Researchers at PNNL have developed an interpretable, lightweight AI model that can easily predict weld microstructure features using only basic machine sensor inputs.
In the search for rare physics events, extremely pure materials are essential. A partnership between PNNL and Ultramet has led to tungsten with low contamination from other elements.
In a recent publication in Nature Communications, a team of researchers presents a mathematical theory to address the challenge of barren plateaus in quantum machine learning.
Spatial proteomics enables researchers to link protein measurements to features in the image of a tissue sample, which are lost using standard approaches.
A combined experimental and theoretical study identified multiple interactions that affect the performance of redox-active metal oxides for potential electrochemical separation and quantum computing applications.