Searching for ternary magnetic Zr–Fe–B compounds through deep machine learning
Journal of Physics D: Applied Physics · 12.06.2026 · 59 (23) · 235002
DOI: 10.1088/1361-6463/ae71de ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Physics D: Applied Physics, online erschienen am 12.06.2026. Verfasst von Rong Cheng und 5 weiteren Autor:innen. Die Arbeit nennt 25 Literaturangaben. Gefördert von: Natural Science Foundation of Shandong Province, Iowa State University, U.S. Department of Energy (DOE), Office of Science, Basic Energy Sciences, Materials Science and Engineering Division.
Abstract (Originalsprache)
We use deep machine learning (ML) combined with first-principles calculations to search for energetically favorable ternary magnetic zirconium–iron borides. We show that an iterative ML approach enables efficient screening of vast structural libraries, effectively selecting promising candidates for subsequent first-principles investigations. Twenty-two new Fe-rich ternary compounds with formation energies within 60 meV atom −1 above the known ternary convex hull and with magnetic polarization larger than 0.6 T are identified, among which ten structures exhibit significant uniaxial anisotropy with magnetocrystalline anisotropy constant K 1 ⩾ 0.8 MJ m −3 , including a Zr 2 Fe 14 B phase. Such an ML-guided approach dramatically accelerates the discovery of rare-earth-free permanent magnetic materials.
Förderung
- Natural Science Foundation of Shandong Province
- Iowa State University
- U.S. Department of Energy (DOE), Office of Science, Basic Energy Sciences, Materials Science and Engineering Division
Zitieren
APA
Cheng, R., Xue, X., Dong, Y., Qin, W., Zhao, L., & Wang, C. Z. (2026). Searching for ternary magnetic Zr–Fe–B compounds through deep machine learning. Journal of Physics D: Applied Physics, 59(23), 235002. https://doi.org/10.1088/1361-6463/ae71de
Vancouver
Cheng R, Xue X, Dong Y, Qin W, Zhao L, Wang CZ. Searching for ternary magnetic Zr–Fe–B compounds through deep machine learning. Journal of Physics D: Applied Physics. 2026;59(23):235002. doi:10.1088/1361-6463/ae71de
BibTeX
@article{Cheng2026,
author = {Cheng, Rong and Xue, Xuyan and Dong, Yuehang and Qin, Wei and Zhao, Lizhen and Wang, C Z},
title = {Searching for ternary magnetic Zr–Fe–B compounds through deep machine learning},
journal = {Journal of Physics D: Applied Physics},
year = {2026},
volume = {59},
number = {23},
pages = {235002},
doi = {10.1088/1361-6463/ae71de}
}
EUVIMED