Researchers at PNNL have developed an interpretable, lightweight AI model that can easily predict weld microstructure features using only basic machine sensor inputs.

PNNL researchers Daniel Deng and Yehia Ibrahim join the 2025 class of National Academy of Inventors Fellows.

PNNL researchers have developed a new, physics-informed machine learning model that accurately predicts how heat accumulates and dissipates during friction stir processing.

A new mini-acoustic transmitter and tagging procedure is able to provide data on small, sensitive fish species like the American shad.

New methodological approach demonstrates how to assess the economic value, including non-traditional value streams, of converting non-powered dams to hydroelectric facilities.

Developed with community input, the new Hydropower Vision Roadmap lays out a path to achieve a shared vison for modern hydropower by 2050.