Machine-learned interatomic potentials for alloys and alloy phase diagrams

  title={Machine-learned interatomic potentials for alloys and alloy phase diagrams},
  author={Conrad W. Rosenbrock and Konstantin Gubaev and Alexander V. Shapeev and L{\'i}via B. P{\'a}rtay and Noam Bernstein and G{\'a}bor Cs{\'a}nyi and Gus L. W. Hart},
  journal={npj Computational Materials},
We introduce machine-learned potentials for Ag-Pd to describe the energy of alloy configurations over a wide range of compositions. We compare two different approaches. Moment tensor potentials (MTPs) are polynomial-like functions of interatomic distances and angles. The Gaussian approximation potential (GAP) framework uses kernel regression, and we use the smooth overlap of atomic position (SOAP) representation of atomic neighborhoods that consist of a complete set of rotational and… 
Spinel nitride solid solutions: charting properties in the configurational space with explainable machine learning
An approach to accelerate ab initio predictions via a combination of density functional theory and machine learning is presented, using the cubic spinel nitride GeSn 2 N 4 as a case study, exploring how formation energy and electronic bandgap are affected by configurational variations.
Machine learned interatomic potentials using random features
The proposed model approximates the energy/forces using a linear combination of random features, thereby enabling fast parameter estimation by solving a linear least-squares problem and addressing scalability issues encountered in this class of machine learning problems.
Bandgap Engineering in the Configurational Space of Solid Solutions via Machine Learning: (Mg,Zn)O Case Study
It is shown here that a simple descriptor based on the Coulomb matrix eigenspectrum clearly outperforms the cluster expansion for both total energy and bandgap energy predictions in the configurational space of a MgO–ZnO solid solution, a prototypical oxide alloy for bandgap engineering.
Taking materials dynamics to new extremes using machine learning interatomic potentials
Understanding materials dynamics under extreme conditions of pressure, temperature, and strain rate is a scientific quest that spans nearly a century. Atomic simulations have had a considerable
Discovering New Superalloys Using Machine-Learned Interatomic Potentials
It is more important today than ever before to accelerate the discovery of new revolutionary materials. Advances in computing, transportation, spaceflight, and all other technology sectors are
Accurate large-scale simulations of siliceous zeolites by neural network potentials
The computational discovery and design of zeolites is a crucial part of the chemical industry. Finding highly accurate while computationally feasible protocol for identification of hypothetical
Efficient implementation of atom-density representations.
An implementation of librascal, whose modular design lends itself both to developing refinements to the density-based formalism and to rapid prototyping for new developments of rotationally equivariant atomistic representations, is presented.
Structure and Dynamics of Energy Materials from Machine Learning Simulations: A Topical Review
Energy materials featuring the capability to store and release chemical energy reversibly involve generally complex geometrical structures with multiple elements. It has been a great challenge to
Explicit Multi-element Extension of the Spectral Neighbor Analysis Potential for Chemically Complex Systems.
This work produces an interatomic potential for indium phosphide capable of capturing high-energy defects that result from radiation damage cascades and reproduces the relaxed defect formation energies with substantially greater accuracy than weighted-density SNAP.


Achieving DFT accuracy with a machine-learning interatomic potential: thermomechanics and defects in bcc ferromagnetic iron
We show that the Gaussian Approximation Potential machine learning framework can describe complex magnetic potential energy surfaces, taking ferromagnetic iron as a paradigmatic challenging case. The
Understanding the thermal properties of amorphous solids using machine-learning-based interatomic potentials
Abstract Understanding the thermal properties of disordered systems is of fundamental importance for condensed matter physics - and for practical applications as well. While quantities such as the
Comparing molecules and solids across structural and alchemical space.
This work discusses how one can combine such local descriptors using a regularized entropy match (REMatch) approach to describe the similarity of both whole molecular and bulk periodic structures, introducing powerful metrics that enable the navigation of alchemical and structural complexities within a unified framework.
Regularised atomic body-ordered permutation-invariant polynomials for the construction of interatomic potentials
It is shown that the low dimensionality combined with careful regularisation actually leads to better transferability than the high dimensional, kernel based Gaussian Approximation Potential.
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 simulated length
Data-Driven Learning of Total and Local Energies in Elemental Boron.
This model readily provides atom-resolved, local energies and thus deepened insight into the frustrated β-rhombohedral boron structure, and opens the door for the efficient and automated generation of GAPs, and other machine-learning-based interatomic potentials, to suggest their usefulness as a tool for materials discovery.
On representing chemical environments
It is demonstrated that certain widely used descriptors that initially look quite different are specific cases of a general approach, in which a finite set of basis functions with increasing angular wave numbers are used to expand the atomic neighborhood density function.
Atomic permutationally invariant polynomials for fitting molecular force fields
Fitted to a combined training set of short linear alkanes, the accuracy of the aPIP force field still significantly exceeds what can be expected from classical empirical force fields, while retaining reasonable transferability to both configurations far from the training set and to new molecules.
Data-driven learning and prediction of inorganic crystal structures.
This paper presents a GAP-RSS interatomic potential model for elemental phosphorus, which identifies and correctly "learns" the orthorhombic black phosphorus structure without prior knowledge of any crystalline allotropes.