Prediction on Properties of Rare-earth 2-17-X Magnets Ce2Fe17-xCoxCN : A Combined Machine-learning and Ab-initio Study

TL;DR

This study combines machine learning and first-principles calculations to predict and analyze magnetic properties of rare-earth lean magnets, specifically Ce2Fe17-xCoxCN, aiming to identify cost-effective permanent magnet materials.

Contribution

It introduces a novel integrated approach using machine learning and ab-initio methods to predict magnetic properties of rare-earth lean magnets, facilitating discovery of new materials.

Findings

Predicted magnetic transition temperatures, saturation magnetization, and anisotropy for Ce2Fe17-xCoxCN.

Identified potential stable compounds with promising magnetic properties.

Suggested these compounds could be cost-effective permanent magnets.

Abstract

We employ a combination of machine learning and first-principles calculations to predict magnetic properties of rare-earth lean magnets. For this purpose, based on training set constructed out of experimental data, the machine is trained to make predictions on magnetic transition temperature (Tc), largeness of saturation magnetization ({\mu}0Ms), and nature of the magnetocrystalline anisotropy (Ku). Subsequently, the quantitative values of {\mu}0Ms and Ku of the yet-to-be synthesized compounds, screened by machine learning, are calculated by first-principles density functional theory. The applicability of the proposed technique of combined machine learning and first-principles calculations is demonstrated on 2-17-X magnets, Ce2Fe17-xCoxCN. Further to this study, we explore stability of the proposed compounds by calculating vacancy formation energy of small atom interstitials (N/C). Our study indicates a number of compounds in the proposed family, offers the possibility to become solution of cheap, and efficient permanent magnet.