Sciact
  • EN
  • RU

Crystal Structure Representation for Neural Networks using Topological Approach Научная публикация

Журнал Molecular Informatics
ISSN: 1868-1743 , E-ISSN: 1868-1751
Вых. Данные Год: 2017, Том: 36, Номер: 8, Номер статьи : 1600162, Страниц : 7 DOI: 10.1002/minf.201600162
Ключевые слова artificial neural network, entropy, lattice energy, molar heat capacity, ToposPro
Авторы Fedorov Aleksandr V. 1,2 , Shamanaev Ivan V. 1
Организации
1 Boreskov Institute of Catalysis, pr. Lavrentieva 5, Novosibirsk, Russia, 630090
2 Novosibirsk State University, 2 Pirogova Str., Novosibirsk, Russia, 630090

Реферат: In the present work we describe a new approach, which uses topology of crystals for physicochemical properties prediction using artificial neural networks (ANN). The topologies of 268 crystal structures were determined using ToposPro software. Quotient graphs were used to identify topological centers and their neighbors. The topological approach was illustrated by training ANN to predict molar heat capacity, standard molar entropy and lattice energy of 268 crystals with different compositions and structures (metals, inorganic salts, oxides, etc.). ANN was trained using Broyden-Fletcher-Goldfarb-Shanno (BFGS) algorithm. Mean absolute percentage error of predicted properties was ≤8 %.
Библиографическая ссылка: Fedorov A.V. , Shamanaev I.V.
Crystal Structure Representation for Neural Networks using Topological Approach
Molecular Informatics. 2017. V.36. N8. 1600162 :1-7. DOI: 10.1002/minf.201600162 WOS Scopus РИНЦ CAPlusCA PMID OpenAlex
Даты:
Поступила в редакцию: 30 дек. 2016 г.
Принята к публикации: 2 мар. 2017 г.
Опубликована online: 7 мар. 2017 г.
Опубликована в печати: 1 авг. 2017 г.
Идентификаторы БД:
Web of science: WOS:000407475600002
Scopus: 2-s2.0-85014617589
РИНЦ: 31014788
Chemical Abstracts: 2017:379548
Chemical Abstracts (print): 167:415948
PMID (PubMed): 28266179
OpenAlex: W2592684016
Цитирование в БД:
БД Цитирований
Web of science 13
Scopus 13
РИНЦ 12
OpenAlex 17
Альметрики: