A focused review on machine learning aided high-throughput methods in high entropy alloy

Abstract High-entropy alloys (HEAs) have attracted tremendous attention in various fields due to unique microstructures and many excellent properties. For particular applications, an in-depth understanding of the essence is important to further developing new HEAs with promising properties. In present paper, the recent development of HEAs was reviewed, including the phase formation and microstructures, various properties, and multi-scale modeling aided composition design. Materials informatics employ machine learning (ML) method to map the relationship between a targeted property and various materials descriptors, providing new avenues to accelerate the discovery of new materials. Particularly with the aid of machine learning approach, reliable composition-properties features can be offered which can act as guides for tuning composition design in HEAs. Eventually, potentials of utilizing machine learning combined multi-scale computation in materials science and the future prospects of HEAs are put forward.