Fast general two- and three-body interatomic potential

Pozdnyakov, Sergey; Oganov, Artem R.; Mazitov, Arslan B.; Kruglov, Ivan A.; Mazhnik, Efim

doi:10.1103/physrevb.107.125160

Cited by 4 publications

(3 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…GAs are favorable for dataset generation as they contribute to greater dataset diversity, 66,67 providing a more complete representation of the PES. Importantly, GAs are free from biases, such as physical intuition, which may be present in approaches like AIMD sampling.…”

Section: Training Datamentioning

confidence: 99%

A Genetic Algorithm Trained Machine-Learned Interatomic Potential for the Silicon–Carbon System

MacIsaac,

Bavdekar,

Spearot

et al. 2024

J. Phys. Chem. C

View full text Add to dashboard Cite

A linear regression-based machine learned interatomic potential (MLIP) was developed for the silicon−carbon system. The MLIP was predominantly trained on structures discovered through a genetic algorithm, encompassing the entire silicon−carbon composition space, and uses as its foundation the Ultra-Fast Force Fields (UF 3 ) formulation. To improve MLIP performance, the learning algorithm was modified to include higher spline interpolation resolution in regions with large potential energy surface curvature. The developed MLIP demonstrates exceptional predictive performance, accurately estimating energies and forces for structures across the silicon−carbon composition and configuration space. The MLIP predicts structural, energetic, and elastic properties of silicon carbide (SiC) with high precision and captures fundamental volume-pressure and volumetemperature relationships. Uniquely, this silicon−carbon MLIP is adept at modeling complex high-temperature phenomena, including the peritectic decomposition of SiC and carbon dimer formation during SiC surface reconstruction, which cannot be captured with prior classical interatomic potentials for this material.

show abstract

Section: Training Datamentioning

confidence: 99%

A Genetic Algorithm Trained Machine-Learned Interatomic Potential for the Silicon–Carbon System

MacIsaac,

Bavdekar,

Spearot

et al. 2024

J. Phys. Chem. C

View full text Add to dashboard Cite

show abstract

“…In the context of MLPs, nonlinear kernel-based MLPs have been trained and subsequently projected onto a spline basis, yielding a linear model 28 . Similar to this work, the general two-and three-body potential approach employs a quadratic spline basis set, exceeding MTPs in speed when trained on the same data 29 . Polynomial symmetry functions improve over Behler-Parrinello symmetry functions 30 in speed and accuracy by introducing compact support 31 .…”

Section: Introductionmentioning

confidence: 96%

Ultra-fast interpretable machine-learning potentials

Xie,

Rupp,

Hennig

2023

npj Comput Mater

View full text Add to dashboard Cite

All-atom dynamics simulations are an indispensable quantitative tool in physics, chemistry, and materials science, but large systems and long simulation times remain challenging due to the trade-off between computational efficiency and predictive accuracy. To address this challenge, we combine effective two- and three-body potentials in a cubic B-spline basis with regularized linear regression to obtain machine-learning potentials that are physically interpretable, sufficiently accurate for applications, as fast as the fastest traditional empirical potentials, and two to four orders of magnitude faster than state-of-the-art machine-learning potentials. For data from empirical potentials, we demonstrate the exact retrieval of the potential. For data from density functional theory, the predicted energies, forces, and derived properties, including phonon spectra, elastic constants, and melting points, closely match those of the reference method. The introduced potentials might contribute towards accurate all-atom dynamics simulations of large atomistic systems over long-time scales.

show abstract

“…Ab initio molecular dynamics (AIMD), albeit with high accuracy, struggle in terms of the accessible time and length scales. Although machine-learning potentials (MLPs) 29 – 40 can significantly speed up MD simulations while retaining first-principles accuracy, exploring the time scales over which the β − λ phase transition occurs still represents a challenge. By contrast, advanced sampling techniques such as metadynamics 41 – 43 allow for efficient sampling of the PES of interest and therefore have been successfully used to study barrier-crossing rare events 10 – 12 , 44 – 49 .…”

Section: Introductionmentioning

confidence: 99%

Layer-by-layer phase transformation in Ti3O5 revealed by machine-learning molecular dynamics simulations

Liu,

Wang,

et al. 2024

Nat Commun

View full text Add to dashboard Cite

Reconstructive phase transitions involving breaking and reconstruction of primary chemical bonds are ubiquitous and important for many technological applications. In contrast to displacive phase transitions, the dynamics of reconstructive phase transitions are usually slow due to the large energy barrier. Nevertheless, the reconstructive phase transformation from β- to λ-Ti3O5 exhibits an ultrafast and reversible behavior. Despite extensive studies, the underlying microscopic mechanism remains unclear. Here, we discover a kinetically favorable in-plane nucleated layer-by-layer transformation mechanism through metadynamics and large-scale molecular dynamics simulations. This is enabled by developing an efficient machine learning potential with near first-principles accuracy through an on-the-fly active learning method and an advanced sampling technique. Our results reveal that the β−λ phase transformation initiates with the formation of two-dimensional nuclei in the ab-plane and then proceeds layer-by-layer through a multistep barrier-lowering kinetic process via intermediate metastable phases. Our work not only provides important insight into the ultrafast and reversible nature of the β−λ transition, but also presents useful strategies and methods for tackling other complex structural phase transitions.

show abstract

Fast general two- and three-body interatomic potential

Cited by 4 publications

References 62 publications

A Genetic Algorithm Trained Machine-Learned Interatomic Potential for the Silicon–Carbon System

A Genetic Algorithm Trained Machine-Learned Interatomic Potential for the Silicon–Carbon System

Ultra-fast interpretable machine-learning potentials

Layer-by-layer phase transformation in Ti3O5 revealed by machine-learning molecular dynamics simulations

Contact Info

Product

Resources

About