On the application of high‐throughput experimentation and data‐driven approaches in metallic glasses

Abstract

Abstract Materials genome engineering (MGE) has been successfully applied in various fields, resulting in a series of novel materials with excellent performance. Significant progress has been made in high‐throughput simulation, experimentation, and data‐driven techniques, enabling the effective prediction, rapid synthesis, and characterization of many classes of materials. In this brief review, we introduce the achievements made in the field of metallic glasses (MGs) using MGE, in particular high‐throughput experimentation and data‐driven approaches. High‐throughput experiments help to efficiently synthesize and characterize many materials in a short period of time, enabling the construction of high‐quality material databases for data‐driven methods. Paired with machine learning, potential alloys of desired properties may be revealed and predicted. Along with the progress in computational power and algorithms of machine learning, the complex composition‐structure‐properties relationship is hopefully established, which in turn help efficient and precise prediction of new MGs.

Keywords

• data‐driven
• high‐throughput experiment
• high‐throughput simulation
• machine learning
• materials genome engineering
• metallic glasses