Machine learning based interatomic potential for amorphous carbon

By Volker L. Deringer, Gábor Csányi. 2016

480 citations recorded by the source corpus.

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 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 a state-of-the-art empirical potential. Exemplary applications of the GAP model to surfaces of “diamondlike” tetrahedral amorphous carbon ($\textit{ta}$-C) are presented, including an estimate of the amorphous material’s surface energy and simulations of high-temperature surface reconstructions (“graphitization”). The presented interatomic potential appears to be promising for realistic and accurate simulations of nanoscale amorphous carbon structures.

Subfields: Electrical and Electronic Engineering, Materials Chemistry

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Electrical and Electronic Engineering

In Materials Chemistry

Citations in the corpus

A Performance and Cost Assessment of Machine Learning Interatomic Potentials. (2019, methodology): “hysics 2011 , 13 , 17930. (13) Szlachta, W. J.; Bartok, A. P.; Csanyi, G. Accuracy and Transferability of Gaussian Approximation Potential Models for Tungsten. Physical Review B 2014 , 90 , 104108. (14) Dragoni, D.; Da, T. D.; Csanyi, G.; Marzari, N. Achieving DFT Accuracy with a Machine-Learning In”
Fast and Accurate Uncertainty Estimation in Chemical Machine Learning. (2018, methodology): “20,21 In this article we focus on Gaussian Process Regression (GPR) 20 for the prediction of atomic structure properties with the well-established Smooth Overlap of Atomic Positions 11,12,22,23 (SOAP) framework to generate the kernels.”
Roadmap on multiscale materials modeling (2020, background): “For atoms, a good guess at some of these lower dimensional representations might be the interaction of pairs of atoms, then triplets, etc (a well worn idea in materials modeling, see also [63] for an example use with ML), but to go further we need to glean the right representations from the data its”
Machine Learning and Materials Informatics: Recent Applications and Prospects (2017, background): “Several candidates, including those based on symmetry functions [76–78], bispectra of neighborhood atomic densities [79], Coulomb matrices (and its variants) [80, 81], smooth overlap of atomic positions (SOAP) [82–85], and others [86,87], have been proposed.”
Active learning of linearly parametrized interatomic potentials (2016, methodology): “l predicting the force errors based on the distance between a given atomic conﬁguration and the training set. A very natural AL approach applicable to force ﬁelds based on Gaussian process regression [7, 17, 6, 27, 29, 30], which has not yet been implemented in practice, would be to use the Bayesian”