Machine-learning based interatomic potential for amorphous carbon

Abstract

We introduce a Gaussian approximation potential (GAP) for atomistic simulations of liquid and amorphous elemental carbon. Based on a machine-learning representation of the density-functional theory (DFT) potential-energy surface, such interatomic potentials enable materials simulations with close-to DFT accuracy but at much lower computational cost. We first determine the maximum accuracy that any finite-range potential can achieve in carbon structures; then, using a novel hierarchical set of two-, three-, and many-body structural descriptors, we construct a GAP model that can indeed reach the target accuracy. The potential yields accurate energetic and structural properties over a wide range of densities; it also correctly captures the structure of the liquid phases, at variance with state-of-the-art empirical potentials. Exemplary applications of the GAP model to surfaces of "diamond-like" tetrahedral amorphous carbon (ta-C) are presented, including an estimate of the amorphous material's surface energy, and simulations of high-temperature surface reconstructions ("graphitization"). The new interatomic potential appears to be promising for realistic and accurate simulations of nanoscale amorphous carbon structures.

16 pages, 16 figures (+ supplement)

References in corpus (2)

• Canonical sampling through velocity-rescaling
• An Efficient and Accurate Car-Parrinello-like Approach to Born-Oppenheimer Molecular Dynamics

Cited by in corpus (25)

• Machine Learning Unifies the Modelling of Materials and Molecules
• On-the-fly machine learning force field generation: Application to melting points
• Phase transitions of hybrid perovskites simulated by machine-learning force fields trained on-the-fly with Bayesian inference
• Symmetry-Adapted Machine-Learning for Tensorial Properties of Atomistic Systems
• An Accurate and Transferable Machine Learning Potential for Carbon
• Machine learning force fields and coarse-grained variables in molecular dynamics: application to materials and biological systems
• Machine Learning for Predicting Thermal Transport Properties of Solids
• Ionic liquids under confinement: From systematic variations of the ion and pore sizes towards an understanding of structure and dynamics in complex porous carbons
• BuRNN: Buffer Region Neural Network Approach for Polarizable-Embedding Neural Network / Molecular Mechanics Simulations
• A Novel Approach to Describe Chemical Environments in High Dimensional Neural Network Potentials
• Efficient implementation of atom-density representations
• Combining phonon accuracy with high transferability in Gaussian approximation potential models
• Atomic structure optimization with machine-learning enabled interpolation between chemical elements
• Ab initio Canonical Sampling based on Variational Inference
• Machine-learning of atomic-scale properties based on physical principles
• A Hessian-Based Assessment of Atomic Forces for Training Machine Learning Interatomic Potentials
• Machine learning modeling of high entropy alloy: the role of short-range order
• Machine learning at the atomic-scale
• Machine Learning and Materials Informatics: Recent Applications and Prospects
• MATGANIP: Learning to Discover the Structure-Property Relationship in Perovskites with Generative Adversarial Networks
• Particle Swarm Based Hyper-Parameter Optimization for Machine Learned Interatomic Potentials
• Machine Learning Forcefield for Silicate Glasses
• Structural transitions in dense disordered silicon from quantum-accurate ultra-large-scale simulations
• Incorporating electronic information into Machine Learning potential energy surfaces via approaching the ground-state electronic energy as a function of atom-based electronic populations
• Machine Learning the Effective Hamiltonian in High Entropy Alloys