Cargando…

Classification of crystal structures using electron diffraction patterns with a deep convolutional neural network

Investigations have been made to explore the applicability of an off-the-shelf deep convolutional neural network (DCNN) architecture, residual neural network (ResNet), to the classification of the crystal structure of materials using electron diffraction patterns without prior knowledge of the mater...

Descripción completa

Detalles Bibliográficos
Autores principales: Ra, Moonsoo, Boo, Younggun, Jeong, Jae Min, Batts-Etseg, Jargalsaikhan, Jeong, Jinha, Lee, Woong
Formato: Online Artículo Texto
Lenguaje:English
Publicado: The Royal Society of Chemistry 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9043913/
https://www.ncbi.nlm.nih.gov/pubmed/35493237
http://dx.doi.org/10.1039/d1ra07156d
_version_ 1784694989688668160
author Ra, Moonsoo
Boo, Younggun
Jeong, Jae Min
Batts-Etseg, Jargalsaikhan
Jeong, Jinha
Lee, Woong
author_facet Ra, Moonsoo
Boo, Younggun
Jeong, Jae Min
Batts-Etseg, Jargalsaikhan
Jeong, Jinha
Lee, Woong
author_sort Ra, Moonsoo
collection PubMed
description Investigations have been made to explore the applicability of an off-the-shelf deep convolutional neural network (DCNN) architecture, residual neural network (ResNet), to the classification of the crystal structure of materials using electron diffraction patterns without prior knowledge of the material systems under consideration. The dataset required for training and validating the ResNet architectures was obtained by the computer simulation of the selected area electron diffraction (SAD) in transmission electron microscopy. Acceleration voltages, zone axes, and camera lengths were used as variables and crystal information format (CIF) files obtained from open crystal data repositories were used as inputs. The cubic crystal system was chosen as a model system and five space groups of 213, 221, 225, 227, and 229 in the cubic system were selected for the test and validation, based on the distinguishability of the SAD patterns. The simulated diffraction patterns were regrouped and labeled from the viewpoint of computer vision, i.e., 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%.
format Online
Article
Text
id pubmed-9043913
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher The Royal Society of Chemistry
record_format MEDLINE/PubMed
spelling pubmed-90439132022-04-28 Classification of crystal structures using electron diffraction patterns with a deep convolutional neural network Ra, Moonsoo Boo, Younggun Jeong, Jae Min Batts-Etseg, Jargalsaikhan Jeong, Jinha Lee, Woong RSC Adv Chemistry Investigations have been made to explore the applicability of an off-the-shelf deep convolutional neural network (DCNN) architecture, residual neural network (ResNet), to the classification of the crystal structure of materials using electron diffraction patterns without prior knowledge of the material systems under consideration. The dataset required for training and validating the ResNet architectures was obtained by the computer simulation of the selected area electron diffraction (SAD) in transmission electron microscopy. Acceleration voltages, zone axes, and camera lengths were used as variables and crystal information format (CIF) files obtained from open crystal data repositories were used as inputs. The cubic crystal system was chosen as a model system and five space groups of 213, 221, 225, 227, and 229 in the cubic system were selected for the test and validation, based on the distinguishability of the SAD patterns. The simulated diffraction patterns were regrouped and labeled from the viewpoint of computer vision, i.e., 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%. The Royal Society of Chemistry 2021-11-29 /pmc/articles/PMC9043913/ /pubmed/35493237 http://dx.doi.org/10.1039/d1ra07156d Text en This journal is © The Royal Society of Chemistry https://creativecommons.org/licenses/by-nc/3.0/
spellingShingle Chemistry
Ra, Moonsoo
Boo, Younggun
Jeong, Jae Min
Batts-Etseg, Jargalsaikhan
Jeong, Jinha
Lee, Woong
Classification of crystal structures using electron diffraction patterns with a deep convolutional neural network
title Classification of crystal structures using electron diffraction patterns with a deep convolutional neural network
title_full Classification of crystal structures using electron diffraction patterns with a deep convolutional neural network
title_fullStr Classification of crystal structures using electron diffraction patterns with a deep convolutional neural network
title_full_unstemmed Classification of crystal structures using electron diffraction patterns with a deep convolutional neural network
title_short Classification of crystal structures using electron diffraction patterns with a deep convolutional neural network
title_sort classification of crystal structures using electron diffraction patterns with a deep convolutional neural network
topic Chemistry
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9043913/
https://www.ncbi.nlm.nih.gov/pubmed/35493237
http://dx.doi.org/10.1039/d1ra07156d
work_keys_str_mv AT ramoonsoo classificationofcrystalstructuresusingelectrondiffractionpatternswithadeepconvolutionalneuralnetwork
AT booyounggun classificationofcrystalstructuresusingelectrondiffractionpatternswithadeepconvolutionalneuralnetwork
AT jeongjaemin classificationofcrystalstructuresusingelectrondiffractionpatternswithadeepconvolutionalneuralnetwork
AT battsetsegjargalsaikhan classificationofcrystalstructuresusingelectrondiffractionpatternswithadeepconvolutionalneuralnetwork
AT jeongjinha classificationofcrystalstructuresusingelectrondiffractionpatternswithadeepconvolutionalneuralnetwork
AT leewoong classificationofcrystalstructuresusingelectrondiffractionpatternswithadeepconvolutionalneuralnetwork