Machine-Learned Bond-Order Potential for Exploring the Configuration Space of Carbon

2025/01/20 by Ikuma Kohata, Kaoru Hisama, Kohata, Ikuma +5 · 1 citation
Biochemistry, Genetics and Molecular Biology · Materials Science · Physics and Astronomy · #Advanced Chemical Physics Studies #FOS: Physical sciences #Machine Learning in Materials Science #Materials Science (cond-mat.mtrl-sci) #Protein Structure and Dynamics

paper · pdf · doi:10.48550/arxiv.2501.11297

openalex publication_date 2025/01/20 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/29

Abstract

Construction of transferable machine-learning interatomic potentials with a minimal number of parameters is important for their general applicability. Here, we present a machine-learning interatomic potential with the functional form of the bond-order potential for comprehensive exploration over the configuration space of carbon. The physics-based design of this potential enables robust and accurate description over a wide range of the potential energy surface with a small number of parameters. We demonstrate the versatility of this potential through validations across various tasks, including phonon dispersion calculations, global structure searches for clusters, phase diagram calculations, and enthalpy-volume mappings of local minima structures. We expect that this potential can contribute to the discovery of novel carbon materials.

Cited by

• Electronic Structure of Bimetallic CoRu Catalysts Modulates SWCNT Nucleation

Related

• The transformative capability of quantum-accurate machine learning interatomic potentials
• Unifying the description of hydrocarbons and hydrogenated carbon materials with a chemically reactive machine learning interatomic potential
• A Systematic Approach to Generating Accurate Neural Network Potentials:\n the Case of Carbon
• Synthetic pre-training for neural-network interatomic potentials
• A Bayesian Committee Machine Potential for Organic Nitrogen Compounds