A critical review of the machine learning guided design of metallic glasses for superior glass-forming ability

The discovery of novel metallic glasses (MGs) with high glass-forming ability (GFA) has been an important area active research for years in materials science and engineering. Unfortunately, the traditional approach based on trial-and-error methods is inefficient, time consuming costly. Therefore, machine learning (ML) recently drawn significant interest as alternative development MGs. In this review, we discuss current progress regarding ML guided design MGs from a variety perspectives, including GFA database, data representation, algorithms numerical evaluation. Furthermore, consider challenges facing field, scarcity quality data, physics informed descriptors, selection appropriate necessity experimental validation. We also briefly possible solutions to tackle these challenges.