Coercivity-Aware Machine Learning Discovery of Rare-Earth-Free Soft Magnetic Alloys with First-Principles Magnetic Benchmarks
Abstract
Coercivity-aware machine learning is developed to screen rare-earth-free soft magnetic alloys using Curie temperature and coercivity as coupled design targets. A compiled experimental magnetic-material dataset is evaluated using composition-grouped partitioning to avoid overlap of identical compositions between training and testing, and elemental fractions and composition-weighted elemental descriptors are examined for prediction of the two magnetic properties. Residual-based prediction intervals and distance-to-training filters are then incorporated to screen Fe-Co-Ni-Mn-Al-Si compositions. Composition-grouped evaluation shows lower predictive accuracy than conventional random partitioning, demonstrating the importance of evaluating transfer to previously unseen compositions. Combining weighted elemental descriptors with elemental fractions improves Curie-temperature prediction, whereas the additional descriptors do not improve coercivity prediction, consistent with the strong dependence of coercivity on processing and microstructure. Uncertainty-aware screening substantially narrows the candidate space and identifies Fe-Co-rich compositions for further evaluation. First-principles calculations independently show strong magnetic polarization and magnetovolume effects in representative Fe-Co structures, while finite-temperature atomistic spin simulations place the Fe-Co benchmark systems on high magnetic-ordering-temperature scales. The combined approach provides a computational framework for prioritizing rare-earth-free soft-magnetic chemistries while distinguishing composition-level screening from candidate-specific physical validation.
Related
- Pyroelectricity: A Brief History of its Discovery and Physical Principles - an Overview
- First Principles Magnetic Initialisation Made Simple
- Piezoelectricity: A Brief History of its Discovery and Physical Principles Using the Example of Low Quartz
- Spatial localization of magnetic-branch force contrasts in substitutional Mn-doped Ge: A first-principles study
- Magnetic Order from First-Principles Linear Response
BibTeX
@misc{mahata2026coercivityaware,
title = {{Coercivity-Aware Machine Learning Discovery of Rare-Earth-Free Soft Magnetic Alloys with First-Principles Magnetic Benchmarks}},
author = {Avik Mahata and David Priefer},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.03171},
eprint = {2610.03171},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.03171},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Coercivity-Aware Machine Learning Discovery of Rare-Earth-Free Soft Magnetic Alloys with First-Principles Magnetic Benchmarks
AU - Avik Mahata
AU - David Priefer
PY - 2026
DA - 2026/10/02
PB - arXiv
DO - 10.48550/arxiv.2610.03171
UR - https://arxiv.org/abs/2610.03171
AB - Coercivity-aware machine learning is developed to screen rare-earth-free soft magnetic alloys using Curie temperature and coercivity as coupled design targets. A compiled experimental magnetic-material dataset is evaluated using composition-grouped partitioning to avoid overlap of identical compositions between training and testing, and elemental fractions and composition-weighted elemental descriptors are examined for prediction of the two magnetic properties. Residual-based prediction intervals and distance-to-training filters are then incorporated to screen Fe-Co-Ni-Mn-Al-Si compositions. Composition-grouped evaluation shows lower predictive accuracy than conventional random partitioning, demonstrating the importance of evaluating transfer to previously unseen compositions. Combining weighted elemental descriptors with elemental fractions improves Curie-temperature prediction, whereas the additional descriptors do not improve coercivity prediction, consistent with the strong dependence of coercivity on processing and microstructure. Uncertainty-aware screening substantially narrows the candidate space and identifies Fe-Co-rich compositions for further evaluation. First-principles calculations independently show strong magnetic polarization and magnetovolume effects in representative Fe-Co structures, while finite-temperature atomistic spin simulations place the Fe-Co benchmark systems on high magnetic-ordering-temperature scales. The combined approach provides a computational framework for prioritizing rare-earth-free soft-magnetic chemistries while distinguishing composition-level screening from candidate-specific physical validation.
ER -