Classification of crystal structures using electron diffraction patterns with a deep convolutional neural network
Moonsoo Ra, Younggun Boo, Jae Min Jeong, Jae Min Jeong, Jargalsaikhan Batts-Etseg, Jinha Jeong, Jinha Jeong, Woong Lee
Abstract
, the way how the neural network recognizes the two-dimensional representation of three-dimensional lattice structure of crystals, for improved training and classification efficiency. Comparison of the various ResNet architectures with varying number of layers demonstrated that the ResNet101 architecture could classify the space groups with the validation accuracy of 92.607%.
Topics & Concepts
Convolutional neural networkComputer scienceArtificial neural networkDiffractionElectron diffractionArtificial intelligenceResidual neural networkPattern recognition (psychology)Crystal (programming language)Crystal structureCrystallographyOpticsPhysicsChemistryProgramming languageMachine Learning in Materials ScienceX-ray Diffraction in CrystallographyElectron and X-Ray Spectroscopy Techniques