skip to main content
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Optimized symmetry functions for machine-learning interatomic potentials of multicomponent systems

Abstract

Current machine-learning methods to reproduce ab initio potential energy landscapes suffer from an unfavorable computational scaling with respect to the number of chemical species. In this work, we propose a new approach by using optimized symmetry functions to explore similarities of structures in multicomponent systems in order to yield linear complexity. Here, we combine these symmetry functions with the charge equilibration via neural network technique, a reliable artificial neural network potential for ionic materials, and apply this method to study alkali-halide materials MX with 6 chemical species (M = {Li, Na, K} and X = {F, Cl, Br}). Our results show that our approach provides good agreement both with experimental and DFT reference data of many physical and structural properties for any chemical combination.

Authors:
ORCiD logo [1];  [2];  [1]
  1. Inst. for Advanced Studies in Basic Sciences, Zanjan (Iran)
  2. Cornell Univ., Ithaca, NY (United States)
Publication Date:
Research Org.:
Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States). National Energy Research Scientific Computing Center (NERSC); Univ. of California, Oakland, CA (United States)
Sponsoring Org.:
USDOE Office of Science (SC)
OSTI Identifier:
1543873
Grant/Contract Number:  
[AC02-05CH11231]
Resource Type:
Accepted Manuscript
Journal Name:
Journal of Chemical Physics
Additional Journal Information:
[ Journal Volume: 149; Journal Issue: 12]; Journal ID: ISSN 0021-9606
Publisher:
American Institute of Physics (AIP)
Country of Publication:
United States
Language:
English
Subject:
74 ATOMIC AND MOLECULAR PHYSICS; Chemistry; Physics

Citation Formats

Rostami, Samare, Amsler, Maximilian, and Ghasemi, S. Alireza. Optimized symmetry functions for machine-learning interatomic potentials of multicomponent systems. United States: N. p., 2018. Web. doi:10.1063/1.5040005.
Rostami, Samare, Amsler, Maximilian, & Ghasemi, S. Alireza. Optimized symmetry functions for machine-learning interatomic potentials of multicomponent systems. United States. doi:10.1063/1.5040005.
Rostami, Samare, Amsler, Maximilian, and Ghasemi, S. Alireza. Tue . "Optimized symmetry functions for machine-learning interatomic potentials of multicomponent systems". United States. doi:10.1063/1.5040005. https://www.osti.gov/servlets/purl/1543873.
@article{osti_1543873,
title = {Optimized symmetry functions for machine-learning interatomic potentials of multicomponent systems},
author = {Rostami, Samare and Amsler, Maximilian and Ghasemi, S. Alireza},
abstractNote = {Current machine-learning methods to reproduce ab initio potential energy landscapes suffer from an unfavorable computational scaling with respect to the number of chemical species. In this work, we propose a new approach by using optimized symmetry functions to explore similarities of structures in multicomponent systems in order to yield linear complexity. Here, we combine these symmetry functions with the charge equilibration via neural network technique, a reliable artificial neural network potential for ionic materials, and apply this method to study alkali-halide materials MX with 6 chemical species (M = {Li, Na, K} and X = {F, Cl, Br}). Our results show that our approach provides good agreement both with experimental and DFT reference data of many physical and structural properties for any chemical combination.},
doi = {10.1063/1.5040005},
journal = {Journal of Chemical Physics},
number = [12],
volume = [149],
place = {United States},
year = {2018},
month = {9}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Citation Metrics:
Cited by: 2 works
Citation information provided by
Web of Science

Save / Share:

Works referenced in this record:

Minima hopping: An efficient search method for the global minimum of the potential energy surface of complex molecular systems
journal, June 2004

  • Goedecker, Stefan
  • The Journal of Chemical Physics, Vol. 120, Issue 21
  • DOI: 10.1063/1.1724816

wACSF—Weighted atom-centered symmetry functions as descriptors in machine learning potentials
journal, June 2018

  • Gastegger, M.; Schwiedrzik, L.; Bittermann, M.
  • The Journal of Chemical Physics, Vol. 148, Issue 24
  • DOI: 10.1063/1.5019667

Efficiency of ab-initio total energy calculations for metals and semiconductors using a plane-wave basis set
journal, July 1996


Alchemical screening of ionic crystals
journal, January 2016

  • Solovyeva, Alisa; von Lilienfeld, O. Anatole
  • Physical Chemistry Chemical Physics, Vol. 18, Issue 45
  • DOI: 10.1039/c6cp04258a

Efficient and accurate machine-learning interpolation of atomic energies in compositions with many species
journal, July 2017


First principles phonon calculations in materials science
journal, November 2015


ReaxFF:  A Reactive Force Field for Hydrocarbons
journal, October 2001

  • van Duin, Adri C. T.; Dasgupta, Siddharth; Lorant, Francois
  • The Journal of Physical Chemistry A, Vol. 105, Issue 41
  • DOI: 10.1021/jp004368u

Commentary: The Materials Project: A materials genome approach to accelerating materials innovation
journal, July 2013

  • Jain, Anubhav; Ong, Shyue Ping; Hautier, Geoffroy
  • APL Materials, Vol. 1, Issue 1
  • DOI: 10.1063/1.4812323

A fingerprint based metric for measuring similarities of crystalline structures
journal, January 2016

  • Zhu, Li; Amsler, Maximilian; Fuhrer, Tobias
  • The Journal of Chemical Physics, Vol. 144, Issue 3
  • DOI: 10.1063/1.4940026

A New Approach to Linear Filtering and Prediction Problems
journal, March 1960

  • Kalman, R. E.
  • Journal of Basic Engineering, Vol. 82, Issue 1
  • DOI: 10.1115/1.3662552

Representing high-dimensional potential-energy surfaces for reactions at surfaces by neural networks
journal, September 2004


Second-Sound Velocities in Cubic Crystals
journal, August 1972


ElaStic: A tool for calculating second-order elastic constants from first principles
journal, August 2013

  • Golesorkhtabar, Rostam; Pavone, Pasquale; Spitaler, Jürgen
  • Computer Physics Communications, Vol. 184, Issue 8
  • DOI: 10.1016/j.cpc.2013.03.010

Neural network potentials for metals and oxides - First applications to copper clusters at zinc oxide
journal, November 2012

  • Artrith, Nongnuch; Hiller, Björn; Behler, Jörg
  • physica status solidi (b), Vol. 250, Issue 6
  • DOI: 10.1002/pssb.201248370

A particle-particle, particle-density algorithm for the calculation of electrostatic interactions of particles with slablike geometry
journal, December 2007

  • Alireza Ghasemi, S.; Neelov, Alexey; Goedecker, Stefan
  • The Journal of Chemical Physics, Vol. 127, Issue 22
  • DOI: 10.1063/1.2804382

Crystal structure prediction using the minima hopping method
journal, December 2010

  • Amsler, Maximilian; Goedecker, Stefan
  • The Journal of Chemical Physics, Vol. 133, Issue 22
  • DOI: 10.1063/1.3512900

A recursive algorithm based on the extended Kalman filter for the training of feedforward neural models
journal, August 1998


Lattice parameters and lattice energies of high-pressure polymorphs of some alkali halides
journal, January 1964

  • Weir, C. E.; Piermarini, G. J.
  • Journal of Research of the National Bureau of Standards Section A: Physics and Chemistry, Vol. 68A, Issue 1
  • DOI: 10.6028/jres.068a.009

Empirical force fields for biological macromolecules: Overview and issues
journal, January 2004

  • Mackerell, Alexander D.
  • Journal of Computational Chemistry, Vol. 25, Issue 13
  • DOI: 10.1002/jcc.20082

Identification of Novel Cu, Ag, and Au Ternary Oxides from Global Structural Prediction
journal, June 2015


Two-Dimensional Hexagonal Sheet of TiO 2
journal, August 2017

  • Eivari, Hossein Asnaashari; Ghasemi, S. Alireza; Tahmasbi, Hossein
  • Chemistry of Materials, Vol. 29, Issue 20
  • DOI: 10.1021/acs.chemmater.7b02031

Atom-centered symmetry functions for constructing high-dimensional neural network potentials
journal, February 2011

  • Behler, Jörg
  • The Journal of Chemical Physics, Vol. 134, Issue 7
  • DOI: 10.1063/1.3553717

Publisher’s Note: On representing chemical environments [Phys. Rev. B 87 , 184115 (2013)]
journal, June 2013