Crystal Structure Representation for Neural Networks using Topological Approach

Aleksandr V. Fedorov, Ivan V. Shamanaev

Research output: Contribution to journalArticlepeer-review

5 Citations (Scopus)

Abstract

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 %.

Original languageEnglish
Article number1600162
Number of pages7
JournalMolecular Informatics
Volume36
Issue number8
DOIs
Publication statusPublished - Aug 2017

Keywords

  • artificial neural network
  • entropy
  • lattice energy
  • molar heat capacity
  • ToposPro
  • GRAPH
  • DESIGN
  • LATTICE ENERGIES
  • PREDICTION
  • SPACE
  • MATERIALS INFORMATICS
  • SOLIDS
  • INORGANIC-COMPOUNDS
  • ENERGY ESTIMATION

Fingerprint

Dive into the research topics of 'Crystal Structure Representation for Neural Networks using Topological Approach'. Together they form a unique fingerprint.

Cite this