Machine learning a general purpose interatomic potential for silicon

Abstract

The success of first principles electronic structure calculation for predictive modeling in chemistry, solid state physics, and materials science is constrained by the limitations on simulated length and time scales due to computational cost and its scaling. Techniques based on machine learning ideas for interpolating the Born-Oppenheimer potential energy surface without explicitly describing electrons have recently shown great promise, but accurately and efficiently fitting the physically relevant space of configurations has remained a challenging goal. Here we present a Gaussian Approximation Potential for silicon that achieves this milestone, accurately reproducing density functional theory reference results for a wide range of observable properties, including crystal, liquid, and amorphous bulk phases, as well as point, line, and plane defects. We demonstrate that this new potential enables calculations that would be extremely expensive with a first principles electronic structure method, such as finite temperature phase boundary lines, self-diffusivity in the liquid, formation of the amorphous by slow quench, and dynamic brittle fracture. We show that the uncertainty quantification inherent to the Gaussian process regression framework gives a qualitative estimate of the potential's accuracy for a given atomic configuration. The success of this model shows that it is indeed possible to create a useful machine-learning-based interatomic potential that comprehensively describes a material, and serves as a template for the development of such models in the future.

arXiv comment28 pages, 27 figures

References in corpus (57)

• Maximally-localized generalized Wannier functions for composite energy bands
• 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
• Moment Tensor Potentials: a class of systematically improvable interatomic potentials
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• Ab initio Random Structure Searching
• High-accuracy first-principles determination of the structural, vibrational and thermodynamical properties of diamond, graphite, and derivatives
• A Spectral Analysis Method for Automated Generation of Quantum-Accurate Interatomic Potentials
• Big Data meets Quantum Chemistry Approximations: The $\Delta$-Machine Learning Approach
• Comparing molecules and solids across structural and alchemical space
• Machine Learning Unifies the Modelling of Materials and Molecules
• High-pressure phases of silane
• Active learning of linearly parametrized interatomic potentials
• Machine learning prediction errors better than DFT accuracy
• Machine-learning based interatomic potential for amorphous carbon
• Machine Learning of Molecular Electronic Properties in Chemical Compound Space
• Interatomic Potential for Silicon Defects and Disordered Phases
• Machine Learning Energies of 2 M Elpasolite (ABC${}_2$D${}_6$) Crystals
• Efficient and Accurate Machine-Learning Interpolation of Atomic Energies in Compositions with Many Species
• Alchemical and structural distribution based representation for improved QML
• Symmetry-Adapted Machine-Learning for Tensorial Properties of Atomistic Systems
• Interatomic potentials for ionic systems with density functional accuracy based on charge densities obtained by a neural network
• Hierarchical modeling of molecular energies using a deep neural network
• Automatic Selection of Atomic Fingerprints and Reference Configurations for Machine-Learning Potentials
• Achieving DFT accuracy with a machine-learning interatomic potential: thermomechanics and defects in bcc ferromagnetic iron
• Understanding molecular representations in machine learning: The role of uniqueness and target similarity
• Accurate Interatomic Force Fields via Machine Learning with Covariant Kernels
• Data-driven learning of total and local energies in elemental boron
• Extending the Accuracy of the SNAP Interatomic Potential Form
• Accuracy of generalized gradient approximation functionals for density functional perturbation theory calculations
• A Machine Learning Potential for Graphene
• A learning scheme to predict atomic forces and accelerate materials simulations
• Growth Mechanism and Origin of High $s{p}^3$ Content in Tetrahedral Amorphous Carbon
• Non-covalent interactions across organic and biological subsets of chemical space: Physics-based potentials parametrized from machine learning
• Structure-based Sampling and Self-correcting Machine Learning for Accurate Calculations of Potential Energy Surfaces and Vibrational Levels
• Accurate Force Field for Molybdenum by Machine Learning Large Materials Data
• Machine learning of molecular properties: locality and active learning
• Constructing first-principles phase diagrams of amorphous LixSi using machine-learning-assisted sampling with an evolutionary algorithm
• Liquid-liquid transition in supercooled silicon determined by first-principles simulation
• Screened empirical bond-order potentials for Si-C
• Transferable atomic multipole machine learning models for small organic molecules
• A fourfold coordinated point defect in silicon
• Generalized Stacking Fault Energy Surfaces and Dislocation Properties of Silicon: A First-Principles Theoretical Study
• A universal preconditioner for simulating condensed phase materials
• Stratified construction of neural network based interatomic models for multicomponent materials
• Wavelet Scattering Regression of Quantum Chemical Energies
• Learning molecular energies using localized graph kernels
• An optimized interatomic potential for silicon and its application to thermal stability of silicene
• Convolutional neural networks for atomistic systems
• Electron correlation and the phase diagram of Si
• Magic Numbers of Silicon Clusters
• Comparison between classical potentials and ab initio for silicon under large shear
• Finite temperature molecular dynamics study of unstable stacking fault free energies in silicon

Cited by in corpus (124)

• Machine learning and the physical sciences
• Machine Learning Force Fields
• A Performance and Cost Assessment of Machine Learning Interatomic Potentials
• On-the-fly machine learning force field generation: Application to melting points
• Neuroevolution machine learning potentials: Combining high accuracy and low cost in atomistic simulations and application to heat transport
• Active Learning of Uniformly Accurate Inter-atomic Potentials for Materials Simulation
• GPUMD: A package for constructing accurate machine-learned potentials and performing highly efficient atomistic simulations
• Machine learning for electronically excited states of molecules
• Machine-learning interatomic potentials for materials science
• The Open Catalyst 2022 (OC22) Dataset and Challenges for Oxide Electrocatalysts
• Embedded Atom Neural Network Potentials: Efficient and Accurate Machine Learning with a Physically Inspired Representation
• An Accurate and Transferable Machine Learning Potential for Carbon
• De novo exploration and self-guided learning of potential-energy surfaces
• Combining SchNet and SHARC: The SchNarc machine learning approach for excited-state dynamics
• Deep Potentials for Materials Science
• On the Completeness of Atomic Structure Representations
• Fast and Accurate Uncertainty Estimation in Chemical Machine Learning
• Machine-learning interatomic potential for radiation damage and defects in tungsten
• Learning the electronic density of states in condensed matter
• How to validate machine-learned interatomic potentials
• Predicting molecular dipole moments by combining atomic partial charges and atomic dipoles
• Deep Learning of Accurate Force Field of Ferroelectric HfO${}_2$
• SchNetPack 2.0: A neural network toolbox for atomistic machine learning
• Machine learning driven simulated deposition of carbon films: from low-density to diamondlike amorphous carbon
• Quantum-corrected thickness-dependent thermal conductivity in amorphous silicon predicted by machine-learning molecular dynamics simulations
• Machine-learning based interatomic potential for phonon transport in perfect crystalline Si and crystalline Si with vacancies
• Simple machine-learned interatomic potentials for complex alloys
• Data-driven Material Models for Atomistic Simulation
• Interatomic potentials: Achievements and challenges
• Machine learning and excited-state molecular dynamics
• Phase Transitions of Zirconia: Machine-Learned Force Fields Beyond Density Functional Theory
• Universal QM/MM Approaches for General Nanoscale Applications
• PANNA: Properties from Artificial Neural Network Architectures
• Temperature Effect on Phonon Dispersion Stability of Zirconium by Machine Learning-driven Atomistic Simulations
• An Experimentally Driven Automated Machine Learned lnter-Atomic Potential for a Refractory Oxide
• Application of machine learning potentials to predict grain boundary properties in fcc elemental metals
• MAISE: Construction of neural network interatomic models and evolutionary structure optimization
• Group-theoretical high-order rotational invariants for structural representations: Application to linearized machine learning interatomic potential
• Combining Machine Learning and Many-Body Calculations: Coverage-Dependent Adsorption of CO on Rh(111)
• Efficient implementation of atom-density representations
• Optimization and Validation of a Deep Learning CuZr Atomistic Potential: Robust Applications for Crystalline and Amorphous Phases with near-DFT Accuracy
• Drawing Phase Diagrams of Random Quantum Systems by Deep Learning the Wave Functions
• Developments and Further Applications of Ephemeral Data Derived Potentials
• Combining phonon accuracy with high transferability in Gaussian approximation potential models
• Machine learning potentials for multicomponent systems: The Ti-Al binary system
• Atomic energy mapping of neural network potential
• Development of a general-purpose machine-learning interatomic potential for aluminum by the physically-informed neural network method
• A New Kind of Atlas of Zeolite Building Blocks
• Efficiency, Accuracy, and Transferability of Machine Learning Potentials: Application to Dislocations and Cracks in Iron
• Self-Parametrizing System-Focused Atomistic Models
• Sensitivity and Dimensionality of Atomic Environment Representations used for Machine Learning Interatomic Potentials
• Exploring the robust extrapolation of high-dimensional machine learning potentials
• Robustness of Local Predictions in Atomistic Machine Learning Models
• Advances in modeling complex materials: The rise of neuroevolution potentials
• Exploring librational pathways with on-the-fly machine-learning force fields: Methylammonium molecules in MAPbX${}_3$ (X=I, Br, Cl) perovskites
• Development of a physically-informed neural network interatomic potential for tantalum
• ænet-PyTorch: a GPU-supported implementation for machine learning atomic potentials training
• Finite-temperature materials modeling from the quantum nuclei to the hot electrons regime
• Atomistic Mechanism Underlying the Si(111)-(7\times7) Surface Reconstruction Revealed by Artificial Neural-network Potential
• Self-learning analytical interatomic potential describing laser-excited silicon
• Do Machine-Learning Atomic Descriptors and Order Parameters Tell the Same Story? The Case of Liquid Water
• Multiscale machine-learning interatomic potentials for ferromagnetic and liquid iron
• Complex Spin Hamiltonian Represented by Artificial Neural Network
• Recent advances in describing and driving crystal nucleation using machine learning and artificial intelligence
• A deep machine learning potential for atomistic simulation of Fe-Si-O systems under Earth's outer core conditions
• Indirect Learning of Interatomic Potentials for Accelerated Materials Simulations
• Enhancing the Accuracy of Density Functional Tight Binding Models Through ChIMES Many-body Interaction Potentials
• Uncertainty quantification and estimation in differential dynamic microscopy
• Optimal radial basis for density-based atomic representations
• Measuring transferability issues in machine-learning force fields: The example of Gold-Iron interactions with linearized potentials
• Modeling the Ga/As binary system across temperaturesand compositions from first principles
• Lattice dynamics and elastic properties of alpha-U at high-temperature and high-pressure by machine learning potential simulations
• Infrared spectra of neutral polycyclic aromatic hydrocarbons by machine learning
• Neural Networks Potential from the Bispectrum Component: A Case Study on Crystalline Silicon
• A collinear-spin machine learned interatomic potential for Fe${}_7$Cr${}_2$Ni alloy
• Mean-Field Density Matrix Decompositions
• Predicting hot-electron free energies from ground-state data
• Proper Orthogonal Descriptors for Efficient and Accurate Interatomic Potentials
• Thermodynamic driving force in the formation of hexagonal-diamond Si and Ge nanowires
• Machine learning phases and criticalities without using real data for training
• A numerical-continuation-enhanced flexible boundary condition scheme applied to Mode I and Mode III fracture
• Unsupervised learning-based structural analysis: Search for a characteristic low-dimensional space by local structures in atomistic simulations
• Solid-phase silicon homoepitaxy via shear-induced amorphization and recrystallization
• Prediction of surface reconstructions using MAGUS
• Machine learning modeling of high entropy alloy: the role of short-range order
• Machine learning potentials for complex aqueous systems made simple
• Efficient force field and energy emulation through partition of permutationally equivalent atoms
• Adaptive energy reference for machine-learning models of the electronic density of states
• Uncertainty Quantification in Atomistic Simulations of Silicon using Interatomic Potentials
• Pre-training, fine-tuning, and distillation (PFD): Automatically generating machine learning force fields from universal models
• Developing Potential Energy Surfaces for Graphene-based 2D-3D Interfaces from Modified High Dimensional Neural Networks for Applications in Energy Storage
• Efficient moment tensor machine-learning interatomic potential for accurate description of defects in Ni-Al Alloys
• Fast proper orthogonal descriptors for many-body interatomic potentials
• Exploring the energy landscape of aluminas through machine learning interatomic potential
• Benchmarking CHGNet Universal Machine Learning Interatomic Potential Against DFT and EXAFS: Case of Layered WS2 and MoS2
• Bayesian inference of composition-dependent phase diagrams
• Machine learning based modeling of disordered elemental semiconductors: understanding the atomic structure of a-Si and a-C
• Rigorous body-order approximations of an electronic structure potential energy landscape
• Deep Learning Inter-atomic Potential for Thermal and Phonon Behaviour of Silicon Carbide with Quantum Accuracy
• Free energy of (CoxMn1-x)3O4 mixed phases from machine-learning-enhanced ab initio calculations
• Critical assessment of machine-learned repulsive potentials for the Density Functional based Tight-Binding method: a case study for pure silicon
• Modeling refractory high-entropy alloys with efficient machine-learned interatomic potentials: defects and segregation
• Active-learning-based efficient prediction of ab-initio atomic energy: a case study on a Fe random grain boundary model with millions of atoms
• Predictive power of polynomial machine learning potentials for liquid states in 22 elemental systems
• Application-specific machine-learned interatomic potentials: exploring the trade-off between DFT convergence, MLIP expressivity, and computational cost
• Machine Learning Forcefield for Silicate Glasses
• A neural-network-backed effective harmonic potential study of the ambient pressure phases of hafnia
• Yielding under compression and the polyamorphic transition in silicon
• Replica exchange nested sampling
• Modeling Chemical Exfoliation of Non-van der Waals Chromium Sulfides by Machine Learning Interatomic Potentials and Monte Carlo Simulations
• Machine-Learning Surrogate Model for Accelerating the Search of Stable Ternary Alloys
• High-performance descriptor for magnetic materials: Accurate discrimination of magnetic structure
• Unraveling the Atomic-Scale Pathways Driving Pressure-Induced Phase Transitions in Silicon
• Accurate Machine Learning Interatomic Potentials for Polyacene Molecular Crystals: Application to Single Molecule Host-Guest Systems
• Radiation damage and phase stability of Al${}_x$CrCuFeNi${}_y$ alloys using a machine-learned interatomic potential
• Structural transitions in dense disordered silicon from quantum-accurate ultra-large-scale simulations
• A general formalism for machine-learning models based on multipolar-spherical harmonics
• Analysis of Kohn-Sham Eigenfunctions Using a Convolutional Neural Network in Simulations of the Metal-insulator Transition in Doped Semiconductors
• Emulating the First Principles of Matter: A Probabilistic Roadmap
• Scalable Data-Driven Basis Selection for Linear Machine Learning Interatomic Potentials
• Systematic global structure search of bismuth-based binary systems under pressure using machine learning potentials
• Learning electron densities in the condensed phase
• Similarity of particle systems using an invariant root mean square deviation measure
• Machine Learning the Effective Hamiltonian in High Entropy Alloys