| Abstract Scope |
Metallic glasses offer advantageous properties for many applications, but are difficult to materials to engineer. Like most materials, achieving optimal performance in metallic glasses requires identifying composition and processing conditions which achieve a delicate balances between properties. However, this design process is complicated by the lack of understanding of the mechanisms behind the properties of glasses and, consequently, the absence of computational tools for predicting material properties. In this talk, we provide several examples of how machine learning can fill this void. In particular, we will demonstrate how machine learning can be used to tailor the properties of Bulk Metallic Glasses (BMG) and be used with high-throughput experimentation to quickly identify amorphous coatings. This talk will focus on the methods behind developing, validating, and using these models in order to show how machine-learning-aided design could be useful in other areas of materials engineering. |