Nature

Linking atomic structural defects to mesoscale properties in crystalline solids using graph neural networks

Structural defects are abundant in solids, and vital to the macroscopic materials properties. However, a defect-property linkage typically requires significant efforts from experiments or simulations, ...
Phys.org

AI model can reveal the structures of crystalline materials

For more than 100 years, scientists have been using X-ray crystallography to determine the structure of crystalline materials such as metals, rocks, and ceramics. This technique works best when the ...
Nature

Equivariant diffusion solution for inorganic crystal structure determination from powder X-ray diffraction data

X-ray diffraction (XRD) is one of the most widely used structural characterization techniques for inorganic crystalline materials. Since Bragg’s law was first proposed in 1912, X-ray crystallography ...
Phys.org

Crystallography-informed AI achieves high performance in predicting novel crystal structures

A research team from the Institute of Statistical Mathematics and Panasonic Holdings Corporation has developed a machine learning algorithm, ShotgunCSP, that enables fast and accurate prediction of ...