|About this Abstract
||Materials Science & Technology 2019
||Data Science for Material Property Interpretation
||Deciphering the Atomic Origin of Glasses’ Properties by Machine Learning
||Tyanyi Bao, Mathieu Bauchy
|On-Site Speaker (Planned)
The complex, disordered structure of glasses makes it challenging to elucidate how their atomic structure control their macroscopic properties (e.g., mechanical properties). Here, we adopt machine learning (ML) to decipher the complex structural features that govern the fracture toughness of glasses. Our approach relies on molecular dynamics simulations, which outcomes are analyzed by ML-based supervised classification. This analysis yields a non-intuitive structural descriptor that is highly correlated with the response of glasses to fracture.
||Definite: At-meeting proceedings