edoc

Crystal structure representations for machine learning models of formation energies

Faber, Felix and Lindmaa, Alexander and von Lilienfeld, O. Anatole and Armiento, Rickard. (2015) Crystal structure representations for machine learning models of formation energies. International Journal of Quantum Chemistry, 115 (16). pp. 1094-1101.

[img]
Preview
PDF - Accepted Version
2597Kb

Official URL: http://edoc.unibas.ch/53264/

Downloads: Statistics Overview

Abstract

We introduce and evaluate a set of feature vector representations of crystal structures for machine learning (ML) models of formation energies of solids. ML models of atomization energies of organic molecules have been successful using a Coulomb matrix representation of the molecule. We consider three ways to generalize such representations to periodic systems: (i) a matrix where each element is related to the Ewald sum of the electrostatic interaction between two different atoms in the unit cell repeated over the lattice; (ii) an extended Coulomb-like matrix that takes into account a number of neighboring unit cells; and (iii) an ansatz that mimics the periodicity and the basic features of the elements in the Ewald sum matrix using a sine function of the crystal coordinates of the atoms. The representations are compared for a Laplacian kernel with Manhattan norm, trained to reproduce formation energies using a dataset of 3938 crystal structures obtained from the Materials Project. For training sets consisting of 3000 crystals, the generalization error in predicting formation energies of new structures corresponds to (i) 0.49, (ii) 0.64, and (iii) 0.37eV/atom for the respective representations. (c) 2015 Wiley Periodicals, Inc.
Faculties and Departments:05 Faculty of Science > Departement Chemie > Former Organization Units Chemistry > Physikalische Chemie (Lilienfeld)
UniBasel Contributors:von Lilienfeld, Anatole
Item Type:Article, refereed
Article Subtype:Research Article
Publisher:Wiley
ISSN:0020-7608
e-ISSN:1097-461X
Note:Publication type according to Uni Basel Research Database: Journal article
Language:English
Identification Number:
edoc DOI:
Last Modified:25 Feb 2020 11:45
Deposited On:25 Jan 2017 14:16

Repository Staff Only: item control page