Premium
Crystal Structure Representation for Neural Networks using Topological Approach
Author(s) -
Fedorov Aleksandr V.,
Shamanaev Ivan V.
Publication year - 2017
Publication title -
molecular informatics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.481
H-Index - 68
eISSN - 1868-1751
pISSN - 1868-1743
DOI - 10.1002/minf.201600162
Subject(s) - broyden–fletcher–goldfarb–shanno algorithm , artificial neural network , crystal structure , topology (electrical circuits) , representation (politics) , computer science , crystal (programming language) , lattice (music) , materials science , mathematics , machine learning , chemistry , physics , crystallography , combinatorics , computer network , programming language , asynchronous communication , politics , political science , acoustics , law
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 %.