Sensitivity and dimensionality of atomic environment representations used for machine learning interatomic potentials

Onat, Berk; Ortner, Christoph; Kermode, James R.

doi:10.1063/5.0016005

Cited by 37 publications

(47 citation statements)

References 74 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, instead of using R 3N -dimensional description of the local atomic environments, one employs a space R D . The dimension of descriptor space commonly ranges from few tens to few thousands [15][16][17]. Most commonly, atomic descriptors encode the local geometry on neighboring atoms using the distances and/or angles between atoms [11,15,18], spectral analysis of local atomic environments [15,18] or a tensorial description of atomic coordinates [19,20].…”

Section: Introductionmentioning

confidence: 99%

Efficient and transferable machine learning potentials for the simulation of crystal defects in bcc Fe and W

Goryaeva

Dérès

Lapointe

et al. 2021

Phys. Rev. Materials

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Introductionmentioning

confidence: 99%

Efficient and transferable machine learning potentials for the simulation of crystal defects in bcc Fe and W

Goryaeva

Dérès

Lapointe

et al. 2021

Phys. Rev. Materials

Self Cite

View full text Add to dashboard Cite

show abstract

“…For example, in [68] polycrystalline structures with microstructure properties have been a subject of studies with machine learning and deep learning approaches, combined with multiscale analysis. The interest in machine learning tools for studies of martensitic phase transformations, typical for SMMs, has been growing significantly over recent years [69], and this direction of research has also included various approaches for developing interatomic potentials [70].…”

Section: Data-driven Approaches For Studying Materials With Shape Mem...mentioning

confidence: 99%

Machine Learning for Shape Memory Graphene Nanoribbons and Applications in Biomedical Engineering

León

Melnik

2022

Bioengineering

View full text Add to dashboard Cite

Shape memory materials have been playing an important role in a wide range of bioengineering applications. At the same time, recent developments of graphene-based nanostructures, such as nanoribbons, have demonstrated that, due to the unique properties of graphene, they can manifest superior electronic, thermal, mechanical, and optical characteristics ideally suited for their potential usage for the next generation of diagnostic devices, drug delivery systems, and other biomedical applications. One of the most intriguing parts of these new developments lies in the fact that certain types of such graphene nanoribbons can exhibit shape memory effects. In this paper, we apply machine learning tools to build an interatomic potential from DFT calculations for highly ordered graphene oxide nanoribbons, a material that had demonstrated shape memory effects with a recovery strain up to 14.5% for 2D layers. The graphene oxide layer can shrink to a metastable phase with lower constant lattice through the application of an electric field, and returns to the initial phase through an external mechanical force. The deformation leads to an electronic rearrangement and induces magnetization around the oxygen atoms. DFT calculations show no magnetization for sufficiently narrow nanoribbons, while the machine learning model can predict the suppression of the metastable phase for the same narrower nanoribbons. We can improve the prediction accuracy by analyzing only the evolution of the metastable phase, where no magnetization is found according to DFT calculations. The model developed here allows also us to study the evolution of the phases for wider nanoribbons, that would be computationally inaccessible through a pure DFT approach. Moreover, we extend our analysis to realistic systems that include vacancies and boron or nitrogen impurities at the oxygen atomic positions. Finally, we provide a brief overview of the current and potential applications of the materials exhibiting shape memory effects in bioengineering and biomedical fields, focusing on data-driven approaches with machine learning interatomic potentials.

show abstract

“…Representation of atomic structures entails quantifying local structural information in certain mathematical expressions, named descriptors or fingerprints [53] . In order to simulate large systems, the total energy is expressed as a linear combination of the sum of local energy contributions from all the atoms.…”

Section: Representations For Local Atomic Environmentsmentioning

confidence: 99%

“…The selection of D i is of great importance as it can affect the accuracy and efficiency of MLIPs. Several different representations have been proposed in the past decade [53,[56][57][58][59][60][61][62][63][64][65] , including the Gaussian function truncated forms [66] and the spherical harmonic function [62] . optimizations are also applied to select important structures for DFT calculations [52] .…”

Section: Representations For Local Atomic Environmentsmentioning

confidence: 99%

See 1 more Smart Citation

Taking materials dynamics to new extremes using machine learning interatomic potentials

Yang¹,

Zhao²,

Han³

et al. 2021

JMI

View full text Add to dashboard Cite

Understanding materials dynamics under extreme conditions of pressure, temperature, and strain rate is a scientific quest that spans nearly a century. Atomic simulations have had a considerable impact on this endeavor because of their ability to uncover materials' microstructure evolution and properties at the scale of the relevant physical phenomena. However, this is still a challenge for most materials as it requires modeling large atomic systems (up to millions of particles) with improved accuracy. In many cases, the availability of sufficiently accurate but efficient interatomic potentials has become a serious bottleneck for performing these simulations as traditional potentials fail to represent the multitude of bonding. A new class of potentials has emerged recently, based on a different paradigm from the traditional approach. The new potentials are constructed by machinelearning with a high degree of fidelity from quantum-mechanical calculations. In this review, a brief introduction to the central ideas underlying machine learning interatomic potentials is given. In particular, the coupling of machine learning models with domain knowledge to improve accuracy, computational efficiency, and interpretability is highlighted. Subsequently, we demonstrate the effectiveness of the domain knowledge-based approach in certain select problems related to the kinetic response of warm dense materials. It is hoped that this review will inspire further advances in the understanding of matter under extreme conditions.

show abstract

Sensitivity and dimensionality of atomic environment representations used for machine learning interatomic potentials

Abstract: Note: This paper is part of the JCP Special Topic on Machine Learning Meets Chemical Physics.

Cited by 37 publications

References 74 publications

Efficient and transferable machine learning potentials for the simulation of crystal defects in bcc Fe and W

Efficient and transferable machine learning potentials for the simulation of crystal defects in bcc Fe and W

Machine Learning for Shape Memory Graphene Nanoribbons and Applications in Biomedical Engineering

Taking materials dynamics to new extremes using machine learning interatomic potentials

Contact Info

Product

Resources

About