Important Descriptors and Descriptor Groups of Curie Temperatures of Rare-earth Transition-metal Binary Alloys

We analyze the Curie temperatures of rare-earth transition metal binary alloys using machinelearning. In order to select important descriptors and descriptor groups, we introduce a newlydeveloped subgroup relevance analysis and adopt hierarchical clustering in the representation.We execute exhaustive search and demonstrate that our approach results in the successfulselection of important descriptors and descriptor groups. It helps us to choose thecombination of descriptors and to understand the meaning of the selected combination ofdescriptors.

This work was partly supported by PRESTO and by the “Materials Research by Information Integration” Initiative (MI²I) project of the Support Program for Starting Up Innovation Hub, both from the Japan Science and Technology Agency (JST), Japan; by the Elements Strategy Initiative Project under the auspices of MEXT; and also by MEXT as a social and scientific priority issue (Creation of New Functional Devices and High-Performance Materials to Support Next-Generation Industries; CDMSI) to be tackled by using a post-K computer. The calculations were partly carried out on Numerical Materials Simulator at NIMS.