Important descriptors and descriptor groups of Curie temperatures of rare-earth transition-metal binary alloys

TL;DR

This paper uses machine learning and subgroup relevance analysis to identify key descriptors influencing the Curie temperatures of rare-earth transition-metal binary alloys, aiding in understanding and predicting magnetic properties.

Contribution

Introduces a novel subgroup relevance analysis combined with hierarchical clustering for selecting important descriptors in magnetic property prediction.

Findings

Successful identification of important descriptors and groups affecting Curie temperatures.

Demonstrates the effectiveness of exhaustive search in descriptor selection.

Provides insights into the physical meaning of selected descriptors.

Abstract

We analyze Curie temperatures of rare-earth transition metal binary alloys with machine learning method. In order to select important descriptors and descriptor groups, we introduce newly developed subgroup relevance analysis and adopt the hierarchical clustering in the representation. We execute the exhaustive search and successfully illustrate the importance of descriptors and descriptor groups. We execute the exhaustive search and illustrate that our approach indeed leads to the successful selection of important descriptors and descriptor groups. It helps us to choose the combination of the descriptors and to understand the meaning of the selected combination of descriptors.