Accelerating crystal structure prediction by machine-learning interatomic potentials with active learning

Podryabinkin, Evgeny V.; Tikhonov, E. V.; Shapeev, Alexander V.; Oganov, Artem R.

doi:10.1103/physrevb.99.064114

Cited by 293 publications

(242 citation statements)

References 43 publications

Supporting

Mentioning

229

Contrasting

Unclassified

Order By: Relevance

“…For theoretical studies, relatively large composite molecular models have to be developed to address this aspect, which are extensively computationally demanding to be studied by the DFT-based simulations. To address the stability under the water, we do believe that classical molecular dynamics simulations by using the machine learning potentials [54][55][56] may show a great prospect.…”

Section: Resultsmentioning

confidence: 99%

Two-Dimensional SiP, SiAs, GeP and GeAs as Promising Candidates for Photocatalytic Applications

et al. 2019

View full text Add to dashboard Cite

Group IV–V-type layered materials, such as SiP, SiAs, GeP and GeAs, are among the most attractive two-dimensional (2D) materials that exhibit anisotropic mechanical, optical and transport properties. In this short communication, we conducted density functional theory simulations to explore the prospect of SiP, SiAs, GeP and GeAs nanosheets for the water-splitting application. The semiconducting gaps of stress-free SiP, SiAs, GeP and GeAs monolayers were estimated to be 2.59, 2.34, 2.30 and 2.07 eV, respectively, which are within the desirable ranges for the water splitting. Moreover, all the considered nanomaterials were found to yield optical absorption in the visible spectrum, which is a critical feature for the employment in the solar water splitting systems. Our results furthermore confirm that the valence and conduction band edge positions in SiP, SiAs, GeP and GeAs monolayers also satisfy the requirements for the water splitting. Our results highlight the promising photocatalytic characteristics of SiP, SiAs, GeP and GeAs nanosheets for the application in solar water splitting and design of advanced hydrogen fuel cells.

show abstract

Section: Resultsmentioning

confidence: 99%

Two-Dimensional SiP, SiAs, GeP and GeAs as Promising Candidates for Photocatalytic Applications

et al. 2019

View full text Add to dashboard Cite

show abstract

“…We demonstrate the method for boron, one of the most structurally complex elements 57 . With the exception of a high-pressure α-Ga type phase, all relevant boron allotropes contain B 12 icosahedra as the defining structural unit 57 with DFT 58-61 and, more recently, with ML potentials for bulk allotropes 18,20 and gas-phase clusters 22 . Our previous work showed how the PES for boron can be fitted in a ML framework 18 , leading to the first interatomic potential able to describe the different allotropes.…”

Section: A Unified Framework For Exploring and Fitting Structural Spacementioning

confidence: 99%

De novo exploration and self-guided learning of potential-energy surfaces

2019

View full text Add to dashboard Cite

Interatomic potential models based on machine learning (ML) are rapidly developing as tools for materials simulations. However, because of their flexibility, they require large fitting databases that are normally created with substantial manual selection and tuning of reference configurations. Here, we show that ML potentials can be built in a largely automated fashion, exploring and fitting potential-energy surfaces from the beginning (de novo) within one and the same protocol. The key enabling step is the use of a configuration-averaged kernel metric that allows one to select the few most relevant structures at each step. The resulting potentials are accurate and robust for the wide range of configurations that occur during structure searching, despite only requiring a relatively small number of single-point DFT calculations on small unit cells. We apply the method to materials with diverse chemical nature and coordination environments, marking a milestone toward the more routine application of ML potentials in physics, chemistry, and materials science.

show abstract

“…This iterative training approach was suggested early on already, in the creation of the first ML potentials for silicon, [40] sodium, [41] and for the phase-change material GeTe, [42] the latter of which we will discuss in Section 4.1. [46,[48][49][50] Such approaches hold the long-term promise of discovering new materials on larger length scales than would be accessible to current state-of-the-art methods. [43] A more pressing challenge concerns the sampling of general PESs, which is needed to ensure wide applicability of ML potentials-combining robustness and flexibility in the high-energy regions with sufficient accuracy in the low-energy regions (that is, for the stable and metastable crystal structures).…”

Section: Ingredient 1: Reference Databasesmentioning

confidence: 99%

Machine Learning Interatomic Potentials as Emerging Tools for Materials Science

2019

View full text Add to dashboard Cite

In pursuit of this goal, atomic-scale computer simulations have long been a central approach, and two major families of methods are routinely used today. On the one hand, there are quantum-mechanical simulations, in which we solve Schrödinger's equation for the electronic structure of molecular and periodic systems, most widely based on density-functional theory (DFT). [6][7][8] These methods provide (largely) reliable results for structural models of materials that normally contain a few tens or hundreds of atoms. State-of-the-art DFT methods can be applied to many material classes, and they are increasingly used for high-throughput screening and "in silico" (computer-based) design of materials: new compositions and previously unknown structures have been identified in DFT searches and subsequently experimentally realized. [5,[9][10][11] On the other hand, interatomic potential models ("force fields"), parameterizing interactions between atoms with (relatively) simple functional forms, are widely used in materials science to describe matter in molecular dynamics (MD) simulations. These simulations grant access to larger time and length scales, reaching system sizes of up to hundreds of thousands of atoms. [12] In parameterizing these potentials, a certain physical form of the atomic interactions is assumed, often in terms of bond distances, angles, and so on, and physical properties such as equilibrium lattice parameters or elastic constants enter the fitting of the potential. For this reason, such potentials are often called "empirical." They are several orders of magnitude faster than DFT, but necessarily less accurate and less easily transferable.In this Progress Report, we highlight recent developments in "machine-learned" interatomic potentials, which represent a rapidly growing field that promises to do away with the aforementioned trade-offs. Over the last year, there has been a surge of interest in machine learning (ML) methodology: part of it is due to the dramatic growth of ML throughout the scientific disciplines, and part of it is due to tangible success stories of ML-based interatomic potentials that are now beginning to emerge. We will argue that this is an exciting development with very practical implications, currently on the verge of moving from a somewhat specialized new technology to everyday applicability, poised to enhance and complement the communities' existing strengths in computational materials modeling. We will show selected applications of ML potentials to problems in materials science, discuss the current limitations (and possible pitfalls), and outline what we expect to be interesting directions for the development of the field in the coming years.Atomic-scale modeling and understanding of materials have made remarkable progress, but they are still fundamentally limited by the large computational cost of explicit electronic-structure methods such as density-functional theory. This Progress Report shows how machine learning (ML) is currently enabling a new degree of realism in materi...

show abstract

Accelerating crystal structure prediction by machine-learning interatomic potentials with active learning

Cited by 293 publications

References 43 publications

Two-Dimensional SiP, SiAs, GeP and GeAs as Promising Candidates for Photocatalytic Applications

Two-Dimensional SiP, SiAs, GeP and GeAs as Promising Candidates for Photocatalytic Applications

De novo exploration and self-guided learning of potential-energy surfaces

Machine Learning Interatomic Potentials as Emerging Tools for Materials Science

Contact Info

Product

Resources

About