PNNL's “co-scientist” serves as a one-stop AI shop for accelerating scientific discovery. By leveraging AI agents, researchers can explore scientific databases, conduct analyses and request step-by-step plans for testing their hypotheses.
Over the next four years, PNNL and University of Arizona will develop open-source computational tools to better identify and characterize the viruses associated with the human microbiome.
PNNL’s year in review includes highlights ranging from advancing soil science to understanding Earth systems, expanding electricity transmission, detecting fentanyl, and applying artificial intelligence to aid scientific discovery.
A team of researchers at PNNL is developing a new approach to explore the higher-dimensional shape of cyber systems to identify signatures of adversarial attacks.
PNNL biodefense experts seek to identify, understand and mitigate the risks of biological pathogens—whether naturally occurring or intentionally created—so steps can be taken to prepare and respond.
Researchers are planning for an electric grid that deploys machine learning to think ahead, plan for the worst, anticipate demand, and meet consumer needs safely and securely.
A breakthrough in electron microscopy based on deep learning can automatically visualize and identify areas of interest, helping to speed advances in materials science.
A new AI model developed at PNNL can identify patterns in electron microscope images of materials without requiring human intervention, allowing for more accurate and consistent materials science.
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.
