Abstract Scope |
Traditional glass discovery relies on trial and error approaches, thereby leading to a design-to-deploy period of 20-30 years. To address this challenge, we discuss the application of artificial intelligence (AI) and machine learning (ML) in accelerating glass modeling and discovery. Specifically, three aspects where AI and ML can be used include: (i) data-driven models for glass property predictions, (ii) natural language processing (NLP) for extracting information from the glass literature, and (iii) reinforcement learning for accelerated aging of glasses. To demonstrate these aspects, three problems will be discussed. The first focuses on developing interpretable ML models for predicting 25 properties of glasses. The second focuses on extracting information on glasses and other materials from literature to answer specific queries. Finally, we will discuss general purpose machine learned interatomic potentials can be used for materials simulations. |