1. Experimental exploration of ErB2 and SHAP analysis on a machine-learned model of magnetocaloric materials for materials design
- Author
-
Kensei Terashima, Pedro Baptista de Castro, Akiko Takahashi Saito, Takafumi D Yamamoto, Ryo Matsumoto, Hiroyuki Takeya, and Yoshihiko Takano
- Subjects
magnetocaloric materials ,machine learning ,data-driven materials search ,Materials of engineering and construction. Mechanics of materials ,TA401-492 - Abstract
Stimulated by a recent report of a giant magnetocaloric effect in HoB2 found via machine-learning predictions, we have explored the magnetocaloric properties of a related compound ErB2 that has remained the last ferromagnetic material among the rare-earth diboride (REB2) family with unreported magnetic entropy change $|{\rm \Delta} {S_M}|$. The evaluated $|{\rm \Delta} {S_M}|$ at field change of 5 T in ErB2 turned out to be as high as 26.1 J kg−1 K−1 around the ferromagnetic transition (${T_C}$) of 14 K. In this series, HoB2 is found to be the material with the largest $|{\rm \Delta} {S_M}|$ as the model predicted, while the predicted values showed a deviation with a systematic error compared to the experimental values. Through a coalition analysis using SHAP, we explore how this rare-earth dependence and the deviation in the prediction are deduced in the model. We further discuss how SHAP analysis can be useful in clarifying favorable combinations of constituent atoms through the machine-learned model with compositional descriptors. This analysis helps us to perform materials design with aid of machine learning of materials data.
- Published
- 2023
- Full Text
- View/download PDF