Optimization of noncollinear magnetic ordering temperature in Y-type hexaferrite by machine learning

TL;DR

This paper employs machine learning to optimize the noncollinear magnetic transition temperature in Y-type hexaferrites, successfully predicting and experimentally validating a composition with a record high TNC of 568 K.

Contribution

It introduces a data-driven machine learning approach using SISSO to identify optimal doping compositions for enhanced magnetic transition temperatures in hexaferrites.

Findings

Predicted a composition with TNC up to 568 K.

Experimentally validated the predicted composition.

Achieved elevated magnetic transition temperature of 735 K.

Abstract

Searching the optimal doping compositions of the Y-type hexaferrite Ba2Mg2Fe12O22 remains a long-standing challenge for enhanced non-collinear magnetic transition temperature (TNC). Instead of the conventional trial-and-error approach, the composition-property descriptor is established via a data driven machine learning method named SISSO (sure independence screening and sparsifying operator). Based on the chosen efficient and physically interpretable descriptor, a series of Y-type hexaferrite compositions are predicted to hold high TNC, among which the BaSrMg0.28Co1.72Fe10Al2O22 is then experimentally validated. Test results indicate that, under appropriate external magnetic field conditions, the TNC of this composition reaches up to reaches up to 568 K, and its magnetic transition temperature is also elevated to 735 K. This work offers a machine learning-based route to develop room temperature single phase multiferroics for device applications.