Data driven screening of CaCu5-type magnetic structures
Abstract
We develop a machine learning assisted workflow for the rapid screening of permanent magnet candidates within the CaCu5 structure family. We generated more than 60,000 structures through substitutions. These compositions were screened using a combination of pretrained materials models, Materials Project data, and a machine-learning model for magnetization prediction. Four criteria, namely, metallicity, negative formation energy, energy above the convex hull ≤ 50~meV/atom, and predicted magnetization above the adopted ≥ 0.75~T threshold reduced the initial chemical space to 439 candidates for first-principles calculations. Density functional theory calculations revealed that 159 compounds exhibit positive axial magnetic anisotropy energy, favoring [001] over the tested in-plane directions. The resulting dataset reveals chemical trends in magnetic anisotropy across the CaCu5 compositional space and provides a set of candidates for further investigation. More broadly, this work demonstrates a practical strategy for combining existing machine learning models with first-principles calculations to systematically reduce large chemical spaces to tractable sets for computationally intensive materials screening.
Related
- Magnetic island structures in relativistic laser-driven plasma channels
- Magnetic structures in a model nickelate: Monte Carlo study
- Controlling exceptional points of layered non-Hermitian structures with magnetic field
- Creating functional nanostructures for vortex manipulation in superconducting Bi2Sr2CaCu2O8+x thin films via focused He ion beam irradiation
- Spatial statistics for screening molecular structures
BibTeX
@misc{pokhrel2026data,
title = {{Data driven screening of CaCu$_5$-type magnetic structures}},
author = {Nabaraj Pokhrel and Sheila Whitman and David S. Parker},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.10891},
eprint = {2610.10891},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.10891},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - UNPB
TI - Data driven screening of CaCu_5-type magnetic structures
AU - Nabaraj Pokhrel
AU - Sheila Whitman
AU - David S. Parker
PY - 2026
DA - 2026/10/07
PB - arXiv
DO - 10.48550/arxiv.2610.10891
UR - https://arxiv.org/abs/2610.10891
AB - We develop a machine learning assisted workflow for the rapid screening of permanent magnet candidates within the CaCu_5 structure family. We generated more than 60,000 structures through substitutions. These compositions were screened using a combination of pretrained materials models, Materials Project data, and a machine-learning model for magnetization prediction. Four criteria, namely, metallicity, negative formation energy, energy above the convex hull ≤ 50~meV/atom, and predicted magnetization above the adopted ≥ 0.75~T threshold reduced the initial chemical space to 439 candidates for first-principles calculations. Density functional theory calculations revealed that 159 compounds exhibit positive axial magnetic anisotropy energy, favoring [001] over the tested in-plane directions. The resulting dataset reveals chemical trends in magnetic anisotropy across the CaCu_5 compositional space and provides a set of candidates for further investigation. More broadly, this work demonstrates a practical strategy for combining existing machine learning models with first-principles calculations to systematically reduce large chemical spaces to tractable sets for computationally intensive materials screening.
ER -