created a database designed to make ideas, technologies, methods and software developed by DOE available in one place. DOE said it worked with software engineers and others at Pacific Northwest National Laboratory on the Visual Intellectual Property Search database, or VIPS, designed to make […]
‘Physics-Informed Machine Learning’: New Technique at PNNL Corrects Remote Sensing Data
July 30, 2024 by
Turbulence, temperature changes, water vapor, carbon dioxide, ozone, methane, and other gases absorb, reflect, and scatter sunlight as it passes through the atmosphere, bounces off the Earth’s surface, and is collected ….
Power Grid Modeling Tool Launched on Frontier Exascale Supercomputer
June 1, 2023 by
Exascale Grid Optimization (ExaGO), a power grid simulation and optimization platform developed by Pacific Northwest National Laboratory (PNNL), is the first of its kind to run on Oak Ridge National Laboratory’s (ORNL) Frontier, the first supercomputer in the world to reach exascale. Frontier, which was launched this spring, can calculate more than 1 quintillion operations per second and […]
LLNL, Oak Ridge Among Winners of $15M in DOE Funds for Extreme-Scale Scientific Computing
September 19, 2022 by
Sept. 19, 2022 — The U.S. Department of Energy today announced $15 million in funding for basic research to explore potentially high-impact approaches in scientific computing and extreme-scale science. DOE said the projects will address disruptive technology changes from emerging trends in high-end computing, massive datasets, artificial intelligence, and increasingly heterogeneous architectures such as neuromorphic […]
Los Alamos, PNNL, Univ. of New Mexico Researchers to Lead $70M DOE HPC Climate Model Projects
August 30, 2022 by
The U.S. Department of Energy (DOE) today announced $70 million in funding for seven projects intended to improve climate prediction and aid in the fight against climate change. The research will be used to accelerate development of DOE’s Energy Exascale Earth System Model (E3SM), enabling scientific discovery through collaborations between climate scientists, computer scientists and […]
PNNL and Micron Partner to Push Memory Boundaries for HPC and AI
March 8, 2022 by
Researchers at Pacific Northwest National Laboratory (PNNL) and Micron are are developing an advanced memory system to support AI for scientific computing. The work is designed to address AI’s insatiable demand for live data — to push the boundaries of memory-bound AI applications — by connecting memory across processors in a technology strategy utilizing the […]
Ruby Leung, Chief Scientist for Energy Exascale Earth System Model Project, Named a DOE Distinguished Scientist Fellow.
September 28, 2021 by
Ruby Leung likes to ask questions. That started at her high school in Hong Kong, where she also became interested in science. “I was one of those kids in science who always was curious. And then you can find the answers,” said Leung, an atmospheric scientist at Pacific Northwest National Laboratory (PNNL) in Richland, Washington. “Of course, after you […]
PNNL’S CENATE Taps ML to Guard DOE Supercomputers Against Illegitimate Workloads
October 28, 2020 by
Pacific Northwest National Lab sent along this article today by PNNL’s Allan Brettman, who writes about the advanced techniques used by the lab’s Center for Advanced Technology Evaluation (CENATE) “to judge HPC workload legitimacy that is as stealthy as an undercover detective surveying the scene through a two-way mirror.” This includes machine learning methods, such […]
