Cartesian atomic moment machine learning interatomic potentials

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Wen, Mingjian, Huang, Wei-Fan, Dai, Jin, Adhikari, Santosh
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910925487865856
author Wen, Mingjian
Huang, Wei-Fan
Dai, Jin
Adhikari, Santosh
author_facet Wen, Mingjian
Huang, Wei-Fan
Dai, Jin
Adhikari, Santosh
contents Machine learning interatomic potentials (MLIPs) have substantially advanced atomistic simulations in materials science and chemistry by balancing accuracy and computational efficiency. While leading MLIPs rely on representing atomic environments using spherical tensors, Cartesian representations offer potential advantages in simplicity and efficiency. Here, we introduce the Cartesian Atomic Moment Potential (CAMP), an approach to building MLIPs entirely in Cartesian space. CAMP constructs atomic moment tensors from neighboring atoms and employs tensor products to incorporate higher body-order interactions, providing a complete description of local atomic environments. Integrated into a graph neural network (GNN) framework, CAMP enables physically motivated, systematically improvable potentials. The model demonstrates excellent performance across diverse systems, including periodic structures, small organic molecules, and two-dimensional materials, achieving accuracy, efficiency, and stability in molecular dynamics simulations that rival or surpass current leading models. CAMP provides a powerful tool for atomistic simulations to accelerate materials understanding and discovery.
format Preprint
id arxiv_https___arxiv_org_abs_2411_12096
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Cartesian atomic moment machine learning interatomic potentials
Wen, Mingjian
Huang, Wei-Fan
Dai, Jin
Adhikari, Santosh
Materials Science
Machine learning interatomic potentials (MLIPs) have substantially advanced atomistic simulations in materials science and chemistry by balancing accuracy and computational efficiency. While leading MLIPs rely on representing atomic environments using spherical tensors, Cartesian representations offer potential advantages in simplicity and efficiency. Here, we introduce the Cartesian Atomic Moment Potential (CAMP), an approach to building MLIPs entirely in Cartesian space. CAMP constructs atomic moment tensors from neighboring atoms and employs tensor products to incorporate higher body-order interactions, providing a complete description of local atomic environments. Integrated into a graph neural network (GNN) framework, CAMP enables physically motivated, systematically improvable potentials. The model demonstrates excellent performance across diverse systems, including periodic structures, small organic molecules, and two-dimensional materials, achieving accuracy, efficiency, and stability in molecular dynamics simulations that rival or surpass current leading models. CAMP provides a powerful tool for atomistic simulations to accelerate materials understanding and discovery.
title Cartesian atomic moment machine learning interatomic potentials
topic Materials Science
url https://arxiv.org/abs/2411.12096