Machine-Learning Interatomic Potentials for Materials Science (2021-02-11T00:00:00.000000Z)

TL;DR

The current status of the interatomic potential field is reviewed, comparing the strengths and weaknesses of the traditional and ML potentials and a third class of potentials is introduced, in which an ML model is coupled with a physics-based potential to improve the transferability to unknown atomic environments.

Authors

Y. Mishin

1 papers

TL;DR

Authors

References152 items

Development of a physically-informed neural network interatomic potential for tantalum

Emerging materials intelligence ecosystems propelled by machine learning

Machine learning-accelerated quantum mechanics-based atomistic simulations for industrial applications

Machine learning for metallurgy I. A neural-network potential for Al-Cu

Machine learning for metallurgy II. A neural-network potential for magnesium

Development of a general-purpose machine-learning interatomic potential for aluminum by the physically informed neural network method

Machine-learned interatomic potentials by active learning: amorphous and liquid hafnium dioxide

The MLIP package: moment tensor potentials with MPI and active learning

Machine Learning in Materials Discovery: Confirmed Predictions and Their Underlying Approaches

An accurate and transferable machine learning potential for carbon.

Review of the Frenkel–Ladd technique for computing free energies of crystalline solids

Sensitivity and dimensionality of atomic environment representations used for machine learning interatomic potentials.

MAISE: Construction of neural network interatomic models and evolutionary structure optimization

Explicit Multi-element Extension of the Spectral Neighbor Analysis Potential for Chemically Complex Systems.

Roadmap on multiscale materials modeling

Scientific AI in materials science: a path to a sustainable and scalable paradigm

Atomic cluster expansion of scalar, vectorial, and tensorial properties including magnetism and charge transfer

Optimization and validation of a deep learning CuZr atomistic potential: Robust applications for crystalline and amorphous phases with near-DFT accuracy.

Efficient training of ANN potentials by including atomic forces via Taylor expansion and application to water and a transition-metal oxide

Machine learning for interatomic potential models.

On the Completeness of Atomic Structure Representations

Anharmonic thermodynamics of vacancies using a neural network potential

Machine Learning Interatomic Potentials as Emerging Tools for Materials Science

Efficient Global Structure Optimization with a Machine-Learned Surrogate Model.

Revealing the intrinsic nature of the mid-gap defects in amorphous Ge2Sb2Te5

Continuous and optimally complete description of chemical environments using Spherical Bessel descriptors

A Performance and Cost Assessment of Machine Learning Interatomic Potentials.

Machine-learned interatomic potentials for alloys and alloy phase diagrams

General Atomic Neighborhood Fingerprint for Machine Learning-Based Methods

MatCALO: Knowledge-enabled machine learning in materials science

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

Machine-learning-based interatomic potential for phonon transport in perfect crystalline Si and crystalline Si with vacancies

Structure prediction drives materials discovery

On-the-fly machine learning force field generation: Application to melting points

Multitribe evolutionary search for stable Cu-Pd-Ag nanoparticles using neural network models.

DScribe: Library of Descriptors for Machine Learning in Materials Science

Enabling QM-accurate simulation of dislocation motion in γ−Ni and α−Fe using a hybrid multiscale approach

New frontiers for the materials genome initiative

High-throughput calculations in the context of alloy design

Accelerating materials science with high-throughput computations and machine learning

Materials informatics: From the atomic-level to the continuum

PhysNet: A Neural Network for Predicting Energies, Forces, Dipole Moments, and Partial Charges.

Transferability of interatomic potentials for molybdenum and silicon

Atomic cluster expansion for accurate and transferable interatomic potentials

Group-theoretical high-order rotational invariants for structural representations: Application to linearized machine learning interatomic potential

Machine Learning Classical Interatomic Potentials for Molecular Dynamics from First-Principles Training Data

Machine learning in materials design and discovery: Examples from the present and suggestions for the future

Structural search for stable Mg-Ca alloys accelerated with a neural network interatomic model.

Active Learning of Uniformly Accurate Inter-atomic Potentials for Materials Simulation

Data-driven learning and prediction of inorganic crystal structures.

Machine-learned multi-system surrogate models for materials prediction

General machine-learning surrogate models for materials prediction

Modeling the Phase-Change Memory Material, Ge2Sb2Te5, with a Machine-Learned Interatomic Potential.

Improving accuracy of interatomic potentials: more physics or more data? A case study of silica

Physically informed artificial neural networks for atomistic modeling of materials

Atom-density representations for machine learning.

Accelerating high-throughput searches for new alloys with active learning of interatomic potentials

Quantum-accurate spectral neighbor analysis potential models for Ni-Mo binary alloys and fcc metals

Evaluating variability with atomistic simulations: the effect of potential and calculation methodology on the modeling of lattice and elastic constants

Machine Learning a General-Purpose Interatomic Potential for Silicon

Growth Mechanism and Origin of High sp^{3} Content in Tetrahedral Amorphous Carbon.

Automatic selection of atomic fingerprints and reference configurations for machine-learning potentials.

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

Constructing first-principles phase diagrams of amorphous LixSi using machine-learning-assisted sampling with an evolutionary algorithm.

Efficient nonparametric n -body force fields from machine learning

SchNet - A deep learning architecture for molecules and materials.

Neural network potential for Al-Mg-Si alloys

Data-Driven Learning of Total and Local Energies in Elemental Boron.

Non-covalent interactions across organic and biological subsets of chemical space: Physics-based potentials parametrized from machine learning.

Machine Learning and Materials Informatics: Recent Applications and Prospects

The atomic simulation environment-a Python library for working with atoms.

Accurate Force Field for Molybdenum by Machine Learning Large Materials Data

Efficient and accurate machine-learning interpolation of atomic energies in compositions with many species

Extracting Crystal Chemistry from Amorphous Carbon Structures

Atomicrex—a general purpose tool for the construction of atomic interaction models

Active learning of linearly parametrized interatomic potentials

Accurate interatomic force fields via machine learning with covariant kernels