2, Shanghai University, Shang Hai, , China
There is a genuine need to shorten the development period for new materials with desired properties. Bulk metallic glasses (BMGs) are a unique class of materials that are gaining attention in a wide variety of applications due to their attractive physical properties. One limitation to the wide-scale use of these materials is the lack of predictable tools for understanding the relationship between alloy composition and ideal properties. In this work, machine learning (ML) approach was applied on a dataset of 6312 alloys. The resulting ML model predicted the glass forming ability and elastic moduli of unseen alloys in good agreement with most experimentally measured values. It will promote the development of basic theories of metallic glasses to reveal the intrinsic correlation of physical properties through material big-data mining. This work indicates the great potential of ML in the design of advanced materials with target properties.