The use of disciplines in pure mathematics can increase the reliability and explainability of machine learning models that “transcend human intuition,” according to PNNL scientists.
To overcome high-performance computing bottlenecks, a research team at PNNL proposed using graph theory, a mathematical field that explores relationships and connections between a number, or cluster, of points in a space.
As the world races to discover solutions for reaching net zero carbon emissions, a PNNL analysis quantifies the economic value of the existing nuclear power fleet and its carbon-free energy contributions.
Some rocks can potentially convert injected carbon dioxide into more stable solid minerals. A new review article explores what scientists know about the atom-by-atom process.
Scientists are pioneering approaches in the branch of artificial intelligence known as machine learning to design and train computer software programs that guide the development of new manufacturing processes.
This PNNL-developed separation system quickly and successfully separates larger particles from smaller ones at various scales, in different solid-liquid mixtures and at different flow rates.
Johannes Lercher, Battelle Fellow and director of the PNNL Institute for Integrated Catalysis, envisions energy storage solutions at the new Energy Sciences Center.
A Q&A with Lauren Charles, veterinarian and PNNL data scientist, on zoonotic diseases and the role biosurveillance plays in mitigating the growing threat to global health.
PNNL’s new Hydrogen Energy Storage Evaluation Tool allows users to examine multiple energy delivery pathways and grid applications to maximize benefits.
PNNL combines AI and cloud computing with damage assessment tool to predict path of wildfires and quickly evaluate the impact of natural disasters, giving first responders an upper hand.