Orbital-free bond breaking via machine learning

John C. Snyder, Matthias Rupp, Katja Hansen, Leo Blooston, Klaus Muller, Kieron Burke

Research output: Contribution to journalArticle

40 Citations (Scopus)

Abstract

Using a one-dimensional model, we explore the ability of machine learning to approximate the non-interacting kinetic energy density functional of diatomics. This nonlinear interpolation between Kohn-Sham reference calculations can (i) accurately dissociate a diatomic, (ii) be systematically improved with increased reference data and (iii) generate accurate self-consistent densities via a projection method that avoids directions with no data. With relatively few densities, the error due to the interpolation is smaller than typical errors in standard exchange-correlation functionals.

Original languageEnglish
Article number224104
JournalJournal of Chemical Physics
Volume139
Issue number22
DOIs
Publication statusPublished - 2013 Dec 14

Fingerprint

machine learning
Learning systems
Interpolation
orbitals
interpolation
Kinetic energy
functionals
flux density
kinetic energy
projection
Direction compound

ASJC Scopus subject areas

  • Physics and Astronomy(all)
  • Physical and Theoretical Chemistry

Cite this

Snyder, J. C., Rupp, M., Hansen, K., Blooston, L., Muller, K., & Burke, K. (2013). Orbital-free bond breaking via machine learning. Journal of Chemical Physics, 139(22), [224104]. https://doi.org/10.1063/1.4834075

Orbital-free bond breaking via machine learning. / Snyder, John C.; Rupp, Matthias; Hansen, Katja; Blooston, Leo; Muller, Klaus; Burke, Kieron.

In: Journal of Chemical Physics, Vol. 139, No. 22, 224104, 14.12.2013.

Research output: Contribution to journalArticle

Snyder, JC, Rupp, M, Hansen, K, Blooston, L, Muller, K & Burke, K 2013, 'Orbital-free bond breaking via machine learning', Journal of Chemical Physics, vol. 139, no. 22, 224104. https://doi.org/10.1063/1.4834075
Snyder JC, Rupp M, Hansen K, Blooston L, Muller K, Burke K. Orbital-free bond breaking via machine learning. Journal of Chemical Physics. 2013 Dec 14;139(22). 224104. https://doi.org/10.1063/1.4834075
Snyder, John C. ; Rupp, Matthias ; Hansen, Katja ; Blooston, Leo ; Muller, Klaus ; Burke, Kieron. / Orbital-free bond breaking via machine learning. In: Journal of Chemical Physics. 2013 ; Vol. 139, No. 22.
@article{df63f556c4fd4c5c856036b1bd81fcc9,
title = "Orbital-free bond breaking via machine learning",
abstract = "Using a one-dimensional model, we explore the ability of machine learning to approximate the non-interacting kinetic energy density functional of diatomics. This nonlinear interpolation between Kohn-Sham reference calculations can (i) accurately dissociate a diatomic, (ii) be systematically improved with increased reference data and (iii) generate accurate self-consistent densities via a projection method that avoids directions with no data. With relatively few densities, the error due to the interpolation is smaller than typical errors in standard exchange-correlation functionals.",
author = "Snyder, {John C.} and Matthias Rupp and Katja Hansen and Leo Blooston and Klaus Muller and Kieron Burke",
year = "2013",
month = "12",
day = "14",
doi = "10.1063/1.4834075",
language = "English",
volume = "139",
journal = "Journal of Chemical Physics",
issn = "0021-9606",
publisher = "American Institute of Physics Publising LLC",
number = "22",

}

TY - JOUR

T1 - Orbital-free bond breaking via machine learning

AU - Snyder, John C.

AU - Rupp, Matthias

AU - Hansen, Katja

AU - Blooston, Leo

AU - Muller, Klaus

AU - Burke, Kieron

PY - 2013/12/14

Y1 - 2013/12/14

N2 - Using a one-dimensional model, we explore the ability of machine learning to approximate the non-interacting kinetic energy density functional of diatomics. This nonlinear interpolation between Kohn-Sham reference calculations can (i) accurately dissociate a diatomic, (ii) be systematically improved with increased reference data and (iii) generate accurate self-consistent densities via a projection method that avoids directions with no data. With relatively few densities, the error due to the interpolation is smaller than typical errors in standard exchange-correlation functionals.

AB - Using a one-dimensional model, we explore the ability of machine learning to approximate the non-interacting kinetic energy density functional of diatomics. This nonlinear interpolation between Kohn-Sham reference calculations can (i) accurately dissociate a diatomic, (ii) be systematically improved with increased reference data and (iii) generate accurate self-consistent densities via a projection method that avoids directions with no data. With relatively few densities, the error due to the interpolation is smaller than typical errors in standard exchange-correlation functionals.

UR - http://www.scopus.com/inward/record.url?scp=84903362304&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84903362304&partnerID=8YFLogxK

U2 - 10.1063/1.4834075

DO - 10.1063/1.4834075

M3 - Article

VL - 139

JO - Journal of Chemical Physics

JF - Journal of Chemical Physics

SN - 0021-9606

IS - 22

M1 - 224104

ER -