Researchers at PNNL have developed an interpretable, lightweight AI model that can easily predict weld microstructure features using only basic machine sensor inputs.
Matteo Muratori, director of transportation and industry programs at PNNL, has been named to the 2026–2028 cohort of the National Academies of Sciences, Engineering, and Medicine’s New Voices Program.
This summer, PNNL hosted the inaugural “As Conductive As Copper” (AC2.0) workshop, fostering a collaborative conversation on the future of the U.S. copper supply chain.
Shear Assisted Processing and Extrusion (ShAPE) imparts significantly more deformation compared to conventional extrusion. The latest ShAPE system at PNNL, ShAPEshifter, is a purpose-built machine designed for maximum configurability.
PNNL researchers have developed a new, physics-informed machine learning model that accurately predicts how heat accumulates and dissipates during friction stir processing.
PNNL researchers are exploring the kinds of flicker waveforms that the eye and brain can detect, seeking to understand the different visual and non-visual effects that result.
A compilation of soil viral genomes provides a comprehensive description of the soil virosphere, its potential to impact global biogeochemistry, and an open database for future investigations of soil viral ecology.
GUV can reduce transmission of airborne disease while reducing energy use and carbon emissions. But fulfilling that promise depends on having accurate and verifiable performance data.
Researchers devised a quantitative and predictive understanding of the cloud chemistry of biomass-burning organic gases helping increase the understanding of wildfires.
Spatial proteomics enables researchers to link protein measurements to features in the image of a tissue sample, which are lost using standard approaches.
