Application of machine learning in understanding the irradiation damage mechanism of high-entropy materials

Abstract

The concept of high entropy materials (HEMs) provides a fertile ground for developing novel irradiation-resistant structural materials. In HEMs, the vast and complicated configurational space induced by extreme disorder poses grant challenges to understanding defect dynamics and evolution. Machine learning (ML) techniques, which can exploit implicit relationships between diverse descriptors and observations, exhibit great potential in uncovering the governing factors for irradiation damage and modeling local environment dependence of defect dynamics. Herein, three applications of ML in understanding radiation damage in HEMs are summarized and discussed, including ML-based irradiation response prediction, ML-based interatomic potential development, and ML-informed defect evolution.