Machine learning for high-entropy alloys: Progress, challenges and opportunities
High-entropy alloys (HEAs) have attracted extensive interest due to their exceptional
mechanical properties and the vast compositional space for new HEAs. However …
mechanical properties and the vast compositional space for new HEAs. However …
Recent advances and applications of machine learning in solid-state materials science
One of the most exciting tools that have entered the material science toolbox in recent years
is machine learning. This collection of statistical methods has already proved to be capable …
is machine learning. This collection of statistical methods has already proved to be capable …
Machine-learning interatomic potentials for materials science
Y Mishin - Acta Materialia, 2021 - Elsevier
Large-scale atomistic computer simulations of materials rely on interatomic potentials
providing computationally efficient predictions of energy and Newtonian forces. Traditional …
providing computationally efficient predictions of energy and Newtonian forces. Traditional …
Machine learning for interatomic potential models
T Mueller, A Hernandez, C Wang - The Journal of chemical physics, 2020 - pubs.aip.org
The use of supervised machine learning to develop fast and accurate interatomic potential
models is transforming molecular and materials research by greatly accelerating atomic …
models is transforming molecular and materials research by greatly accelerating atomic …
Machine learning a general-purpose interatomic potential for silicon
The success of first-principles electronic-structure calculation for predictive modeling in
chemistry, solid-state physics, and materials science is constrained by the limitations on …
chemistry, solid-state physics, and materials science is constrained by the limitations on …
The TensorMol-0.1 model chemistry: a neural network augmented with long-range physics
Traditional force fields cannot model chemical reactivity, and suffer from low generality
without re-fitting. Neural network potentials promise to address these problems, offering …
without re-fitting. Neural network potentials promise to address these problems, offering …
Automatic selection of atomic fingerprints and reference configurations for machine-learning potentials
Machine learning of atomic-scale properties is revolutionizing molecular modeling, making it
possible to evaluate inter-atomic potentials with first-principles accuracy, at a fraction of the …
possible to evaluate inter-atomic potentials with first-principles accuracy, at a fraction of the …
Machine-learning and high-throughput studies for high-entropy materials
The combination of multiple-principal element materials, known as high-entropy materials
(HEMs), expands the multi-dimensional compositional space to gigantic stoichiometry. It is …
(HEMs), expands the multi-dimensional compositional space to gigantic stoichiometry. It is …
wACSF—Weighted atom-centered symmetry functions as descriptors in machine learning potentials
M Gastegger, L Schwiedrzik, M Bittermann… - The Journal of …, 2018 - pubs.aip.org
We introduce weighted atom-centered symmetry functions (wACSFs) as descriptors of a
chemical system's geometry for use in the prediction of chemical properties such as …
chemical system's geometry for use in the prediction of chemical properties such as …
Incompleteness of atomic structure representations
Many-body descriptors are widely used to represent atomic environments in the construction
of machine-learned interatomic potentials and more broadly for fitting, classification, and …
of machine-learned interatomic potentials and more broadly for fitting, classification, and …