An Accurate and Transferable Machine Learning Potential for Carbon

Abstract

We present an accurate machine learning (ML) model for atomistic simulations of carbon, constructed using the Gaussian approximation potential (GAP) methodology. The potential, named GAP-20, describes the properties of the bulk crystalline and amorphous phases, crystal surfaces and defect structures with an accuracy approaching that of direct ab initio simulation, but at a significantly reduced cost. We combine structural databases for amorphous carbon and graphene, which we extend substantially by adding suitable configurations, for example, for defects in graphene and other nanostructures. The final potential is fitted to reference data computed using the optB88-vdW density functional theory (DFT) functional. Dispersion interactions, which are crucial to describe multilayer carbonaceous materials, are therefore implicitly included. We additionally account for long-range dispersion interactions using a semianalytical two-body term and show that an improved model can be obtained through an optimisation of the many-body smooth overlap of atomic positions (SOAP) descriptor. We rigorously test the potential on lattice parameters, bond lengths, formation energies and phonon dispersions of numerous carbon allotropes. We compare the formation energies of an extensive set of defect structures, surfaces and surface reconstructions to DFT reference calculations. The present work demonstrates the ability to combine, in the same ML model, the previously attained flexibility required for amorphous carbon [Phys. Rev. B, 95, 094203, (2017)] with the high numerical accuracy necessary for crystalline graphene [Phys. Rev. B, 97, 054303, (2018)], thereby providing an interatomic potential that will be applicable to a wide range of applications concerning diverse forms of bulk and nanostructured carbon.

The following article has been accepted by The Journal of Chemical Physics. After it is published, it will be found at https://publishing.aip.org/resources/librarians/products/journals/

References in corpus (33)

• Electric Field Effect in Atomically Thin Carbon Films
• The electronic properties of graphene
• Graphene: Status and Prospects
• Graphene Photonics and Optoelectronics
• Van der Waals Density Functional for General Geometries
• Van der Waals density functionals applied to solids
• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• A Higher-Accuracy van der Waals Density Functional
• On representing chemical environments
• SchNet - a deep learning architecture for molecules and materials
• Ab initio Random Structure Searching
• Comparing molecules and solids across structural and alchemical space
• Machine Learning Unifies the Modelling of Materials and Molecules
• Machine-learning based interatomic potential for amorphous carbon
• Machine learning a general purpose interatomic potential for silicon
• Nucleation mechanism for the direct graphite-to-diamond phase transition
• FCHL revisited: faster and more accurate quantum machine learning
• Alchemical and structural distribution based representation for improved QML
• Achieving DFT accuracy with a machine-learning interatomic potential: thermomechanics and defects in bcc ferromagnetic iron
• Stone-Wales--type transformations in carbon nanostructures driven by electron irradiation
• Accurate Interatomic Force Fields via Machine Learning with Covariant Kernels
• Data-driven learning of total and local energies in elemental boron
• A Machine Learning Potential for Graphene
• Improving the convergence of defect calculations in supercells - an ab initio study of the neutral silicon vacancy
• Growth Mechanism and Origin of High $s{p}^3$ Content in Tetrahedral Amorphous Carbon
• Transport properties for liquid silicon-oxygen-iron mixtures at Earth's core conditions
• On-Chip Diamond Raman Laser
• Feature Optimization for Atomistic Machine Learning Yields A Data-Driven Construction of the Periodic Table of the Elements
• Gaussian approximation potential modeling of lithium intercalation in carbon nanostructures
• Inscription of 3D waveguides in diamond using an ultrafast laser
• Buckyball sandwiches
• Pressure-induced s-band ferromagnetism in alkali metals
• Recognizing Local and Global Structural Motifs at the Atomic Scale

Cited by in corpus (51)

• Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems
• Neuroevolution machine learning potentials: Combining high accuracy and low cost in atomistic simulations and application to heat transport
• Physics-inspired structural representations for molecules and materials
• Machine-learning interatomic potentials for materials science
• Towards self-driving laboratories: The central role of density functional theory in the AI age
• General-purpose machine-learned potential for 16 elemental metals and their alloys
• Evaluation of the MACE Force Field Architecture: from Medicinal Chemistry to Materials Science
• How to validate machine-learned interatomic potentials
• A Deep Dive into Machine Learning Density Functional Theory for Materials Science and Chemistry
• Tutorial: How to Train a Neural Network Potential
• BIGDML: Towards Exact Machine Learning Force Fields for Materials
• Complex ${\mathrm{Ga}}_2{\mathrm{O}}_3$ Polymorphs Explored by Accurate and General-Purpose Machine-Learning Interatomic Potentials
• Anisotropic and high thermal conductivity in monolayer quasi-hexagonal fullerene: A comparative study against bulk phase fullerene
• Interatomic potentials: Achievements and challenges
• Machine Learning Interatomic Potential for Simulations of Carbon at Extreme Conditions
• Defect-Dependent Corrugation in Graphene
• Diamond formation from hydrocarbon mixtures in planets
• Efficient implementation of atom-density representations
• Predicting Properties of Periodic Systems from Cluster Data: A Case Study of Liquid Water
• Developments and Further Applications of Ephemeral Data Derived Potentials
• Efficiency, Accuracy, and Transferability of Machine Learning Potentials: Application to Dislocations and Cracks in Iron
• E(n)-Equivariant Cartesian Tensor Passing Potential
• Advances in modeling complex materials: The rise of neuroevolution potentials
• Transferability of machine learning potentials: Protonated water neural network potential applied to the protonated water hexamer
• Metadynamics sampling in atomic environment space for collecting training data for machine learning potentials
• Model-free quantification of completeness, uncertainties, and outliers in atomistic machine learning using information theory
• PYSED: A tool for extracting kinetic-energy-weighted phonon dispersion and lifetime from molecular dynamics simulations
• Machine Learning and Data-Driven Methods in Computational Surface and Interface Science
• Combining linear-scaling quantum transport and machine-learning molecular dynamics to study thermal and electronic transports in complex materials
• PiNNwall: Heterogeneous Electrode Models from Integrating Machine Learning and Atomistic Simulation
• Combining the D3 dispersion correction with the neuroevolution machine-learned potential
• Molecular potentials for 2D molybdenum disulphide: transferability and performance
• Anisotropic molecular coarse-graining by force and torque matching with neural networks
• Neural network approach for a rapid prediction of metal-supported borophene properties
• Defects induce phase transition from dynamic to static rippling in graphene
• Revisit Many-body Interaction Heat Current and Thermal Conductivity Calculation in Moment Tensor Potential/LAMMPS Interface
• Machine learning potentials for complex aqueous systems made simple
• Machine learning based modeling of disordered elemental semiconductors: understanding the atomic structure of a-Si and a-C
• Exploring the energy landscape of aluminas through machine learning interatomic potential
• A computational framework for nanotrusses: input convex neural networks approach
• Elastic Screening of Pseudogauge Fields in Graphene
• API Phonons: Python Interfaces for Phonon Transport Modeling
• HighNESS Conceptual Design Report: Volume I
• Machine-Learning Surrogate Model for Accelerating the Search of Stable Ternary Alloys
• Site-projected Thermal Conductivity: Application to defects, interfaces, and homogeneously disordered materials
• A general formalism for machine-learning models based on multipolar-spherical harmonics
• Machine-Learned Bond-Order Potential for Exploring the Configuration Space of Carbon
• Managing Expectations and Imbalanced Training Data in Reactive Force Field Development: an Application to Water Adsorption on Alumina
• Cluster Fragments in Amorphous Phosphorus and their Evolution under Pressure
• Validation of moment tensor potentials for fcc and bcc metals using EXAFS spectra
• Transfer learning of many-body electronic correlation entropy from local measurements