Data-based Modeling and Machine Learning for Glass Science

Data-driven modeling and machine learning have been attracting a lot of attention in recent years to solve complex problems in the field of glass science. Specifically, machine learning methods have been demonstrated as promising tools to tackle open problems such as predicting composition–property relationships in glasses. The aim of this session is to focus on recent advances in the field of glass science achieved using data-driven modeling and machine learning. Topics of interest include, but are not restricted to, the use of data-based modeling to develop composition–property relationships, design optimized glass compositions, develop interatomic potentials, understand the fundamentals of glassy state for image processing, predict the structure of glasses, and develop empirical relationships.

organizers:

• Adama Tandia, Corning Inc., USA
• Mathieu Bauchy, University of California Los Angeles, USA
• N.M. Anoop Krishan, Indian Institute of Technology Delhi, India