Collaborative crystal structure prediction

Sangheum Hwang, Jiho Yoo, Chanhee Lee, Sang Hyun Lee

Research output: Contribution to journalArticle

Abstract

The prediction of crystal structures is one of the most essential challenges in designing novel functional materials. A data-driven prediction technique that uses the database of known crystal structures and substitutes ions among materials of known crystal structures to concoct new crystal structures has been proposed. This technique has been applied to generate crystal-structure candidates for the purpose of first-principles-calculation-based high-throughput computational screening. However, this technique has a functional limitation that the ion substitution tendencies are available only for typical ions such that their associated crystal structures appear in well-known materials. To overcome such a limitation, this work introduces an idea of collaborative filtering to the calculation of the ionic substitution tendencies. Based on this idea, we develop symmetric matrix factorization (SMF) method to model underlying substitution conditions. In addition, we present a symmetric matrix co-factorization (SMCF) method to incorporate additional knowledge pertaining to chemical properties in estimating the substitution tendencies among ions with extremely small amount of previous knowledge in the database. The performance of the prediction is investigated along with existing techniques through in silico experiments using real crystal-structure database. The numerical results show that the proposed SMF- and SMCF-based prediction outperform existing techniques in terms of the prediction accuracy.

Original languageEnglish
Pages (from-to)222-230
Number of pages9
JournalExpert Systems with Applications
Volume63
DOIs
Publication statusPublished - 2016 Nov 30
Externally publishedYes

Fingerprint

Crystal structure
Factorization
Substitution reactions
Ions
Collaborative filtering
Functional materials
Chemical properties
Screening
Throughput
Experiments

Keywords

  • Collaborative filtering
  • Crystal structure prediction
  • High-throughput computational screening
  • Side information

ASJC Scopus subject areas

  • Engineering(all)
  • Computer Science Applications
  • Artificial Intelligence

Cite this

Collaborative crystal structure prediction. / Hwang, Sangheum; Yoo, Jiho; Lee, Chanhee; Lee, Sang Hyun.

In: Expert Systems with Applications, Vol. 63, 30.11.2016, p. 222-230.

Research output: Contribution to journalArticle

Hwang, Sangheum ; Yoo, Jiho ; Lee, Chanhee ; Lee, Sang Hyun. / Collaborative crystal structure prediction. In: Expert Systems with Applications. 2016 ; Vol. 63. pp. 222-230.
@article{ec2b64bfeb5743c69ac9e412bc1f24e1,
title = "Collaborative crystal structure prediction",
abstract = "The prediction of crystal structures is one of the most essential challenges in designing novel functional materials. A data-driven prediction technique that uses the database of known crystal structures and substitutes ions among materials of known crystal structures to concoct new crystal structures has been proposed. This technique has been applied to generate crystal-structure candidates for the purpose of first-principles-calculation-based high-throughput computational screening. However, this technique has a functional limitation that the ion substitution tendencies are available only for typical ions such that their associated crystal structures appear in well-known materials. To overcome such a limitation, this work introduces an idea of collaborative filtering to the calculation of the ionic substitution tendencies. Based on this idea, we develop symmetric matrix factorization (SMF) method to model underlying substitution conditions. In addition, we present a symmetric matrix co-factorization (SMCF) method to incorporate additional knowledge pertaining to chemical properties in estimating the substitution tendencies among ions with extremely small amount of previous knowledge in the database. The performance of the prediction is investigated along with existing techniques through in silico experiments using real crystal-structure database. The numerical results show that the proposed SMF- and SMCF-based prediction outperform existing techniques in terms of the prediction accuracy.",
keywords = "Collaborative filtering, Crystal structure prediction, High-throughput computational screening, Side information",
author = "Sangheum Hwang and Jiho Yoo and Chanhee Lee and Lee, {Sang Hyun}",
year = "2016",
month = "11",
day = "30",
doi = "10.1016/j.eswa.2016.07.001",
language = "English",
volume = "63",
pages = "222--230",
journal = "Expert Systems with Applications",
issn = "0957-4174",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - Collaborative crystal structure prediction

AU - Hwang, Sangheum

AU - Yoo, Jiho

AU - Lee, Chanhee

AU - Lee, Sang Hyun

PY - 2016/11/30

Y1 - 2016/11/30

N2 - The prediction of crystal structures is one of the most essential challenges in designing novel functional materials. A data-driven prediction technique that uses the database of known crystal structures and substitutes ions among materials of known crystal structures to concoct new crystal structures has been proposed. This technique has been applied to generate crystal-structure candidates for the purpose of first-principles-calculation-based high-throughput computational screening. However, this technique has a functional limitation that the ion substitution tendencies are available only for typical ions such that their associated crystal structures appear in well-known materials. To overcome such a limitation, this work introduces an idea of collaborative filtering to the calculation of the ionic substitution tendencies. Based on this idea, we develop symmetric matrix factorization (SMF) method to model underlying substitution conditions. In addition, we present a symmetric matrix co-factorization (SMCF) method to incorporate additional knowledge pertaining to chemical properties in estimating the substitution tendencies among ions with extremely small amount of previous knowledge in the database. The performance of the prediction is investigated along with existing techniques through in silico experiments using real crystal-structure database. The numerical results show that the proposed SMF- and SMCF-based prediction outperform existing techniques in terms of the prediction accuracy.

AB - The prediction of crystal structures is one of the most essential challenges in designing novel functional materials. A data-driven prediction technique that uses the database of known crystal structures and substitutes ions among materials of known crystal structures to concoct new crystal structures has been proposed. This technique has been applied to generate crystal-structure candidates for the purpose of first-principles-calculation-based high-throughput computational screening. However, this technique has a functional limitation that the ion substitution tendencies are available only for typical ions such that their associated crystal structures appear in well-known materials. To overcome such a limitation, this work introduces an idea of collaborative filtering to the calculation of the ionic substitution tendencies. Based on this idea, we develop symmetric matrix factorization (SMF) method to model underlying substitution conditions. In addition, we present a symmetric matrix co-factorization (SMCF) method to incorporate additional knowledge pertaining to chemical properties in estimating the substitution tendencies among ions with extremely small amount of previous knowledge in the database. The performance of the prediction is investigated along with existing techniques through in silico experiments using real crystal-structure database. The numerical results show that the proposed SMF- and SMCF-based prediction outperform existing techniques in terms of the prediction accuracy.

KW - Collaborative filtering

KW - Crystal structure prediction

KW - High-throughput computational screening

KW - Side information

UR - http://www.scopus.com/inward/record.url?scp=84978737279&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84978737279&partnerID=8YFLogxK

U2 - 10.1016/j.eswa.2016.07.001

DO - 10.1016/j.eswa.2016.07.001

M3 - Article

VL - 63

SP - 222

EP - 230

JO - Expert Systems with Applications

JF - Expert Systems with Applications

SN - 0957-4174

ER -