Modeling high-entropy transition metal alloys with alchemical compression

Lopanitsyna, Nataliya; Fraux, Guillaume; Springer, Maximilian A.; De, Sandip; Ceriotti, Michele

doi:10.1103/physrevmaterials.7.045802

Cited by 19 publications

(24 citation statements)

References 97 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The details of the reference DFT calculations and the structure of the ML model closely follow those used in a recent paper focused on bulk structures [53], which allows us to perform an insightful comparative study.…”

Section: Theory and Computational Detailsmentioning

confidence: 99%

“…The vacuum size for the surface slab calculations was set to 20 Å. Following the same reasoning as in [53], we performed the calculations without spin polarization. Even though it is possible to describe the magnetism within the spin density functional theory approximation (and even though this framework is often used by ML models that incorporate magnetic information), when dealing with such a broad set of transition-metal compounds it is likely that some element combinations require different approaches, such as DFT with Hubbard U and J corrections (DFT+U+J), and dynamical mean-field theory [60,61].…”

Section: First-principles Calculationsmentioning

confidence: 99%

“…For the sake of consistency between our previous work on bulk HEAs and our current work, we kept the model architecture unchanged. Here, we summarize the main ideas underlying the model, while for all the details, the reader is referred to the [53].…”

Section: Modelmentioning

confidence: 99%

“…In our previous work [53], we introduced a general-purpose machine-learning (ML) model for the study of HEAs with up to 25 transition metals in the composition (the HEA25-4-NN), as well as proposed an efficient approach to generate a training set for it. Based on the idea of a physically-motivated and interpretable alchemical contraction of the feature space [54], the model demonstrated very promising accuracy, robustness and transferability in terms of various bulk HEA simulation scenarios, which is even more remarkable in light of the difficulty in modeling even pure transition metals using MLIPs [55].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Surface segregation in high-entropy alloys from alchemical machine learning

Mazitov,

Springer,

Lopanitsyna

et al. 2024

J. Phys. Mater.

View full text Add to dashboard Cite

High-entropy alloys (HEAs), containing several metallic elements in near-equimolar proportions, have long been of interest for their unique mechanical properties. More recently, they have emerged as a promising platform for the development of novel heterogeneous catalysts, because of the large design space, and the synergistic effects between their components.In this work we use a machine-learning potential that can model simultaneously up to 25 transition metals to study the tendency of different elements to segregate at the surface of a HEA.We use as a starting point a potential that was previously developed using exclusively crystalline bulk phases, and show that, thanks to the physically-inspired functional form of the model, adding a much smaller number of defective configurations makes it capable of describing surface phenomena.We then present several computational studies of surface segregation, including both a simulation of a 25-element alloy, that provides a rough estimate of the relative surface propensity of the various elements, and targeted studies of CoCrFeMnNi and IrFeCoNiCu, which provide further validation of the model, and insights to guide the modeling and design of alloys for heterogeneous catalysis.

show abstract

Section: Theory and Computational Detailsmentioning

confidence: 99%

Section: First-principles Calculationsmentioning

confidence: 99%

Section: Modelmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Surface segregation in high-entropy alloys from alchemical machine learning

Mazitov,

Springer,

Lopanitsyna

et al. 2024

J. Phys. Mater.

View full text Add to dashboard Cite

show abstract

“…Local decomposition allows the models to be easily applied to systems of vastly different length scales (training on small cells and predicting for much larger ones), , underpinning their widespread usage. This is especially the case for ML interatomic potentials, ,− which allow accessing longer length and time scales in simulations with a linear-scaling cost.…”

Section: Introductionmentioning

confidence: 99%

Robustness of Local Predictions in Atomistic Machine Learning Models

Chong,

Grasselli,

Ben Mahmoud

et al. 2023

J. Chem. Theory Comput.

Self Cite

View full text Add to dashboard Cite

Machine learning (ML) models for molecules and materials commonly rely on a decomposition of the global target quantity into local, atom-centered contributions. This approach is convenient from a computational perspective, enabling large-scale ML-driven simulations with a linear-scaling cost and also allows for the identification and posthoc interpretation of contributions from individual chemical environments and motifs to complicated macroscopic properties. However, even though practical justifications exist for the local decomposition, only the global quantity is rigorously defined. Thus, when the atom-centered contributions are used, their sensitivity to the training strategy or the model architecture should be carefully considered. To this end, we introduce a quantitative metric, which we call the local prediction rigidity (LPR), that allows one to assess how robust the locally decomposed predictions of ML models are. We investigate the dependence of the LPR on the aspects of model training, particularly the composition of training data set, for a range of different problems from simple toy models to real chemical systems. We present strategies to systematically enhance the LPR, which can be used to improve the robustness, interpretability, and transferability of atomistic ML models.

show abstract

Systematic assessment of various universal machine‐learning interatomic potentials

Yu,

Giantomassi,

Materzanini

et al. 2024

Materials Genome Engineering Advances

View full text Add to dashboard Cite

Machine‐learning interatomic potentials have revolutionized materials modeling at the atomic scale. Thanks to these, it is now indeed possible to perform simulations of ab initio quality over very large time and length scales. More recently, various universal machine‐learning models have been proposed as an out‐of‐box approach avoiding the need to train and validate specific potentials for each particular material of interest. In this paper, we review and evaluate four different universal machine‐learning interatomic potentials (uMLIPs), all based on graph neural network architectures which have demonstrated transferability from one chemical system to another. The evaluation procedure relies on data both from a recent verification study of density‐functional‐theory implementations and from the Materials Project. Through this comprehensive evaluation, we aim to provide guidance to materials scientists in selecting suitable models for their specific research problems, offer recommendations for model selection and optimization, and stimulate discussion on potential areas for improvement in current machine‐learning methodologies in materials science.

show abstract

Modeling high-entropy transition metal alloys with alchemical compression

Cited by 19 publications

References 97 publications

Surface segregation in high-entropy alloys from alchemical machine learning

Surface segregation in high-entropy alloys from alchemical machine learning

Robustness of Local Predictions in Atomistic Machine Learning Models

Systematic assessment of various universal machine‐learning interatomic potentials

Contact Info

Product

Resources

About