skip to main content
OSTI.GOV 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

Journal Article · · Scientific Reports
 [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
+ Show Author Affiliations

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.

Research Organization:
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 Organization:
USDOE Office of Science (SC), Basic Energy Sciences (BES); USDOE Office of Energy Efficiency and Renewable Energy (EERE)
Grant/Contract Number:
SC0001299; FG02-09ER46577; AC36-8GO28308
OSTI ID:
1368375
Journal Information:
Scientific Reports, Vol. 7, Issue 1; ISSN 2045-2322
Publisher:
Nature Publishing GroupCopyright Statement
Country of Publication:
United States
Language:
English
Citation Metrics:
Cited by: 90 works
Citation information provided by
Web of Science

References (55)

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
Finding Density Functionals with Machine Learning journal June 2012
On the limited memory BFGS method for large scale optimization journal August 1989
Permutation invariant polynomial neural network approach to fitting potential energy surfaces journal August 2013
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
Understanding the Composition and Activity of Electrocatalytic Nanoalloys in Aqueous Solvents: A Combination of DFT and Accurate Neural Network Potentials journal April 2014
Ab initio calculations of optical absorption spectra: Solution of the Bethe–Salpeter equation within density matrix perturbation theory journal October 2010
QUANTUM ESPRESSO: a modular and open-source software project for quantum simulations of materials journal September 2009
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
Resolution-of-identity approach to Hartree–Fock, hybrid density functionals, RPA, MP2 and GW with numeric atom-centered orbital basis functions journal May 2012
Potential Energy Surfaces Fitted by Artificial Neural Networks journal March 2010
The GW method journal March 1998
Fast Parallel Algorithms for Short-Range Molecular Dynamics journal March 1995
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
Machine learning of molecular electronic properties in chemical compound space journal September 2013
Thermal conductivity of group-IV semiconductors from a kinetic-collective model
  • de Tomas, C.; Cantarero, A.; Lopeandia, A. F.
  • Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, Vol. 470, Issue 2169 https://doi.org/10.1098/rspa.2014.0371
journal September 2014
Ab initio molecular simulations with numeric atom-centered orbitals journal November 2009
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
Neural network potential-energy surfaces in chemistry: a tool for large-scale simulations journal January 2011
Neural network approach to quantum-chemistry data: Accurate prediction of density functional theory energies journal August 2009
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
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
Pure density functional for strong correlation and the thermodynamic limit from machine learning journal December 2016
Theory of Polarization: A Modern Approach book January 2007
NWChem: A comprehensive and scalable open-source solution for large scale molecular simulations journal September 2010
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
Self-Consistent Equations Including Exchange and Correlation Effects journal November 1965
High-resolution X-ray luminescence extension imaging journal February 2021
Machine learning of molecular electronic properties in chemical compound space text January 2013
Fast and accurate modeling of molecular atomization energies with machine learning text January 2012
Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning text January 2011
Orbital-free Bond Breaking via Machine Learning text January 2013
First principles phonon calculations in materials science preprint January 2015
A General-Purpose Machine Learning Framework for Predicting Properties of Inorganic Materials text January 2016
Time-dependent density functional theory: Past, present, and future text January 2004
Machine learning of molecular electronic properties in chemical compound space text January 2013
Strain-induced room-temperature ferroelectricity in SrTiO3 membranes journal June 2020
(Fe,Ni)2P allabogdanite can be an ambient pressure phase in iron meteorites journal June 2020
Resolution-of-identity approach to Hartree-Fock, hybrid density functionals, RPA, MP2, and \textit{GW} with numeric atom-centered orbital basis functions text January 2012
Theoretical analysis of doped graphene as cathode catalyst in Li-O2 and Na-O2 batteries -- the impact of the computational scheme preprint January 2020

Cited By (26)

Machine Learning Approaches for Thermoelectric Materials Research journal November 2019
A Critical Review of Machine Learning of Energy Materials journal January 2020
Machine learning for heterogeneous catalyst design and discovery journal May 2018
Perspectives on the Impact of Machine Learning, Deep Learning, and Artificial Intelligence on Materials, Processes, and Structures Engineering journal August 2018
Physically informed artificial neural networks for atomistic modeling of materials journal May 2019
Solving the electronic structure problem with machine learning journal February 2019
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
The TensorMol-0.1 model chemistry: a neural network augmented with long-range physics journal January 2018
Predicting HSE band gaps from PBE charge densities via neural network functionals journal January 2020
From DFT to machine learning: recent approaches to materials science–a review journal May 2019
Machine learning for the modeling of interfaces in energy storage and conversion materials journal July 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
Materials science in the artificial intelligence age: high-throughput library generation, machine learning, and a pathway from correlations to the underpinning physics journal July 2019
The TensorMol-0.1 Model Chemistry: a Neural Network Augmented with Long-Range Physics preprint January 2017
Pattern Learning Electronic Density of States text January 2018
Design and Analysis of Machine Learning Exchange-Correlation Functionals via Rotationally Invariant Convolutional Descriptors text January 2019
Characterization of the Optical Properties of Turbid Media by Supervised Learning of Scattering Patterns journal November 2017
Insights into one-body density matrices using deep learning journal January 2020
Efficient Learning of a One-dimensional Density Functional Theory text January 2020

Figures / Tables (5)

Figure 1(p. 4)figure Figure 1
Figure 2(p. 5)figure Figure 2
Figure 3(p. 5)figure Figure 3
Figure 4(p. 7)figure Figure 4
Figure 5(p. 7)figure Figure 5

Similar Records

Related Subjects

97 MATHEMATICS AND COMPUTING