English
Related papers

Related papers: From GAP to ACE to MACE

200 papers

We present a swift walk-through of our recent work that uses machine learning to fit interatomic potentials based on quantum mechanical data. We describe our Gaussian Approximation Potentials (GAP) framework, discussing a variety of…

Materials Science · Physics 2020-02-06 Albert P. Bartók , Gábor Csányi

Machine learning interatomic potentials are revolutionizing large-scale, accurate atomistic modelling in material science and chemistry. Many potentials use atomic cluster expansion or equivariant message passing frameworks. Such frameworks…

Computational Physics · Physics 2024-07-31 Bingqing Cheng

Foundational machine learning interatomic potentials that can accurately and efficiently model a vast range of materials are critical for accelerating atomistic discovery. We introduce universal potentials based on the graph atomic cluster…

Materials Science · Physics 2026-01-06 Yury Lysogorskiy , Anton Bochkarev , Ralf Drautz

Gaussian Approximation Potentials are a class of Machine Learned Interatomic Potentials routinely used to model materials and molecular systems on the atomic scale. The software implementation provides the means for both fitting models…

We present a general-purpose parameterization of the atomic cluster expansion (ACE) for magnesium. The ACE shows outstanding transferability over a broad range of atomic environments and captures physical properties of bulk as well as…

Materials Science · Physics 2023-05-08 Eslam Ibrahim , Yury Lysogorskiy , Matous Mrovec , Ralf Drautz

Machine learning (ML) has become widely used in the development of interatomic potentials for molecular dynamics simulations. However, most ML potentials are still much slower than classical interatomic potentials and are usually trained…

Materials Science · Physics 2024-08-29 Aslak Fellman , Jesper Byggmästar , Fredric Granberg , Kai Nordlund , Flyura Djurabekova

We introduce a Gaussian approximation potential (GAP) for atomistic simulations of liquid and amorphous elemental carbon. Based on a machine-learning representation of the density-functional theory (DFT) potential-energy surface, such…

Materials Science · Physics 2017-03-08 Volker L. Deringer , Gábor Csányi

The Gaussian approximation potential (GAP) is an accurate machine-learning interatomic potential that was recently extended to include the description of radiation effects. In this study, we seek to validate a faster version of GAP, known…

Materials Science · Physics 2023-06-02 Mikko Koskenniemi , Jesper Byggmästar , Kai Nordlund , Flyura Djurabekova

Machine-learned interatomic potentials enable large systems to be simulated for long time scales at near ab-initio accuracy. This accuracy is achieved by fitting extremely flexible model architectures to high quality reference data. In…

Machine learning interatomic potentials (MLIPs) have massively changed the field of atomistic modeling. They enable the accuracy of density functional theory in large-scale simulations while being nearly as fast as classical interatomic…

Materials Science · Physics 2025-12-03 Niklas Leimeroth , Linus C. Erhard , Karsten Albe , Jochen Rohrer

Machine-learning-based interatomic potentials enable accurate materials simulations on extended time- and lengthscales. ML potentials based on the Atomic Cluster Expansion (ACE) framework have recently shown promising performance for this…

Computational Physics · Physics 2024-08-02 Daniel F. Thomas du Toit , Yuxing Zhou , Volker L. Deringer

The Atomic Cluster Expansion (ACE) [R. Drautz, Phys. Rev. B, 99:014104 (2019)] provides a systematically improvable, universal descriptor for the environment of an atom that is invariant to permutation, translation and rotation. ACE is…

Computational Physics · Physics 2023-08-15 Christoph Ortner

Traditionally, interatomic potentials assume local bond formation supplemented by long-range electrostatic interactions when necessary. This ignores intermediate range multi-atom interactions that arise from the relaxation of the electronic…

Materials Science · Physics 2022-11-07 Anton Bochkarev , Yury Lysogorskiy , Christoph Ortner , Gábor Csányi , Ralf Drautz

Phase change materials such as Ge$_{2}$Sb$_{2}$Te$_{5}$ (GST) are ideal candidates for next-generation, non-volatile, solid-state memory due to the ability to retain binary data in the amorphous and crystal phases, and rapidly transition…

Materials Science · Physics 2024-11-14 Owen R. Dunton , Tom Arbaugh , Francis W. Starr

We present an accurate machine learning (ML) model for atomistic simulations of carbon, constructed using the Gaussian approximation potential (GAP) methodology. The potential, named GAP-20, describes the properties of the bulk crystalline…

Computational Physics · Physics 2020-08-26 Patrick Rowe , Volker L Deringer , Piero Gasparotto , Gábor Csányi , Angelos Michaelides

Machine learning driven interatomic potentials, including Gaussian approximation potential (GAP) models, are emerging tools for atomistic simulations. Here, we address the methodological question of how one can fit GAP models that…

Materials Science · Physics 2020-08-20 Janine George , Geoffroy Hautier , Albert P. Bartók , Gábor Csányi , Volker L. Deringer

The atomic cluster expansion (ACE) was proposed recently as a new class of data-driven interatomic potentials with a formally complete basis set. Since the development of any interatomic potential requires a careful selection of training…

Materials Science · Physics 2022-12-20 Yury Lysogorskiy , Anton Bochkarev , Matous Mrovec , Ralf Drautz

We demonstrate how machine-learning based interatomic potentials can be used to model guest atoms in host structures. Specifically, we generate Gaussian approximation potential (GAP) models for the interaction of lithium atoms with…

Machine learning potentials have revolutionised the field of atomistic simulations in recent years and are becoming a mainstay in the toolbox of computational scientists. This paper aims to provide an overview and introduction into machine…

Chemical Physics · Physics 2024-10-02 Fabian L. Thiemann , Niamh O'Neill , Venkat Kapil , Angelos Michaelides , Christoph Schran

Using the maximum entropy method, we derive the "adaptive cluster expansion" (ACE), which can be trained to estimate probability density functions in high dimensional spaces. The main advantage of ACE over other Bayesian networks is its…

Neural and Evolutionary Computing · Computer Science 2007-05-23 Stephen Luttrell
‹ Prev 1 2 3 10 Next ›