Magnetic iron-cobalt silicides discovered using machine-learning
Timothy Liao, Weiyi Xia, Masahiro Sakurai, Renhai Wang, Chao Zhang, Huaijun Sun, Kai‐Ming Ho, Cai‐Zhuang Wang, James R. Chelikowsky
Abstract
We employ machine-learning (ML) combined with first principles calculations to discover different rare-earth-free magnetic iron-cobalt silicide compounds. Deep machine-learning models are used to provide rapid screening of over 350 000 hypothetical structures to select a small fraction of promising structures and compositions for further studies by first-principles calculations. An adaptive genetic algorithm is used to search for lower energy structures based on the promising chemical compositions. Such a ML-guided approach dramatically accelerates the pace of materials discovery. We discover four new ternary Fe-Co-Si compounds, which exhibit desirable properties such as a large magnetic polarization $({J}_{s}>1.0\phantom{\rule{0.28em}{0ex}}\mathrm{T})$, a significant easy-axis magnetic anisotropy $({K}_{1}\ensuremath{\ge}1.0\phantom{\rule{0.28em}{0ex}}\mathrm{MJ}/{\mathrm{m}}^{3})$, and a high Curie temperature $({T}_{\mathrm{C}}>840\phantom{\rule{0.28em}{0ex}}\mathrm{K})$. Moreover, the formation energies of these compounds are all within 70 meV/atom relative to the ternary convex hull, offering the possibility of synthesis.