Research output: Contribution to journal › Article › peer-review
Crystal Structure Representation for Neural Networks using Topological Approach. / Fedorov, Aleksandr V.; Shamanaev, Ivan V.
In: Molecular Informatics, Vol. 36, No. 8, 1600162, 08.2017.Research output: Contribution to journal › Article › peer-review
}
TY - JOUR
T1 - Crystal Structure Representation for Neural Networks using Topological Approach
AU - Fedorov, Aleksandr V.
AU - Shamanaev, Ivan V.
PY - 2017/8
Y1 - 2017/8
N2 - 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 %.
AB - 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 %.
KW - artificial neural network
KW - entropy
KW - lattice energy
KW - molar heat capacity
KW - ToposPro
KW - GRAPH
KW - DESIGN
KW - LATTICE ENERGIES
KW - PREDICTION
KW - SPACE
KW - MATERIALS INFORMATICS
KW - SOLIDS
KW - INORGANIC-COMPOUNDS
KW - ENERGY ESTIMATION
UR - http://www.scopus.com/inward/record.url?scp=85014617589&partnerID=8YFLogxK
U2 - 10.1002/minf.201600162
DO - 10.1002/minf.201600162
M3 - Article
AN - SCOPUS:85014617589
VL - 36
JO - Molecular Informatics
JF - Molecular Informatics
SN - 1868-1743
IS - 8
M1 - 1600162
ER -
ID: 10276210