Crystal symmetry classification from powder X-ray diffraction patterns using a convolutional neural network

Описание

Тип публикации: статья из журнала

Год издания: 2020

Идентификатор DOI: 10.1016/j.mtcomm.2020.101662

Ключевые слова: artificial neural networks, crystal systems, powder diffraction, space groups

Аннотация: A convolutional artificial neural network was applied to identify crystal systems and symmetry space groups by full-profile X-ray diffraction patterns calculated from crystal structures of the ICSD 2017 database. The database contains 192 004 crystal structures; 80 % of them were used as a training dataset, and the other 20 % were Показать полностьюused as a test dataset to establish the accuracy of classification. The neural network identified crystal systems correctly for 90.02 % of structures and space groups for 79.82 % of structures from the test dataset. Factors affecting the classification accuracy were established. The first, nonlinear normalization of intensities of diffraction peaks increases the accuracy, and the second, the accuracy depends on the number of structures represented in each space group. © 2020 Elsevier Ltd

Ссылки на полный текст

Издание

Журнал: Materials Today Communications

Выпуск журнала: Vol. 25

Номера страниц: 101662

ISSN журнала: 23524928

Персоны

  • Zaloga Alexander N. (Siberian Fed Univ, 79 Svobodny, Krasnoyarsk 660041, Russia)
  • Stanovov Vladimir V. (Siberian Fed Univ, 79 Svobodny, Krasnoyarsk 660041, Russia)
  • Bezrukova Oksana E. (Siberian Fed Univ, 79 Svobodny, Krasnoyarsk 660041, Russia)
  • Dubinin Petr S. (Siberian Fed Univ, 79 Svobodny, Krasnoyarsk 660041, Russia)
  • Yakimov Igor S. (Siberian Fed Univ, 79 Svobodny, Krasnoyarsk 660041, Russia)