Efficient small-cell sampling for machine-learning potentials of multi-principal element alloys

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Yan, Wang, Jiantao, Deng, Hongkun, Sun, Yan, Chen, Xing-Qiu, Liu, Peitao
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914103103062016
author Liu, Yan
Wang, Jiantao
Deng, Hongkun
Sun, Yan
Chen, Xing-Qiu
Liu, Peitao
author_facet Liu, Yan
Wang, Jiantao
Deng, Hongkun
Sun, Yan
Chen, Xing-Qiu
Liu, Peitao
contents Multi-principal element alloys (MPEAs) exhibit exceptional properties but face significant challenges in developing accurate machine-learning potentials (MLPs) due to their vast compositional and configurational complexity. Here, we introduce an efficient small-cell sampling (SCS) method, which allows for generating diverse and representative training datasets for MPEAs using only small-cell structures with just one and two elements, thereby bypassing the computational overhead of iterative active learning cycles and large-cell density functional theory calculations. The efficacy of the method is carefully validated through principal component analysis, extrapolation grades evaluation, and root-mean-square errors and physical properties assessment on the TiZrHfCuNi system. Further demonstrations on TiZrVMo, CoCrFeMnNi, and AlTiZrNbHfTa systems accurately reproduce complex phenomena including phase transitions, chemical orderings, and thermodynamic properties. This work establishes an efficient one-shot protocol for constructing high-quality training datasets across multiple elements, laying a solid foundation for developing universal MLPs for MPEAs.
format Preprint
id arxiv_https___arxiv_org_abs_2510_16697
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Efficient small-cell sampling for machine-learning potentials of multi-principal element alloys
Liu, Yan
Wang, Jiantao
Deng, Hongkun
Sun, Yan
Chen, Xing-Qiu
Liu, Peitao
Materials Science
Multi-principal element alloys (MPEAs) exhibit exceptional properties but face significant challenges in developing accurate machine-learning potentials (MLPs) due to their vast compositional and configurational complexity. Here, we introduce an efficient small-cell sampling (SCS) method, which allows for generating diverse and representative training datasets for MPEAs using only small-cell structures with just one and two elements, thereby bypassing the computational overhead of iterative active learning cycles and large-cell density functional theory calculations. The efficacy of the method is carefully validated through principal component analysis, extrapolation grades evaluation, and root-mean-square errors and physical properties assessment on the TiZrHfCuNi system. Further demonstrations on TiZrVMo, CoCrFeMnNi, and AlTiZrNbHfTa systems accurately reproduce complex phenomena including phase transitions, chemical orderings, and thermodynamic properties. This work establishes an efficient one-shot protocol for constructing high-quality training datasets across multiple elements, laying a solid foundation for developing universal MLPs for MPEAs.
title Efficient small-cell sampling for machine-learning potentials of multi-principal element alloys
topic Materials Science
url https://arxiv.org/abs/2510.16697