For more than 100 years, scientists have used a method called crystallography to determine the atomic structure of materials, but this technique only works well when researchers have large, pure crystals. For a powder of nanocrystals, the method only hints at the unseen structure. Now, scientists at Columbia Engineering have created a machine learning algorithm that can observe the pattern produced by a powder of nanocrystals to infer their atomic structures. The scientists began with a dataset of 40,000 crystal structures and jumbled their atomic positions until they were indistinguishable from random placement. Then, they trained a deep neural network to connect these almost randomly placed nanocrystals with their associated X-ray diffraction patterns. Lastly, the algorithm was able to determine the atomic structure from nanocrystals of various shapes in the powder.
An official website of the United States government.
