A Deep Dive into Machine Learning Density Functional Theory for Materials Science and Chemistry

Abstract

With the growth of computational resources, the scope of electronic structure simulations has increased greatly. Artificial intelligence and robust data analysis hold the promise to accelerate large-scale simulations and their analysis to hitherto unattainable scales. Machine learning is a rapidly growing field for the processing of such complex datasets. It has recently gained traction in the domain of electronic structure simulations, where density functional theory takes the prominent role of the most widely used electronic structure method. Thus, DFT calculations represent one of the largest loads on academic high-performance computing systems across the world. Accelerating these with machine learning can reduce the resources required and enables simulations of larger systems. Hence, the combination of density functional theory and machine learning has the potential to rapidly advance electronic structure applications such as in-silico materials discovery and the search for new chemical reaction pathways. We provide the theoretical background of both density functional theory and machine learning on a generally accessible level. This serves as the basis of our comprehensive review including research articles up to December 2020 in chemistry and materials science that employ machine-learning techniques. In our analysis, we categorize the body of research into main threads and extract impactful results. We conclude our review with an outlook on exciting research directions in terms of a citation analysis.

References in corpus (116)

• Quantum ESPRESSO: a modular and open-source software project for quantum simulations of materials
• Advanced capabilities for materials modelling with Quantum ESPRESSO
• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• On representing chemical environments
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics
• SchNet - a deep learning architecture for molecules and materials
• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• Quantum ESPRESSO toward the exascale
• The GW method
• Moment Tensor Potentials: a class of systematically improvable interatomic potentials
• Astrophysics Source Code Library
• Machine Learning of Accurate Energy-Conserving Molecular Force Fields
• A Spectral Analysis Method for Automated Generation of Quantum-Accurate Interatomic Potentials
• Big Data meets Quantum Chemistry Approximations: The $\Delta$-Machine Learning Approach
• SISSO: a compressed-sensing method for identifying the best low-dimensional descriptor in an immensity of offered candidates
• The Open Catalyst 2020 (OC20) Dataset and Community Challenges
• By-passing the Kohn-Sham equations with machine learning
• Active learning of linearly parametrized interatomic potentials
• Towards Exact Molecular Dynamics Simulations with Machine-Learned Force Fields
• Machine learning prediction errors better than DFT accuracy
• Machine-learning based interatomic potential for amorphous carbon
• Finding Density Functionals with Machine Learning
• The Joint Automated Repository for Various Integrated Simulations (JARVIS) for data-driven materials design
• Active Learning of Uniformly Accurate Inter-atomic Potentials for Materials Simulation
• How to represent crystal structures for machine learning: towards fast prediction of electronic properties
• Accelerating crystal structure prediction by machine-learning interatomic potentials with active learning
• ANI-1: A data set of 20M off-equilibrium DFT calculations for organic molecules
• Physically-informed artificial neural networks for atomistic modeling of materials
• Alchemical and structural distribution based representation for improved QML
• Machine learning with systematic density-functional theory calculations: Application to melting temperatures of single and binary component solids
• AiiDA 1.0, a scalable computational infrastructure for automated reproducible workflows and data provenance
• Hierarchical modeling of molecular energies using a deep neural network
• Achieving DFT accuracy with a machine-learning interatomic potential: thermomechanics and defects in bcc ferromagnetic iron
• QMCPACK : An open source ab initio Quantum Monte Carlo package for the electronic structure of atoms, molecules, and solids
• Developing an improved Crystal Graph Convolutional Neural Network framework for accelerated materials discovery
• Chemical Shifts in Molecular Solids by Machine Learning
• Electronic Spectra from TDDFT and Machine Learning in Chemical Space
• An Accurate and Transferable Machine Learning Potential for Carbon
• A Transferable Machine-Learning Model of the Electron Density
• A critical examination of compound stability predictions from machine-learned formation energies
• Deep Neural Networks for Accurate Predictions of Garnet Stability
• A neural network interatomic potential for the phase change material GeTe
• Correlated electron-nuclear dynamics: Exact factorization of the molecular wavefunction
• Applying machine learning techniques to predict the properties of energetic materials
• Predicting the thermodynamic stability of perovskite oxides using machine learning models
• sGDML: Constructing Accurate and Data Efficient Molecular Force Fields Using Machine Learning
• A recommendation engine for suggesting unexpected thermoelectric chemistries
• De novo exploration and self-guided learning of potential-energy surfaces
• Accelerating first-principles estimation of thermal conductivity by machine-learning interatomic potentials: A MTP/ShengBTE solution
• Machine-Learning Interatomic Potentials Enable First-Principles Multiscale Modeling of Lattice Thermal Conductivity in Graphene/Borophene Heterostructures
• Extending the Accuracy of the SNAP Interatomic Potential Form
• A Machine Learning Potential for Graphene
• Accurate molecular polarizabilities with coupled-cluster theory and machine learning
• Predicting Electronic Structure Properties of Transition Metal Complexes with Neural Networks
• Convergence and machine learning predictions of Monkhorst-Pack k-points and plane-wave cut-off in high-throughput DFT calculations
• Workflows in AiiDA: Engineering a high-throughput, event-based engine for robust and modular computational workflows
• Machine learning with force-field inspired descriptors for materials: fast screening and mapping energy landscape
• Accurate Force Field for Molybdenum by Machine Learning Large Materials Data
• Machine learning of molecular properties: locality and active learning
• Nanoporous C3N4, C3N5 and C3N6 nanosheets; Novel strong semiconductors with low thermal conductivities and appealing optical/electronic properties
• Exploring Phononic Properties of Two-Dimensional Materials using Machine Learning Interatomic Potentials
• Accelerated Discovery of Efficient Solar-cell Materials using Quantum and Machine-learning Methods
• Calculations on millions of atoms with DFT: Linear scaling shows its potential
• Learning the electronic density of states in condensed matter
• Quantum-Accurate Spectral Neighbor Analysis Potential Models for Ni-Mo Binary Alloys and FCC Metals
• High-throughput Density Functional Perturbation Theory and Machine Learning Predictions of Infrared, Piezoelectric and Dielectric Responses
• Non-empirical Generalized Gradient Approximation Free Energy Functional for Orbital-free Simulations
• Ab initio vibrational free energies including anharmonicity for multicomponent alloys
• Large scale and linear scaling DFT with the CONQUEST code
• Predicting the Activity and Selectivity of Bimetallic Metal Catalysts for Ethanol Reforming using Machine Learning
• Pure density functional for strong correlations and the thermodynamic limit from machine learning
• Predicting molecular dipole moments by combining atomic partial charges and atomic dipoles
• Molecular Force Fields with Gradient-Domain Machine Learning: Construction and Application to Dynamics of Small Molecules with Coupled Cluster Forces
• First-Principles Equation of State Database for Warm Dense Matter Computation
• Machine Learning the Physical Non-Local Exchange-Correlation Functional of Density-Functional Theory
• Accelerating CALYPSO Structure Prediction by Data-driven Learning of Potential Energy Surface
• Exact conditions and scaling relations in finite temperature density functional theory
• A sparse representation for potential energy surface
• Magnetic susceptibility of insulators from first principles
• Quantum deep field: data-driven wave function, electron density generation, and atomization energy prediction and extrapolation with machine learning
• First-principles interatomic potentials for ten elemental metals via compressed sensing
• Solid Harmonic Wavelet Scattering for Predictions of Molecule Properties
• Design and Analysis of Machine Learning Exchange-Correlation Functionals via Rotationally Invariant Convolutional Descriptors
• Band gap and band alignment prediction of nitride based semiconductors using machine learning
• Isotope Effects in Liquid Water via Deep Potential Molecular Dynamics
• Pattern Learning Electronic Density of States
• Modern Machine Learning and Particle Physics
• Robust FCC solute diffusion predictions from ab-initio machine learning methods
• Explicit Multi-element Extension of the Spectral Neighbor Analysis Potential for Chemically Complex Systems
• Data-driven Material Models for Atomistic Simulation
• Data-driven Discovery of 3D and 2D Thermoelectric Materials
• Accelerating Finite-temperature Kohn-Sham Density Functional Theory with Deep Neural Networks
• High thermal conductivity in semiconducting Janus and non-Janus diamanes
• PANNA: Properties from Artificial Neural Network Architectures
• Matrix- and tensor-based recommender systems for the discovery of currently unknown inorganic compounds
• Application of machine learning potentials to predict grain boundary properties in fcc elemental metals
• Molecular Force Fields with Gradient-Domain Machine Learning (GDML): Comparison and Synergies with Classical Force Fields
• Building machine learning force fields for nanoclusters
• Machine learning density functional theory for the Hubbard model
• Automated Calculation of Thermal Rate Coefficients using Ring Polymer Molecular Dynamics and Machine-Learning Interatomic Potentials with Active Learning
• Training machine-learning potentials for crystal structure prediction using disordered structures
• Predicting Oxidation and Spin States by High-Dimensional Neural Networks: Applications to Lithium Manganese Oxide Spinels
• Self-learning Hybrid Monte Carlo: A First-principles Approach
• Learning from the Density to Correct Total Energy and Forces in First Principle Simulations
• A Multiple Filter Based Neural Network Approach to the Extrapolation of Adsorption Energies on Metal Surfaces for Catalysis Applications
• Machine Learning Exchange-Correlation Potential in Time Dependent Density Functional Theory
• Accelerating inverse crystal structure prediction by machine learning: a case study of carbon allotropes
• Leaving the Valley: Charting the Energy Landscape of Metal/Organic Interfaces via Machine Learning
• Machine learning formation enthalpies of intermetallics
• Chemical Bonding in Metallic Glasses from Machine Learning and Crystal Orbital Hamilton Population
• Ring Polymer Molecular Dynamics and Active Learning of Moment Tensor Potential for Gas-Phase Barrierless Reactions: Application to S + H2
• Machine learning optimization of the collocation point set for solving the Kohn-Sham equation
• Machine learning forces trained by Gaussian process in liquid states: Transferability to temperature and pressure
• Smart energy models for atomistic simulations using a DFT-driven multifidelity approach
• Learning electron densities in the condensed phase

Cited by in corpus (19)

• Electronic Density Response of Warm Dense Matter
• First principles simulations of dense hydrogen
• Predicting electronic structures at any length scale with machine learning
• ænet-PyTorch: a GPU-supported implementation for machine learning atomic potentials training
• Accelerating Equilibration in First-Principles Molecular Dynamics with Orbital-Free Density Functional Theory
• Assessing the accuracy of hybrid exchange-correlation functionals for the density response of warm dense electrons
• Combining stochastic density functional theory with deep potential molecular dynamics to study warm dense matter
• Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems
• Classical and quantum machine learning applications in spintronics
• Machine learning the electronic structure of matter across temperatures
• Morphological evolution via surface diffusion learned by convolutional, recurrent neural networks: extrapolation and prediction uncertainty
• Inverting the Kohn-Sham equations with physics-informed machine learning
• Ensemble Generalization of the Perdew-Zunger Self-Interaction Correction: a Way Out of Multiple Minima and Symmetry Breaking
• Extrapolation of polaron properties to low phonon frequencies by Bayesian machine learning
• Effect of molecular and electronic geometries on the electronic density in FLO-SIC
• Coupling-Constant Averaged Exchange-Correlation Hole for He, Li, Be, N, Ne Atoms from CCSD
• Electronic specific heat capacities and entropies from density matrix quantum Monte Carlo using Gaussian process regression to find gradients of noisy data
• Electronic structures of crystalline and amorphous GeSe and GeSbTe compounds using machine learning empirical pseudopotentials
• Physics-enhanced neural networks for equation-of-state calculations