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

Title: Discovering charge density functionals and structure-property relationships with PROPhet: A general framework for coupling machine learning and first-principles methods

Abstract

Modern ab initio methods have rapidly increased our understanding of solid state materials properties, chemical reactions, and the quantum interactions between atoms. However, poor scaling often renders direct ab initio calculations intractable for large or complex systems. There are two obvious avenues through which to remedy this problem: (i) develop new, less expensive methods to calculate system properties, or (ii) make existing methods faster. This paper describes an open source framework designed to pursue both of these avenues. PROPhet (short for PROPerty Prophet) utilizes machine learning techniques to find complex, non-linear mappings between sets of material or system properties. The result is a single code capable of learning analytical potentials, non-linear density functionals, and other structure-property or property-property relationships. These capabilities enable highly accurate mesoscopic simulations, facilitate computation of expensive properties, and enable the development of predictive models for systematic materials design and optimization. Here, this work explores the coupling of machine learning to ab initio methods through means both familiar (e.g., the creation of various potentials and energy functionals) and less familiar (e.g., the creation of density functionals for arbitrary properties), serving both to demonstrate PROPhet’s ability to create exciting post-processing analysis tools and to open the door tomore » improving ab initio methods themselves with these powerful machine learning techniques.« less

Authors:
 [1];  [2];  [2]
  1. Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States). Dept. of Mechanical Engineering; Univ. of New Mexico, Albuquerque, NM (United States). Dept. of Chemistry and Chemical Biology
  2. Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States). Dept. of Mechanical Engineering
Publication Date:
Research Org.:
Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States); Alliance for Sustainable Energy, LLC, Golden, CO (United States); Energy Frontier Research Centers (EFRC) (United States). Center for Next Generation of Materials by Design: Incorporating Metastability (CNGMD)
Sponsoring Org.:
USDOE Office of Science (SC), Basic Energy Sciences (BES); USDOE Office of Energy Efficiency and Renewable Energy (EERE)
OSTI Identifier:
1368375
Grant/Contract Number:  
SC0001299; FG02-09ER46577; AC36-8GO28308
Resource Type:
Accepted Manuscript
Journal Name:
Scientific Reports
Additional Journal Information:
Journal Volume: 7; Journal Issue: 1; Journal ID: ISSN 2045-2322
Publisher:
Nature Publishing Group
Country of Publication:
United States
Language:
English
Subject:
97 MATHEMATICS AND COMPUTING

Citation Formats

Kolb, Brian, Lentz, Levi C., and Kolpak, Alexie M. Discovering charge density functionals and structure-property relationships with PROPhet: A general framework for coupling machine learning and first-principles methods. United States: N. p., 2017. Web. doi:10.1038/s41598-017-01251-z.
Kolb, Brian, Lentz, Levi C., & Kolpak, Alexie M. Discovering charge density functionals and structure-property relationships with PROPhet: A general framework for coupling machine learning and first-principles methods. United States. doi:https://doi.org/10.1038/s41598-017-01251-z
Kolb, Brian, Lentz, Levi C., and Kolpak, Alexie M. Wed . "Discovering charge density functionals and structure-property relationships with PROPhet: A general framework for coupling machine learning and first-principles methods". United States. doi:https://doi.org/10.1038/s41598-017-01251-z. https://www.osti.gov/servlets/purl/1368375.
@article{osti_1368375,
title = {Discovering charge density functionals and structure-property relationships with PROPhet: A general framework for coupling machine learning and first-principles methods},
author = {Kolb, Brian and Lentz, Levi C. and Kolpak, Alexie M.},
abstractNote = {Modern ab initio methods have rapidly increased our understanding of solid state materials properties, chemical reactions, and the quantum interactions between atoms. However, poor scaling often renders direct ab initio calculations intractable for large or complex systems. There are two obvious avenues through which to remedy this problem: (i) develop new, less expensive methods to calculate system properties, or (ii) make existing methods faster. This paper describes an open source framework designed to pursue both of these avenues. PROPhet (short for PROPerty Prophet) utilizes machine learning techniques to find complex, non-linear mappings between sets of material or system properties. The result is a single code capable of learning analytical potentials, non-linear density functionals, and other structure-property or property-property relationships. These capabilities enable highly accurate mesoscopic simulations, facilitate computation of expensive properties, and enable the development of predictive models for systematic materials design and optimization. Here, this work explores the coupling of machine learning to ab initio methods through means both familiar (e.g., the creation of various potentials and energy functionals) and less familiar (e.g., the creation of density functionals for arbitrary properties), serving both to demonstrate PROPhet’s ability to create exciting post-processing analysis tools and to open the door to improving ab initio methods themselves with these powerful machine learning techniques.},
doi = {10.1038/s41598-017-01251-z},
journal = {Scientific Reports},
number = 1,
volume = 7,
place = {United States},
year = {2017},
month = {4}
}

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

Citation Metrics:
Cited by: 3 works
Citation information provided by
Web of Science

Figures / Tables:

Figure 1 Figure 1: Histogram of the errors between a machine-learned analytical potential and the directly computed DFT energies for carbon in the diamond structure. The network used here, trained in PROPhet, contained 2 hidden layers each containing 35 nodes. The errors shown here are for 2000 structures that were not usedmore » in the fitting procedure.« less

Save / Share:

Works referenced in this record:

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


Density‐functional thermochemistry. III. The role of exact exchange
journal, April 1993

  • Becke, Axel D.
  • The Journal of Chemical Physics, Vol. 98, Issue 7, p. 5648-5652
  • DOI: 10.1063/1.464913

Finding Density Functionals with Machine Learning
journal, June 2012


On the limited memory BFGS method for large scale optimization
journal, August 1989

  • Liu, Dong C.; Nocedal, Jorge
  • Mathematical Programming, Vol. 45, Issue 1-3
  • DOI: 10.1007/BF01589116

Permutation invariant polynomial neural network approach to fitting potential energy surfaces
journal, August 2013

  • Jiang, Bin; Guo, Hua
  • The Journal of Chemical Physics, Vol. 139, Issue 5
  • DOI: 10.1063/1.4817187

A meeting with Enrico Fermi
journal, January 2004


Kinetic-energy functional of the electron density
journal, June 1992


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


Representing potential energy surfaces by high-dimensional neural network potentials
journal, April 2014


Time-dependent density functional theory: Past, present, and future
journal, August 2005

  • Burke, Kieron; Werschnik, Jan; Gross, E. K. U.
  • The Journal of Chemical Physics, Vol. 123, Issue 6
  • DOI: 10.1063/1.1904586

Ab initio calculations of optical absorption spectra: Solution of the Bethe–Salpeter equation within density matrix perturbation theory
journal, October 2010

  • Rocca, Dario; Lu, Deyu; Galli, Giulia
  • The Journal of Chemical Physics, Vol. 133, Issue 16
  • DOI: 10.1063/1.3494540

QUANTUM ESPRESSO: a modular and open-source software project for quantum simulations of materials
journal, September 2009

  • Giannozzi, Paolo; Baroni, Stefano; Bonini, Nicola
  • Journal of Physics: Condensed Matter, Vol. 21, Issue 39, Article No. 395502
  • DOI: 10.1088/0953-8984/21/39/395502

Lattice Dynamics of Diamond
journal, June 1967


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


First principles phonon calculations in materials science
journal, November 2015


Potential Energy Surfaces Fitted by Artificial Neural Networks
journal, March 2010

  • Handley, Chris M.; Popelier, Paul L. A.
  • The Journal of Physical Chemistry A, Vol. 114, Issue 10
  • DOI: 10.1021/jp9105585

The GW method
journal, March 1998


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


Density-Functional Theory for Time-Dependent Systems
journal, March 1984


Inhomogeneous Electron Gas
journal, November 1964


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


Orbital-free bond breaking via machine learning
journal, December 2013

  • Snyder, John C.; Rupp, Matthias; Hansen, Katja
  • The Journal of Chemical Physics, Vol. 139, Issue 22
  • DOI: 10.1063/1.4834075

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


Thermal conductivity of group-IV semiconductors from a kinetic-collective model
journal, September 2014

  • de Tomas, C.; Cantarero, A.; Lopeandia, A. F.
  • Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, Vol. 470, Issue 2169
  • DOI: 10.1098/rspa.2014.0371

Ab initio molecular simulations with numeric atom-centered orbitals
journal, November 2009

  • Blum, Volker; Gehrke, Ralf; Hanke, Felix
  • Computer Physics Communications, Vol. 180, Issue 11
  • DOI: 10.1016/j.cpc.2009.06.022

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


Modified Statistical Treatment of Kinetic Energy in the Thomas−Fermi Model
journal, May 2004

  • Chai, Jeng-Da; Weeks, John D.
  • The Journal of Physical Chemistry B, Vol. 108, Issue 21
  • DOI: 10.1021/jp037716b

Neural network potential-energy surfaces in chemistry: a tool for large-scale simulations
journal, January 2011

  • Behler, Jörg
  • Physical Chemistry Chemical Physics, Vol. 13, Issue 40
  • DOI: 10.1039/c1cp21668f

Neural network approach to quantum-chemistry data: Accurate prediction of density functional theory energies
journal, August 2009

  • Balabin, Roman M.; Lomakina, Ekaterina I.
  • The Journal of Chemical Physics, Vol. 131, Issue 7
  • DOI: 10.1063/1.3206326

Grand canonical molecular dynamics simulations of Cu–Au nanoalloys in thermal equilibrium using reactive ANN potentials
journal, December 2015


Ab initiomolecular dynamics for liquid metals
journal, January 1993


Neural network molecular dynamics simulations of solid–liquid interfaces: water at low-index copper surfaces
journal, January 2016

  • Natarajan, Suresh Kondati; Behler, Jörg
  • Physical Chemistry Chemical Physics, Vol. 18, Issue 41
  • DOI: 10.1039/C6CP05711J

Kinetic Energy of Hydrocarbons as a Function of Electron Density and Convolutional Neural Networks
journal, February 2016


Picosecond optical studies of amorphous diamond and diamondlike carbon: Thermal conductivity and longitudinal sound velocity
journal, September 1994

  • Morath, Christopher J.; Maris, Humphrey J.; Cuomo, Jerome J.
  • Journal of Applied Physics, Vol. 76, Issue 5
  • DOI: 10.1063/1.357560

Pure density functional for strong correlation and the thermodynamic limit from machine learning
journal, December 2016


NWChem: A comprehensive and scalable open-source solution for large scale molecular simulations
journal, September 2010

  • Valiev, M.; Bylaska, E. J.; Govind, N.
  • Computer Physics Communications, Vol. 181, Issue 9, p. 1477-1489
  • DOI: 10.1016/j.cpc.2010.04.018

Coupled-cluster theory in quantum chemistry
journal, February 2007


A general-purpose machine learning framework for predicting properties of inorganic materials
journal, August 2016


Understanding machine-learned density functionals: Understanding Machine-Learned Density Functionals
journal, November 2015

  • Li, Li; Snyder, John C.; Pelaschier, Isabelle M.
  • International Journal of Quantum Chemistry, Vol. 116, Issue 11
  • DOI: 10.1002/qua.25040

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


Inhomogeneous Electron Gas
journal, March 1973


    Works referencing / citing this record:

    Machine Learning Approaches for Thermoelectric Materials Research
    journal, November 2019

    • Wang, Tian; Zhang, Cheng; Snoussi, Hichem
    • Advanced Functional Materials, Vol. 30, Issue 5
    • DOI: 10.1002/adfm.201906041

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


    Machine learning for heterogeneous catalyst design and discovery
    journal, May 2018

    • Goldsmith, Bryan R.; Esterhuizen, Jacques; Liu, Jin-Xun
    • AIChE Journal, Vol. 64, Issue 7
    • DOI: 10.1002/aic.16198

    Perspectives on the Impact of Machine Learning, Deep Learning, and Artificial Intelligence on Materials, Processes, and Structures Engineering
    journal, August 2018

    • Dimiduk, Dennis M.; Holm, Elizabeth A.; Niezgoda, Stephen R.
    • Integrating Materials and Manufacturing Innovation, Vol. 7, Issue 3
    • DOI: 10.1007/s40192-018-0117-8

    Physically informed artificial neural networks for atomistic modeling of materials
    journal, May 2019


    Solving the electronic structure problem with machine learning
    journal, February 2019

    • Chandrasekaran, Anand; Kamal, Deepak; Batra, Rohit
    • npj Computational Materials, Vol. 5, Issue 1
    • DOI: 10.1038/s41524-019-0162-7

    Theory-guided design of catalytic materials using scaling relationships and reactivity descriptors
    journal, November 2019


    A Universal 3D Voxel Descriptor for Solid-State Material Informatics with Deep Convolutional Neural Networks
    journal, December 2017


    Machine learning assisted optimization of electrochemical properties for Ni-rich cathode materials
    journal, October 2018


    Pattern Learning Electronic Density of States
    journal, April 2019


    Machine learning in catalysis
    journal, April 2018


    A fast neural network approach for direct covariant forces prediction in complex multi-element extended systems
    journal, September 2019

    • Mailoa, Jonathan P.; Kornbluth, Mordechai; Batzner, Simon
    • Nature Machine Intelligence, Vol. 1, Issue 10
    • DOI: 10.1038/s42256-019-0098-0

    The TensorMol-0.1 model chemistry: a neural network augmented with long-range physics
    journal, January 2018

    • Yao, Kun; Herr, John E.; Toth, David W.
    • Chemical Science, Vol. 9, Issue 8
    • DOI: 10.1039/c7sc04934j

    Predicting HSE band gaps from PBE charge densities via neural network functionals
    journal, January 2020

    • Lentz, Levi C.; Kolpak, Alexie M.
    • Journal of Physics: Condensed Matter, Vol. 32, Issue 15
    • DOI: 10.1088/1361-648x/ab5f3a

    From DFT to machine learning: recent approaches to materials science–a review
    journal, May 2019

    • Schleder, Gabriel R.; Padilha, Antonio C. M.; Acosta, Carlos Mera
    • Journal of Physics: Materials, Vol. 2, Issue 3
    • DOI: 10.1088/2515-7639/ab084b

    Machine learning for the modeling of interfaces in energy storage and conversion materials
    journal, July 2019


    Predicting charge density distribution of materials using a local-environment-based graph convolutional network
    journal, November 2019


    Analytic continuation via domain knowledge free machine learning
    journal, December 2018


    Machine-learning-based interatomic potential for phonon transport in perfect crystalline Si and crystalline Si with vacancies
    journal, July 2019


    Gap Prediction in Hybrid Graphene-Hexagonal Boron Nitride Nanoflakes Using Artificial Neural Networks
    journal, May 2019

    • Nemnes, G. A.; Mitran, T. L.; Manolescu, A.
    • Journal of Nanomaterials, Vol. 2019
    • DOI: 10.1155/2019/6960787

      Figures/Tables have been extracted from DOE-funded journal article accepted manuscripts.