Compositional optimization of hard-magnetic phases with machine-learning models

TL;DR

This paper demonstrates how machine learning models can predict optimal compositions for hard-magnetic phases, aiding the discovery of efficient, less critical rare-earth permanent magnets through data-driven materials design.

Contribution

The study introduces kernel-based ML models trained on DFT data for compositional optimization of magnetic materials, enabling targeted discovery of promising magnetic substitutes.

Findings

ML models accurately predict magnetic properties from composition.

Identified potential substitutes with similar magnetic performance.

Reduced reliance on critical rare-earth elements in magnets.

Abstract

Machine Learning (ML) plays an increasingly important role in the discovery and design of new materials. In this paper, we demonstrate the potential of ML for materials research using hard-magnetic phases as an illustrative case. We build kernel-based ML models to predict optimal chemical compositions for new permanent magnets, which are key components in many green-energy technologies. The magnetic-property data used for training and testing the ML models are obtained from a combinatorial high-throughput screening based on density-functional theory calculations. Our straightforward choice of describing the different configurations enables the subsequent use of the ML models for compositional optimization and thereby the prediction of promising substitutes of state-of-the-art magnetic materials like Nd$_2$Fe$_{14}$B with similar intrinsic hard-magnetic properties but a lower amount of critical rare-earth elements.