By-passing the Kohn-Sham equations with machine learning

Abstract

Last year, at least 30,000 scientific papers used the Kohn-Sham scheme of density functional theory to solve electronic structure problems in a wide variety of scientific fields, ranging from materials science to biochemistry to astrophysics. Machine learning holds the promise of learning the kinetic energy functional via examples, by-passing the need to solve the Kohn-Sham equations. This should yield substantial savings in computer time, allowing either larger systems or longer time-scales to be tackled, but attempts to machine-learn this functional have been limited by the need to find its derivative. The present work overcomes this difficulty by directly learning the density-potential and energy-density maps for test systems and various molecules. Both improved accuracy and lower computational cost with this method are demonstrated by reproducing DFT energies for a range of molecular geometries generated during molecular dynamics simulations. Moreover, the methodology could be applied directly to quantum chemical calculations, allowing construction of density functionals of quantum-chemical accuracy.

References in corpus (8)

• Quantum ESPRESSO: a modular and open-source software project for quantum simulations of materials
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• Machine Learning of Accurate Energy-Conserving Molecular Force Fields
• DFT: A Theory Full of Holes?
• Pure density functional for strong correlations and the thermodynamic limit from machine learning
• Ions in solution: Density Corrected Density Functional Theory (DC-DFT)
• Electronic structure via potential functional approximations
• Corrections to Thomas-Fermi densities at turning points and beyond

Cited by in corpus (196)

• Machine learning and the physical sciences
• SchNet - a deep learning architecture for molecules and materials
• Machine Learning Force Fields
• A Performance and Cost Assessment of Machine Learning Interatomic Potentials
• Machine learning for molecular simulation
• Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems
• Data-driven materials science: status, challenges and perspectives
• Towards Exact Molecular Dynamics Simulations with Machine-Learned Force Fields
• A Fourth-Generation High-Dimensional Neural Network Potential with Accurate Electrostatics Including Non-local Charge Transfer
• Opportunities and Challenges for Machine Learning in Materials Science
• SchNetPack: A Deep Learning Toolbox For Atomistic Systems
• Machine learning for electronically excited states of molecules
• Alchemical and structural distribution based representation for improved QML
• WACSF - Weighted Atom-Centered Symmetry Functions as Descriptors in Machine Learning Potentials
• A Transferable Machine-Learning Model of the Electron Density
• sGDML: Constructing Accurate and Data Efficient Molecular Force Fields Using Machine Learning
• OrbNet: Deep Learning for Quantum Chemistry Using Symmetry-Adapted Atomic-Orbital Features
• Deep-Learning Density Functional Theory Hamiltonian for Efficient ab initio Electronic-Structure Calculation
• Transferability in Machine Learning for Electronic Structure via the Molecular Orbital Basis
• Bayesian optimization for tuning and selecting hybrid-density functionals
• Perspective on integrating machine learning into computational chemistry and materials science
• Machine Learning the Voltage of Electrode Materials in Metal-ion Batteries
• Kohn-Sham equations as regularizer: building prior knowledge into machine-learned physics
• Constructing first-principles phase diagrams of amorphous LixSi using machine-learning-assisted sampling with an evolutionary algorithm
• Learning the electronic density of states in condensed matter
• Quantum Machine Learning for Electronic Structure Calculations
• Machine Learning for Quantum Matter
• Neural Quantum States of frustrated magnets: generalization and sign structure
• The Importance of being consistent
• Deep Learning and Density Functional Theory
• Machine learning and density functional theory
• A Deep Dive into Machine Learning Density Functional Theory for Materials Science and Chemistry
• Machine Learning Configuration Interaction
• Molecular Force Fields with Gradient-Domain Machine Learning: Construction and Application to Dynamics of Small Molecules with Coupled Cluster Forces
• A Universal Density Matrix Functional from Molecular Orbital-Based Machine Learning: Transferability across Organic Molecules
• Machine Learning the Physical Non-Local Exchange-Correlation Functional of Density-Functional Theory
• Discriminative Cooperative Networks for Detecting Phase Transitions
• Learning the exchange-correlation functional from nature with fully differentiable density functional theory
• Uncertainty estimation for molecular dynamics and sampling
• Electronic Density Response of Warm Dense Matter
• Image-based deep learning for classification of noise transients in gravitational wave detectors
• SchNetPack 2.0: A neural network toolbox for atomistic machine learning
• DeePKS: a comprehensive data-driven approach towards chemically accurate density functional theory
• Quantum deep field: data-driven wave function, electron density generation, and atomization energy prediction and extrapolation with machine learning
• Design and Analysis of Machine Learning Exchange-Correlation Functionals via Rotationally Invariant Convolutional Descriptors
• An assessment of initial guesses for self-consistent field calculations. Superposition of Atomic Potentials: simple yet efficient
• Inverse Kohn-Sham Density Functional Theory: Progress and Challenges
• Metadynamics for Training Neural Network Model Chemistries: a Competitive Assessment
• Machine learning materials physics: Multi-resolution neural networks learn the free energy and nonlinear elastic response of evolving microstructures
• Thermodynamics and its Prediction and CALPHAD Modeling: Review, State of the Art, and Perspectives
• Neural-network Kohn-Sham exchange-correlation potential and its out-of-training transferability
• KITE: high-performance accurate modelling of electronic structure and response functions of large molecules, disordered crystals and heterostructures
• Band gap prediction for large organic crystal structures with machine learning
• Pattern Learning Electronic Density of States
• Predicting electronic structures at any length scale with machine learning
• Regression-clustering for Improved Accuracy and Training Cost with Molecular-Orbital-Based Machine Learning
• Kinetic energy densities based on the fourth order gradient expansion: performance in different classes of materials and improvement via machine learning
• Predicting charge density distribution of materials using a local-environment-based graph convolutional network
• Deep learning the Hohenberg-Kohn maps of Density Functional Theory
• Accelerating Finite-temperature Kohn-Sham Density Functional Theory with Deep Neural Networks
• ACCDB: A Collection of Chemistry DataBases for Broad Computational Purposes
• Equivariant graph neural networks for fast electron density estimation of molecules, liquids, and solids
• Machine learning and excited-state molecular dynamics
• Gaussian Process-Based Refinement of Dispersion Corrections
• PANNA: Properties from Artificial Neural Network Architectures
• Deep-learning density functional perturbation theory
• Nuclear energy density functionals from machine learning
• Putting Density Functional Theory to the Test in Machine-Learning-Accelerated Materials Discovery
• Extensive deep neural networks for transferring small scale learning to large scale systems
• Molecular Force Fields with Gradient-Domain Machine Learning (GDML): Comparison and Synergies with Classical Force Fields
• Improved accuracy and transferability of molecular-orbital-based machine learning: Organics, transition-metal complexes, non-covalent interactions, and transition states
• Machine learning configuration interaction for ab initio potential energy curves
• Challenges for Machine Learning Force Fields in Reproducing Potential Energy Surfaces of Flexible Molecules
• Dynamical Strengthening of Covalent and Non-Covalent Molecular Interactions by Nuclear Quantum Effects at Finite Temperature
• Convolutional neural networks for atomistic systems
• A classical density functional from machine learning and a convolutional neural network
• A deep neural network for molecular wave functions in quasi-atomic minimal basis representation
• Toward Orbital-Free Density Functional Theory with Small Data Sets and Deep Learning
• Data-driven kinetic energy density fitting for orbital-free DFT: linear vs Gaussian process regression
• Evolving symbolic density functionals
• Quantum Machine-Learning for Eigenstate Filtration in Two-Dimensional Materials
• Analytical classical density functionals from an equation learning network
• Machine-learning models for Raman spectra analysis of twisted bilayer graphene
• Overcoming the Barrier of Orbital-Free Density Functional Theory for Molecular Systems Using Deep Learning
• Deep Neural Network Computes Electron Densities and Energies of a Large Set of Organic Molecules Faster than Density Functional Theory (DFT)
• Machine learning the derivative discontinuity of density-functional theory
• Machine learning quantum mechanics: solving quantum mechanics problems using radial basis function networks
• Learning from the Density to Correct Total Energy and Forces in First Principle Simulations
• NENCI-2021 Part I: A Large Benchmark Database of Non-Equilibrium Non-Covalent Interactions Emphasizing Close Intermolecular Contacts
• Density Functional Theory Transformed into a One-electron Reduced Density Matrix Functional Theory for the Capture of Static Correlation
• Machine Learning Exchange-Correlation Potential in Time Dependent Density Functional Theory
• Order-$N$ orbital-free density-functional calculations with machine learning of functional derivatives for semiconductors and metals
• Building high accuracy emulators for scientific simulations with deep neural architecture search
• A perspective on machine learning and data science for strongly correlated electron problems
• Predicting the Charge Density Response in Metal Electrodes
• Finite-temperature materials modeling from the quantum nuclei to the hot electrons regime
• Artificial neural networks for density-functional optimizations in fermionic systems
• Generating equilibrium molecules with deep neural networks
• Accurate Molecular-Orbital-Based Machine Learning Energies via Unsupervised Clustering of Chemical Space
• Deep Learning the Functional Renormalization Group
• Supervised machine learning of ultracold atoms with speckle disorder
• Machine learning electron correlation in a disordered medium
• Comparison of Density-Matrix Corrections to Density Functional Theory
• Scalable neural networks for the efficient learning of disordered quantum systems
• Linear Jacobi-Legendre expansion of the charge density for machine learning-accelerated electronic structure calculations
• Machine Learning Universal Bosonic Functionals
• Reliable emulation of complex functionals by active learning with error control
• Fast and flexible long-range models for atomistic machine learning
• Emergent Quantum Mechanics in an Introspective Machine Learning Architecture
• 3DReact: Geometric deep learning for chemical reactions
• Exact constraints and appropriate norms in machine learned exchange-correlation functionals
• Machine learning density functionals from the random-phase approximation
• Machine learning nonequilibrium electron forces for adiabatic spin dynamics
• Non-parametric Local Pseudopotentials with Machine Learning: a Tin Pseudopotential Built Using Gaussian Process Regression
• Uncertainty quantification and estimation in differential dynamic microscopy
• An Introduction to Electrocatalyst Design using Machine Learning for Renewable Energy Storage
• Towards a Quantum Fluid Theory of Correlated Many-Fermion Systems from First Principles
• Degeneration of kernel regression with Matern kernels into low-order polynomial regression in high dimension
• Determining electronic properties from L-edge X-ray absorption spectra of transition metal compounds with artificial neural networks
• MGNN: Moment Graph Neural Network for Universal Molecular Potentials
• Machine Learning Diffusion Monte Carlo Energies
• Grad DFT: a software library for machine learning enhanced density functional theory
• Efficient Learning of a One-dimensional Density Functional Theory
• Completing density functional theory by machine-learning hidden messages from molecules
• Bridging electronic and classical density-functional theory using universal machine-learned functional approximations
• Sampling algorithms for validation of supervised learning models for Ising-like systems
• Unified Deep Learning Framework for Many-Body Quantum Chemistry via Green's Functions
• Machine learning band gaps from the electron density
• Machine-learned prediction of the electronic fields in a crystal
• Deep learning for surrogate modelling of 2D mantle convection
• Learning the energy curvature versus particle number in approximate density functionals
• Reducing the Quantum Many-electron Problem to Two Electrons with Machine Learning
• Wavelet Scattering Networks for Atomistic Systems with Extrapolation of Material Properties
• Fast and stable deep-learning predictions of material properties for solid solution alloys
• Deep learning and high harmonic generation
• Predicting The One-Particle Density Matrix With Machine Learning
• Mean-Field Density Matrix Decompositions
• Bypassing the computational bottleneck of quantum-embedding theories for strong electron correlations with machine learning
• Learning on-top: regressing the on-top pair density for real-space visualization of electron correlation
• Machine learning of kinetic energy densities with target and feature averaging: better results with fewer training data
• Supervised learning of few dirty bosons with variable particle number
• Density functionals and Kohn-Sham potentials with minimal wavefunction preparations on a quantum computer
• Construction of Machine Learned Force Fields with Quantum Chemical Accuracy: Applications and Chemical Insights
• Machine learning forces trained by Gaussian process in liquid states: Transferability to temperature and pressure
• How Well Does Kohn-Sham Regularizer Work for Weakly Correlated Systems?
• The loss of the property of locality of the kernel in high-dimensional Gaussian process regression on the example of the fitting of molecular potential energy surfaces
• Scalable Training of Trustworthy and Energy-Efficient Predictive Graph Foundation Models for Atomistic Materials Modeling: A Case Study with HydraGNN
• Low-data deep quantum chemical learning for accurate MP2 and coupled-cluster correlations
• Convolutional network learning of self-consistent electron density via grid-projected atomic fingerprints
• SPA${}^{\mathrm{H}}$M(a,b): encoding the density information from guess Hamiltonian in quantum machine learning representations
• Training-free hyperparameter optimization of neural networks for electronic structures in matter
• Accurate Molecular Dynamics Enabled by Efficient Physically-Constrained Machine Learning Approaches
• Generation of Bose-Einstein Condensates' Ground State Through Machine Learning
• Machine learning for accuracy in density functional approximations
• Compressing physical properties of atomic species for improving predictive chemistry
• Nonequilibrium fluctuations of a driven quantum heat engine via machine learning
• Neural-network-supported basis optimizer for the configuration interaction problem in quantum many-body clusters: Feasibility study and numerical proof
• A machine-learned kinetic energy model for light weight metals and compounds of group III-V elements
• Molecular Dipole Moment Learning via Rotationally Equivariant Gaussian Process Regression with Derivatives in Molecular-orbital-based Machine Learning
• Deep learning density functionals for gradient descent optimization
• Insights into one-body density matrices using deep learning
• Reactive molecular dynamics at constant pressure via non-reactive force fields: extending the Empirical Valence Bond method to the isothermal-isobaric ensemble
• Detecting Nematic Order in STM/STS Data with Artificial Intelligence
• Impact of quantum-chemical metrics on the machine learning prediction of electron density
• Machine learning the electronic structure of matter across temperatures
• Deep learning nonlocal and scalable energy functionals for quantum Ising models
• Lean CNNs for mapping electron charge density fields to material properties
• Machine-Learning Surrogate Model for Accelerating the Search of Stable Ternary Alloys
• Self-consistent assessment of Englert-Schwinger model on atomic properties
• Physical machine learning outperforms "human learning" in Quantum Chemistry
• Machine learning-guided construction of an analytic kinetic energy functional for orbital free density functional theory
• Predicting electronic screening for fast Koopmans spectral functional calculations
• Solution of inverse problem for Gross-Pitaevskii equation with artificial neural networks
• Linear convergence in optimization over directed graphs with row-stochastic matrices
• A two-density approach to the general many-body problem and a proof of principle for small atoms and molecules
• Learning DFT
• Deep-learning atomistic semi-empirical pseudopotential model for nanomaterials
• Predicting fermionic densities using a Projected Quantum Kernel method
• Orbital Mixer: Using Atomic Orbital Features for Basis Dependent Prediction of Molecular Wavefunctions
• Learning Density Functionals from Noisy Quantum Data
• On the Kinetic Energy Density Functional: The Limit of the Density Derivative Order
• Alchemical perturbation density functional theory (APDFT)
• Electronic structures of crystalline and amorphous GeSe and GeSbTe compounds using machine learning empirical pseudopotentials
• Solving deep-learning density functional theory via variational autoencoders
• Machine-learning semi-local density functional theory for many-body lattice models at zero and finite temperature
• Stacked Generalization Approach to Improve Prediction of Molecular Atomization Energies
• Challenges and opportunities in the supervised learning of quantum circuit outputs
• Quantum-Enhanced Neural Exchange-Correlation Functionals
• Neural Polarization: Toward Electron Density for Molecules by Extending Equivariant Networks
• Machine learning approach for vibronically renormalized electronic band structures
• Global sampling of Feynman's diagrams through Normalizing Flow
• Charge Transfer in Classical Molecular Dynamics Simulations of Met-enkephalin: Improving Traditional Force Field with Data Driven Models
• Machine learning of electronic structure and atomistic properties from the external potential
• Machine learning based prediction of the electronic structure of quasi-one-dimensional materials under strain
• Learning electron densities in the condensed phase
• Reducing the Long Tail Losses in Scientific Emulations with Active Learning