Machine learning-based prediction models for formation energies of interstitial atoms in HCP crystals

Daegun You; Shraddha Ganorkar; Sooran Kim; Keonwook Kang; Won Yong Shin; Dongwoo Lee

doi:10.1016/j.scriptamat.2020.02.042

Machine learning-based prediction models for formation energies of interstitial atoms in HCP crystals

Daegun You, Shraddha Ganorkar, Sooran Kim, Keonwook Kang, Won Yong Shin, Dongwoo Lee

Research output: Contribution to journal › Article › peer-review

1 Citation (Scopus)

Abstract

Prediction models of the formation energies of H, B, C, N, and O atoms in various interstitial sites of hcp-Ti, Zr, and Hf crystals are developed based on machine learning. Parametric models such as linear regression and brute force search (BFS) as well as nonparametric algorithms including the support vector regression (SVR) and the Gaussian process regression (GPR) are employed. Readily accessible chemical and geometrical descriptors allow straightforward implementation of the prediction models without any expensive computational modeling. The models based on BFS, SVR, and GPR show the excellent performance with R² > 96%.

Original language	English
Pages (from-to)	1-5
Number of pages	5
Journal	Scripta Materialia
Volume	183
DOIs	https://doi.org/10.1016/j.scriptamat.2020.02.042
Publication status	Published - 2020 Jul 1

Bibliographical note

Funding Information:
This work was supported by the National Research Foundation of Korea (NRF) under Grant No. NRF-2017R1E1A1A01078324 and Samsung Research Funding and Incubation Center for Future Technology under Grant No. SRFC-MA1802-06 .

Funding Information:
This work was supported by the National Research Foundation of Korea (NRF) under Grant No. NRF-2017R1E1A1A01078324 and Samsung Research Funding and Incubation Center for Future Technology under Grant No. SRFC-MA1802-06.

Publisher Copyright:
© 2020 Acta Materialia Inc.

All Science Journal Classification (ASJC) codes

Materials Science(all)
Condensed Matter Physics
Mechanics of Materials
Mechanical Engineering
Metals and Alloys

Access to Document

10.1016/j.scriptamat.2020.02.042

Fingerprint Dive into the research topics of 'Machine learning-based prediction models for formation energies of interstitial atoms in HCP crystals'. Together they form a unique fingerprint.

Cite this

@article{82a49ca5f4a2436f832d2dd875d832d9,

title = "Machine learning-based prediction models for formation energies of interstitial atoms in HCP crystals",

abstract = "Prediction models of the formation energies of H, B, C, N, and O atoms in various interstitial sites of hcp-Ti, Zr, and Hf crystals are developed based on machine learning. Parametric models such as linear regression and brute force search (BFS) as well as nonparametric algorithms including the support vector regression (SVR) and the Gaussian process regression (GPR) are employed. Readily accessible chemical and geometrical descriptors allow straightforward implementation of the prediction models without any expensive computational modeling. The models based on BFS, SVR, and GPR show the excellent performance with R2 > 96%.",

author = "Daegun You and Shraddha Ganorkar and Sooran Kim and Keonwook Kang and Shin, {Won Yong} and Dongwoo Lee",

note = "Funding Information: This work was supported by the National Research Foundation of Korea (NRF) under Grant No. NRF-2017R1E1A1A01078324 and Samsung Research Funding and Incubation Center for Future Technology under Grant No. SRFC-MA1802-06 . Funding Information: This work was supported by the National Research Foundation of Korea (NRF) under Grant No. NRF-2017R1E1A1A01078324 and Samsung Research Funding and Incubation Center for Future Technology under Grant No. SRFC-MA1802-06. Publisher Copyright: {\textcopyright} 2020 Acta Materialia Inc.",

year = "2020",

month = jul,

day = "1",

doi = "10.1016/j.scriptamat.2020.02.042",

language = "English",

volume = "183",

pages = "1--5",

journal = "Scripta Materialia",

issn = "1359-6462",

publisher = "Elsevier Limited",

}

TY - JOUR

T1 - Machine learning-based prediction models for formation energies of interstitial atoms in HCP crystals

AU - You, Daegun

AU - Ganorkar, Shraddha

AU - Kim, Sooran

AU - Kang, Keonwook

AU - Shin, Won Yong

AU - Lee, Dongwoo

N1 - Funding Information: This work was supported by the National Research Foundation of Korea (NRF) under Grant No. NRF-2017R1E1A1A01078324 and Samsung Research Funding and Incubation Center for Future Technology under Grant No. SRFC-MA1802-06 . Funding Information: This work was supported by the National Research Foundation of Korea (NRF) under Grant No. NRF-2017R1E1A1A01078324 and Samsung Research Funding and Incubation Center for Future Technology under Grant No. SRFC-MA1802-06. Publisher Copyright: © 2020 Acta Materialia Inc.

PY - 2020/7/1

Y1 - 2020/7/1

N2 - Prediction models of the formation energies of H, B, C, N, and O atoms in various interstitial sites of hcp-Ti, Zr, and Hf crystals are developed based on machine learning. Parametric models such as linear regression and brute force search (BFS) as well as nonparametric algorithms including the support vector regression (SVR) and the Gaussian process regression (GPR) are employed. Readily accessible chemical and geometrical descriptors allow straightforward implementation of the prediction models without any expensive computational modeling. The models based on BFS, SVR, and GPR show the excellent performance with R2 > 96%.

AB - Prediction models of the formation energies of H, B, C, N, and O atoms in various interstitial sites of hcp-Ti, Zr, and Hf crystals are developed based on machine learning. Parametric models such as linear regression and brute force search (BFS) as well as nonparametric algorithms including the support vector regression (SVR) and the Gaussian process regression (GPR) are employed. Readily accessible chemical and geometrical descriptors allow straightforward implementation of the prediction models without any expensive computational modeling. The models based on BFS, SVR, and GPR show the excellent performance with R2 > 96%.

UR - http://www.scopus.com/inward/record.url?scp=85081133852&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85081133852&partnerID=8YFLogxK

U2 - 10.1016/j.scriptamat.2020.02.042

DO - 10.1016/j.scriptamat.2020.02.042

M3 - Article

AN - SCOPUS:85081133852

VL - 183

SP - 1

EP - 5

JO - Scripta Materialia

JF - Scripta Materialia

SN - 1359-6462

ER -

Machine learning-based prediction models for formation energies of interstitial atoms in HCP crystals

Abstract

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Cite this