Machine-learned prediction of the electronic fields in a crystal

Ying Shi Teh; Swarnava Ghosh; Kaushik Bhattacharya

doi:10.1016/j.mechmat.2021.104070

Machine-learned prediction of the electronic fields in a crystal

Ying Shi Teh, Swarnava Ghosh, Kaushik Bhattacharya

Advanced Computing for Chemistry and Mat

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

11 Scopus citations

Abstract

We propose an approach for exploiting machine learning to approximate electronic fields in crystalline solids subjected to deformation. Strain engineering is emerging as a widely used method for tuning the properties of materials, and this requires repeated density functional theory calculations of the unit cell subjected to strain. Repeated unit cell calculations are also required for multi-resolution studies of defects in crystalline solids. We propose an approach that uses data from such calculations to train a carefully architected machine learning approximation. We demonstrate the approach on magnesium, a promising light-weight structural material: we show that we can predict the energy and electronic fields to the level of chemical accuracy, and even capture lattice instabilities.

Original language	English
Article number	104070
Journal	Mechanics of Materials
Volume	163
DOIs	https://doi.org/10.1016/j.mechmat.2021.104070
State	Published - Dec 2021

Funding

We are grateful to the De Logi foundation and the Army Research Laboratory, USA (under Cooperative Agreement Number W911NF-12-2-0022 ) for their generous support of the research. The views and conclusions contained in this document are those of the authors and should not be interpreted as representing the official policies, either expressed or implied, of the Army Research Laboratory or the U.S. Government. The U.S. Government is authorized to reproduce and distribute reprints for Government purposes notwithstanding any copyright notation herein.

Keywords

Density Functional Theory
First principles calculations
Machine learning
Material Instability

Access to Document

10.1016/j.mechmat.2021.104070

Cite this

@article{bb015be106254ddfb848bd6e478fb2ec,

title = "Machine-learned prediction of the electronic fields in a crystal",

abstract = "We propose an approach for exploiting machine learning to approximate electronic fields in crystalline solids subjected to deformation. Strain engineering is emerging as a widely used method for tuning the properties of materials, and this requires repeated density functional theory calculations of the unit cell subjected to strain. Repeated unit cell calculations are also required for multi-resolution studies of defects in crystalline solids. We propose an approach that uses data from such calculations to train a carefully architected machine learning approximation. We demonstrate the approach on magnesium, a promising light-weight structural material: we show that we can predict the energy and electronic fields to the level of chemical accuracy, and even capture lattice instabilities.",

keywords = "Density Functional Theory, First principles calculations, Machine learning, Material Instability",

author = "Teh, {Ying Shi} and Swarnava Ghosh and Kaushik Bhattacharya",

note = "Publisher Copyright: {\textcopyright} 2021 Elsevier Ltd",

year = "2021",

month = dec,

doi = "10.1016/j.mechmat.2021.104070",

language = "English",

volume = "163",

journal = "Mechanics of Materials",

issn = "0167-6636",

publisher = "Elsevier",

}

TY - JOUR

T1 - Machine-learned prediction of the electronic fields in a crystal

AU - Teh, Ying Shi

AU - Ghosh, Swarnava

AU - Bhattacharya, Kaushik

PY - 2021/12

Y1 - 2021/12

N2 - We propose an approach for exploiting machine learning to approximate electronic fields in crystalline solids subjected to deformation. Strain engineering is emerging as a widely used method for tuning the properties of materials, and this requires repeated density functional theory calculations of the unit cell subjected to strain. Repeated unit cell calculations are also required for multi-resolution studies of defects in crystalline solids. We propose an approach that uses data from such calculations to train a carefully architected machine learning approximation. We demonstrate the approach on magnesium, a promising light-weight structural material: we show that we can predict the energy and electronic fields to the level of chemical accuracy, and even capture lattice instabilities.

AB - We propose an approach for exploiting machine learning to approximate electronic fields in crystalline solids subjected to deformation. Strain engineering is emerging as a widely used method for tuning the properties of materials, and this requires repeated density functional theory calculations of the unit cell subjected to strain. Repeated unit cell calculations are also required for multi-resolution studies of defects in crystalline solids. We propose an approach that uses data from such calculations to train a carefully architected machine learning approximation. We demonstrate the approach on magnesium, a promising light-weight structural material: we show that we can predict the energy and electronic fields to the level of chemical accuracy, and even capture lattice instabilities.

KW - Density Functional Theory

KW - First principles calculations

KW - Machine learning

KW - Material Instability

UR - http://www.scopus.com/inward/record.url?scp=85116404014&partnerID=8YFLogxK

U2 - 10.1016/j.mechmat.2021.104070

DO - 10.1016/j.mechmat.2021.104070

M3 - Article

AN - SCOPUS:85116404014

SN - 0167-6636

VL - 163

JO - Mechanics of Materials

JF - Mechanics of Materials

M1 - 104070

ER -

Machine-learned prediction of the electronic fields in a crystal

Abstract

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this