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

Goryaeva, Alexandra M.; Dérès, Julien; Lapointe, Clovis; Grigorev, Petr; Swinburne, Thomas D.; Kermode, James R.; Ventelon, Lisa; Baima, Jacopo; Marinica, Mihai-Cosmin

doi:10.1103/physrevmaterials.5.103803

Cited by 32 publications

(49 citation statements)

References 167 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The MLIP methodology is moving gradually to address other complex problems, which recently also included the development of accurate interatomic potentials to study dislocation problems, point defects, and their clusters in certain materials (e.g., in bcc iron and tungsten [92]). While, to our best knowledge, no other work reported the development of MLIPs, and MTPs in particular, for the materials with phase transformations, recent attempts have been made in advancing algorithms for training MTPs on such materials as random alloys (e.g., MoNbTa medium-entropy alloys), which can be considered as a first step in simulating multicomponent systems with this methodology [93].…”

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

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

show abstract

“…The severe size and geometry limitations of DFT are also significant for the development of interatomic potentials, which has been revolutionised by the availability of high-dimensional regression algorithms from the machine learning (ML) community, designed to mitigate overfitting issues whilst retaining flexibility [32][33][34]. We refer the reader to a number of excellent recent reviews in this rapidly growing field [35][36][37][38][39], which has attracted explosive interest following the ability of state-of-the-art ML potentials [40][41][42][43][44][45][46][47][48][49][50][51][52] to achieve ab initio accuracy across a diverse configuration space. However, the extrapolation ability of these approaches remains a subject of intense interest [39,46], due in part to the requirement to train and validate only on small, periodic DFT simulations, whilst the desired applications typically operate on much longer time and length scales.…”

Section: Introductionmentioning

confidence: 99%

“…We refer the reader to a number of excellent recent reviews in this rapidly growing field [35][36][37][38][39], which has attracted explosive interest following the ability of state-of-the-art ML potentials [40][41][42][43][44][45][46][47][48][49][50][51][52] to achieve ab initio accuracy across a diverse configuration space. However, the extrapolation ability of these approaches remains a subject of intense interest [39,46], due in part to the requirement to train and validate only on small, periodic DFT simulations, whilst the desired applications typically operate on much longer time and length scales.…”

Section: Introductionmentioning

confidence: 99%

“…In this paper, we describe and apply a general method to simulate extended defects in hybrid, or QM/ML, simulations employing linear machine learning potentials [46].…”

Section: Introductionmentioning

confidence: 99%

“…Kernel methods can have theoretically infinite capacity, which is controlled during the refitting procedure by sparsification and providing the relevant information from the database [54]. However, this procedure requires special design of the database, some prior knowledge of relevant atomic configurations for a specific physical problems pointed up with the appropriate theoretical tools [46,58,59]. The present procedure is general and simply requires a linear ML potential with capacity larger than the minimum required for the assimilation of elastic properties.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Synergistic coupling in ab initio-machine learning simulations of dislocations

Grigorev¹,

Goryaeva²,

Marinica³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Ab initio simulations of dislocations are essential to build quantitative models of material strength, but the required system sizes are often at or beyond the limit of existing methods. Many important structures are thus missing in the training or validation of interatomic potentials, whilst studies of dislocation-defect interactions must mitigate the effect of strong periodic image interactions along the line direction. We show how these restrictions can be lifted through the use of linear machine learning potentials in hybrid simulations, where only a subset of atoms are governed by ab initio forces. The linear form is exploited in a constrained retraining procedure, qualitatively expanding the range of training structures for learning and giving precise matching of dislocation core structures, such that lines can cross the quantum/classical boundary. We apply our method to fully three dimensional studies of impurity segregation to edge and screw dislocations in tungsten. Our retrained potentials give systematically improved accuracy to QM/ML reference data and the three dimensional geometry allows for long-range relaxations that qualitatively change impurity-induced core reconstructions compared to simulations using short periodic supercells. More generally, the ability to treat arbitrary sub-regions of large scale simulations with ab initio accuracy opens a vast range of previously inaccessible extended defects to quantitative investigation.

show abstract

A deep learning interatomic potential suitable for simulating radiation damage in bulk tungsten

et al. 2023

View full text Add to dashboard Cite

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

Abstract: How to cite:Please refer to published version for the most recent bibliographic citation information.

Cited by 32 publications

References 167 publications

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

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

Synergistic coupling in ab initio-machine learning simulations of dislocations

A deep learning interatomic potential suitable for simulating radiation damage in bulk tungsten

Contact Info

Product

Resources

About