Session 6: Data-based Modeling and Machine Learning for Glass Science

Data-driven methods and artificial intelligence-based models have been attracting a lot of attention in recent years to solve complex problems in the field of glass science. Specifically, machine learning has been successfully applied to resolve long-standing problems such as predicting composition–property relationships, developing optimized glass compositions, accelerating glass modeling, and even understanding the fundamental aspects of glass transition.

This session focuses on the recent advances achieved using machine learning in the areas of glass science, technology, and modeling. The topics of interest include, but are not restricted to, the application of machine learning and artificial intelligence to: develop composition-property relationships, design optimized glass compositions, 3D printing and additive manufacturing of glasses, advance computational modeling by developing machine-learned interatomic potentials and accelerating glass simulations, image processing, predict the structure of glasses, identifying key structural patterns/descriptors that govern glass properties, and understanding the fundamentals of glassy state.

organizers:

• Adama Tandia, Corning Inc. USA, TandiaA@Corning.com
• Aditya Kumar, Missouri S&T, USA, kumarad@mst.edu
• Daniel Cassar, Brazilian Center for Research in Energy and Materials, Brazil, cassar@cnpem.br