Moment Tensor Potentials: A Class of Systematically Improvable Interatomic Potentials

Shapeev, Alexander V.

doi:10.1137/15m1054183

Cited by 963 publications

(863 citation statements)

References 27 publications

(51 reference statements)

Supporting

Mentioning

852

Contrasting

Unclassified

Order By: Relevance

“…This is similar in spirit to the recently introduced Moment Tensor Potentials, 56 and also to another scheme that uses a parametric two-body term in combination with a neural network that describes the many-body interactions 57 . In the above expression, the δ are scaling parameters, and each corresponds to the distribution of energy contributions a given interaction term has to represent.…”

mentioning

confidence: 79%

See 1 more Smart Citation

Machine learning based interatomic potential for amorphous carbon

2017

View full text Add to dashboard Cite

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.

show abstract

mentioning

confidence: 79%

“…34,[53][54][55][56] However, for a complete description of these atomic environments one must fit the atomic energy function in a high-dimensional space. This leads to poor "extrapolation", that is, to a poor fit in regions of configuration space far away from any data points.…”

mentioning

confidence: 99%

Machine learning based interatomic potential for amorphous carbon

2017

View full text Add to dashboard Cite

show abstract

“…Another common strategy is a bottom‐up approach, whereby features are constructed from the local environment of each atom and combined at the crystal level. Such descriptors include atom‐centered symmetry functions (ACSF), bispectrum coefficients, smooth overlap of atomic positions (SOAP), moment tensors, classical force‐field‐inspired descriptors (CFID), etc. They benefit from the locality of target properties, e.g., energy can be divided into atomic energy.…”

Section: Featurizationmentioning

confidence: 99%

A Critical Review of Machine Learning of Energy Materials

Chen

Zuo

et al. 2020

Advanced Energy Materials

398

281

View full text Add to dashboard Cite

Machine learning (ML) is rapidly revolutionizing many fields and is starting to change landscapes for physics and chemistry. With its ability to solve complex tasks autonomously, ML is being exploited as a radically new way to help find material correlations, understand materials chemistry, and accelerate the discovery of materials. Here, an in‐depth review of the application of ML to energy materials, including rechargeable alkali‐ion batteries, photovoltaics, catalysts, thermoelectrics, piezoelectrics, and superconductors, is presented. A conceptual framework is first provided for ML in materials science, with a broad overview of different ML techniques as well as best practices. This is followed by a critical discussion of how ML is applied in energy materials. This review is concluded with the perspectives on major challenges and opportunities in this exciting field.

show abstract

“…5, the absolute error δ ABS of these ML force fields falls within 0.02 − 0.09 eV/Å in the whole range of force magnitude. This respectable level of error is equivalent or better than those of other contemporary ML force fields, e.g., ≃0.1 eV/Å for bulk Si, 25 ≃0.2 eV/Å for Si n clusters, 19 and ≳0.04 eV/Å for W. 18 Next, we discuss the applicability of the AGNI force fields within MD simulations, especially pertaining to our ability to obtain total potential energies by appropriate integration of the atomic forces along a MD trajectory, and the stability of such simulations with respect to total energy conservation. In fact, the force field of class (I) created for Al (employing V ′ i;α ) has been successfully used for a variety of MD simulations.…”

Section: Fingerprintingmentioning

confidence: 69%

A universal strategy for the creation of machine learning-based atomistic force fields

et al. 2017

View full text Add to dashboard Cite

Emerging machine learning (ML)-based approaches provide powerful and novel tools to study a variety of physical and chemical problems. In this contribution, we outline a universal strategy to create ML-based atomistic force fields, which can be used to perform high-fidelity molecular dynamics simulations. This scheme involves (1) preparing a big reference dataset of atomic environments and forces with sufficiently low noise, e.g., using density functional theory or higher-level methods, (2) utilizing a generalizable class of structural fingerprints for representing atomic environments, (3) optimally selecting diverse and non-redundant training datasets from the reference data, and (4) proposing various learning approaches to predict atomic forces directly (and rapidly) from atomic configurations. From the atomistic forces, accurate potential energies can then be obtained by appropriate integration along a reaction coordinate or along a molecular dynamics trajectory. Based on this strategy, we have created model ML force fields for six elemental bulk solids, including Al, Cu, Ti, W, Si, and C, and show that all of them can reach chemical accuracy. The proposed procedure is general and universal, in that it can potentially be used to generate ML force fields for any material using the same unified workflow with little human intervention. Moreover, the force fields can be systematically improved by adding new training data progressively to represent atomic environments not encountered previously.

show abstract

Moment Tensor Potentials: A Class of Systematically Improvable Interatomic Potentials

Cited by 963 publications

References 27 publications

Machine learning based interatomic potential for amorphous carbon

Machine learning based interatomic potential for amorphous carbon

A Critical Review of Machine Learning of Energy Materials

A universal strategy for the creation of machine learning-based atomistic force fields

Contact Info

Product

Resources

About