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

Title: Accurate force field for molybdenum by machine learning large materials data

Abstract

In this work, we present a highly accurate spectral neighbor analysis potential (SNAP) model for molybdenum (Mo) developed through the rigorous application of machine learning techniques on large materials data sets. Despite Mo's importance as a structural metal, existing force fields for Mo based on the embedded atom and modified embedded atom methods still do not provide satisfactory accuracy on many properties. We will show that by fitting to the energies, forces and stress tensors of a large density functional theory (DFT)-computed dataset on a diverse set of Mo structures, a Mo SNAP model can be developed that achieves close to DFT accuracy in the prediction of a broad range of properties, including energies, forces, stresses, elastic constants, melting point, phonon spectra, surface energies, grain boundary energies, etc. We will outline a systematic model development process, which includes a rigorous approach to structural selection based on principal component analysis, as well as a differential evolution algorithm for optimizing the hyperparameters in the model fitting so that both the model error and the property prediction error can be simultaneously lowered. We expect that this newly developed Mo SNAP model will find broad applications in large-scale, long-time scale simulations.

Authors:
 [1];  [1];  [1];  [1];  [1];  [1]
  1. Univ. of California, San Diego, CA (United States). Dept. of NanoEngineering
Publication Date:
Research Org.:
Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
Sponsoring Org.:
USDOE Office of Science (SC)
OSTI Identifier:
1559139
Grant/Contract Number:  
AC02-05CH11231
Resource Type:
Accepted Manuscript
Journal Name:
Physical Review Materials
Additional Journal Information:
Journal Volume: 1; Journal Issue: 4; Journal ID: ISSN 2475-9953
Publisher:
American Physical Society (APS)
Country of Publication:
United States
Language:
English
Subject:
36 MATERIALS SCIENCE

Citation Formats

Chen, Chi, Deng, Zhi, Tran, Richard, Tang, Hanmei, Chu, Iek-Heng, and Ong, Shyue Ping. Accurate force field for molybdenum by machine learning large materials data. United States: N. p., 2017. Web. doi:10.1103/physrevmaterials.1.043603.
Chen, Chi, Deng, Zhi, Tran, Richard, Tang, Hanmei, Chu, Iek-Heng, & Ong, Shyue Ping. Accurate force field for molybdenum by machine learning large materials data. United States. doi:10.1103/physrevmaterials.1.043603.
Chen, Chi, Deng, Zhi, Tran, Richard, Tang, Hanmei, Chu, Iek-Heng, and Ong, Shyue Ping. Fri . "Accurate force field for molybdenum by machine learning large materials data". United States. doi:10.1103/physrevmaterials.1.043603. https://www.osti.gov/servlets/purl/1559139.
@article{osti_1559139,
title = {Accurate force field for molybdenum by machine learning large materials data},
author = {Chen, Chi and Deng, Zhi and Tran, Richard and Tang, Hanmei and Chu, Iek-Heng and Ong, Shyue Ping},
abstractNote = {In this work, we present a highly accurate spectral neighbor analysis potential (SNAP) model for molybdenum (Mo) developed through the rigorous application of machine learning techniques on large materials data sets. Despite Mo's importance as a structural metal, existing force fields for Mo based on the embedded atom and modified embedded atom methods still do not provide satisfactory accuracy on many properties. We will show that by fitting to the energies, forces and stress tensors of a large density functional theory (DFT)-computed dataset on a diverse set of Mo structures, a Mo SNAP model can be developed that achieves close to DFT accuracy in the prediction of a broad range of properties, including energies, forces, stresses, elastic constants, melting point, phonon spectra, surface energies, grain boundary energies, etc. We will outline a systematic model development process, which includes a rigorous approach to structural selection based on principal component analysis, as well as a differential evolution algorithm for optimizing the hyperparameters in the model fitting so that both the model error and the property prediction error can be simultaneously lowered. We expect that this newly developed Mo SNAP model will find broad applications in large-scale, long-time scale simulations.},
doi = {10.1103/physrevmaterials.1.043603},
journal = {Physical Review Materials},
number = 4,
volume = 1,
place = {United States},
year = {2017},
month = {9}
}

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

Citation Metrics:
Cited by: 34 works
Citation information provided by
Web of Science

Figures / Tables:

FIG. 1 FIG. 1: Model fitting workflow.

Save / Share:

Works referenced in this record:

A molecular dynamics study of oxygen ion diffusion in A-site ordered perovskite PrBaCo 2 O 5.5 : data mining the oxygen trajectories
journal, January 2015

  • Chen, Chi; Chen, Dengjie; Ciucci, Francesco
  • Physical Chemistry Chemical Physics, Vol. 17, Issue 12
  • DOI: 10.1039/C4CP05847J

Generalized Gradient Approximation Made Simple
journal, October 1996

  • Perdew, John P.; Burke, Kieron; Ernzerhof, Matthias
  • Physical Review Letters, Vol. 77, Issue 18, p. 3865-3868
  • DOI: 10.1103/PhysRevLett.77.3865

Self-diffusion in molybdenum
journal, June 1963


Projector augmented-wave method
journal, December 1994


New opportunities for materials informatics: Resources and data mining techniques for uncovering hidden relationships
journal, April 2016

  • Jain, Anubhav; Hautier, Geoffroy; Ong, Shyue Ping
  • Journal of Materials Research, Vol. 31, Issue 8
  • DOI: 10.1557/jmr.2016.80

UFF, a full periodic table force field for molecular mechanics and molecular dynamics simulations
journal, December 1992

  • Rappe, A. K.; Casewit, C. J.; Colwell, K. S.
  • Journal of the American Chemical Society, Vol. 114, Issue 25, p. 10024-10035
  • DOI: 10.1021/ja00051a040

Charting the complete elastic properties of inorganic crystalline compounds
journal, March 2015

  • de Jong, Maarten; Chen, Wei; Angsten, Thomas
  • Scientific Data, Vol. 2, Issue 1
  • DOI: 10.1038/sdata.2015.9

FireWorks: a dynamic workflow system designed for high-throughput applications: FireWorks: A Dynamic Workflow System Designed for High-Throughput Applications
journal, May 2015

  • Jain, Anubhav; Ong, Shyue Ping; Chen, Wei
  • Concurrency and Computation: Practice and Experience, Vol. 27, Issue 17
  • DOI: 10.1002/cpe.3505

On representing chemical environments
journal, May 2013


Recent advances in differential evolution: a survey and experimental analysis
journal, October 2009


Machine Learning Predictions of Molecular Properties: Accurate Many-Body Potentials and Nonlocality in Chemical Space
journal, June 2015

  • Hansen, Katja; Biegler, Franziska; Ramakrishnan, Raghunathan
  • The Journal of Physical Chemistry Letters, Vol. 6, Issue 12
  • DOI: 10.1021/acs.jpclett.5b00831

Fast Parallel Algorithms for Short-Range Molecular Dynamics
journal, March 1995


Spectral neighbor analysis method for automated generation of quantum-accurate interatomic potentials
journal, March 2015


The Elastic Behaviour of a Crystalline Aggregate
journal, May 1952


Machine learning of molecular electronic properties in chemical compound space
journal, September 2013


Comment on “Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning”
journal, August 2012


Molecular Dynamics with On-the-Fly Machine Learning of Quantum-Mechanical Forces
journal, March 2015


Adaptive machine learning framework to accelerate ab initio molecular dynamics
journal, December 2014

  • Botu, Venkatesh; Ramprasad, Rampi
  • International Journal of Quantum Chemistry, Vol. 115, Issue 16
  • DOI: 10.1002/qua.24836

Moment Tensor Potentials: A Class of Systematically Improvable Interatomic Potentials
journal, January 2016

  • Shapeev, Alexander V.
  • Multiscale Modeling & Simulation, Vol. 14, Issue 3
  • DOI: 10.1137/15M1054183

A climbing image nudged elastic band method for finding saddle points and minimum energy paths
journal, December 2000

  • Henkelman, Graeme; Uberuaga, Blas P.; Jónsson, Hannes
  • The Journal of Chemical Physics, Vol. 113, Issue 22, p. 9901-9904
  • DOI: 10.1063/1.1329672

Density-Functional Theory of the Energy Gap
journal, November 1983


Solving the quantum many-body problem with artificial neural networks
journal, February 2017


Machine learning phases of matter
journal, February 2017

  • Carrasquilla, Juan; Melko, Roger G.
  • Nature Physics, Vol. 13, Issue 5
  • DOI: 10.1038/nphys4035

Self-Consistent Equations Including Exchange and Correlation Effects
journal, November 1965


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

Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
journal, January 2012


Accelerating materials property predictions using machine learning
journal, September 2013

  • Pilania, Ghanshyam; Wang, Chenchen; Jiang, Xun
  • Scientific Reports, Vol. 3, Issue 1
  • DOI: 10.1038/srep02810

The ReaxFF reactive force-field: development, applications and future directions
journal, March 2016


Ab initio based empirical potential used to study the mechanical properties of molybdenum
journal, June 2012


Kernels for small molecules and the prediction of mutagenicity, toxicity and anti-cancer activity
journal, June 2005


Data mining of molecular dynamics data reveals Li diffusion characteristics in garnet Li7La3Zr2O12
journal, January 2017

  • Chen, Chi; Lu, Ziheng; Ciucci, Francesco
  • Scientific Reports, Vol. 7, Issue 1
  • DOI: 10.1038/srep40769

Efficient iterative schemes for ab initio total-energy calculations using a plane-wave basis set
journal, October 1996


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

Misfit-energy-increasing dislocations in vapor-deposited CoFe/NiFe multilayers
journal, April 2004


Generalized Neural-Network Representation of High-Dimensional Potential-Energy Surfaces
journal, April 2007


Computational study of metallic dopant segregation and embrittlement at molybdenum grain boundaries
journal, September 2016


Second nearest-neighbor modified embedded atom method potentials for bcc transition metals
journal, October 2001


Accelerated computational discovery of high-performance materials for organic photovoltaics by means of cheminformatics
journal, January 2011

  • Olivares-Amaya, Roberto; Amador-Bedolla, Carlos; Hachmann, Johannes
  • Energy & Environmental Science, Vol. 4, Issue 12
  • DOI: 10.1039/c1ee02056k

Gaussian Approximation Potentials: The Accuracy of Quantum Mechanics, without the Electrons
journal, April 2010


Genetic Optimization of Training Sets for Improved Machine Learning Models of Molecular Properties
journal, March 2017

  • Browning, Nicholas J.; Ramakrishnan, Raghunathan; von Lilienfeld, O. Anatole
  • The Journal of Physical Chemistry Letters, Vol. 8, Issue 7
  • DOI: 10.1021/acs.jpclett.7b00038

Surface energies of elemental crystals
journal, September 2016

  • Tran, Richard; Xu, Zihan; Radhakrishnan, Balachandran
  • Scientific Data, Vol. 3, Issue 1
  • DOI: 10.1038/sdata.2016.80

Accurate interatomic force fields via machine learning with covariant kernels
journal, June 2017


To address surface reaction network complexity using scaling relations machine learning and DFT calculations
journal, March 2017

  • Ulissi, Zachary W.; Medford, Andrew J.; Bligaard, Thomas
  • Nature Communications, Vol. 8, Issue 1
  • DOI: 10.1038/ncomms14621

First-principles calculations of the ferroelastic transition between rutile-type and CaCl 2 -type SiO 2 at high pressures
journal, October 2008


Combinatorial screening for new materials in unconstrained composition space with machine learning
journal, March 2014


Python Materials Genomics (pymatgen): A robust, open-source python library for materials analysis
journal, February 2013


New tool in the box
journal, February 2017


    Works referencing / citing this record:

    Recent advances and applications of machine learning in solid-state materials science
    journal, August 2019

    • Schmidt, Jonathan; Marques, Mário R. G.; Botti, Silvana
    • npj Computational Materials, Vol. 5, Issue 1
    • DOI: 10.1038/s41524-019-0221-0

    Recent advances and applications of machine learning in solid-state materials science
    journal, August 2019

    • Schmidt, Jonathan; Marques, Mário R. G.; Botti, Silvana
    • npj Computational Materials, Vol. 5, Issue 1
    • DOI: 10.1038/s41524-019-0221-0

    Computational Studies of Electrode Materials in Sodium-Ion Batteries
    journal, March 2018

    • Bai, Qiang; Yang, Lufeng; Chen, Hailong
    • Advanced Energy Materials, Vol. 8, Issue 17
    • DOI: 10.1002/aenm.201702998

    A Critical Review of Machine Learning of Energy Materials
    journal, January 2020


    A strategy to apply machine learning to small datasets in materials science
    journal, May 2018


    Empirical modeling of dopability in diamond-like semiconductors
    journal, December 2018

    • Miller, Samuel A.; Dylla, Maxwell; Anand, Shashwat
    • npj Computational Materials, Vol. 4, Issue 1
    • DOI: 10.1038/s41524-018-0123-6

    Designing interfaces in energy materials applications with first-principles calculations
    journal, February 2019

    • Butler, Keith T.; Sai Gautam, Gopalakrishnan; Canepa, Pieremanuele
    • npj Computational Materials, Vol. 5, Issue 1
    • DOI: 10.1038/s41524-019-0160-9

    An electrostatic spectral neighbor analysis potential for lithium nitride
    journal, July 2019


    Fast, accurate, and transferable many-body interatomic potentials by symbolic regression
    journal, November 2019

    • Hernandez, Alberto; Balasubramanian, Adarsh; Yuan, Fenglin
    • npj Computational Materials, Vol. 5, Issue 1
    • DOI: 10.1038/s41524-019-0249-1

    Extending the accuracy of the SNAP interatomic potential form
    journal, June 2018

    • Wood, Mitchell A.; Thompson, Aidan P.
    • The Journal of Chemical Physics, Vol. 148, Issue 24
    • DOI: 10.1063/1.5017641

    Development of a deep machine learning interatomic potential for metalloid-containing Pd-Si compounds
    journal, November 2019


    Data-driven material models for atomistic simulation
    journal, May 2019


    Achieving DFT accuracy with a machine-learning interatomic potential: Thermomechanics and defects in bcc ferromagnetic iron
    journal, January 2018


    Atomistic description of self-diffusion in molybdenum: A comparative theoretical study of non-Arrhenius behavior
    journal, January 2020


    Machine Learning a General-Purpose Interatomic Potential for Silicon
    journal, December 2018