Machine Learning-guided design of novel glasses with good vitrification ability and multiple property combinations.

• Grant number: 23/09945-0
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: September 01, 2023
• End date: October 31, 2025
• Field of knowledge: Engineering - Materials and Metallurgical Engineering - Nonmetallic Materials
• Principal Investigator: Edgar Dutra Zanotto
• Grantee: Rafael Baságlia Rosante
• Host Institution: Centro de Ciências Exatas e de Tecnologia (CCET). Universidade Federal de São Carlos (UFSCAR). São Carlos , SP, Brazil
• Associated research grant: 13/07793-6 - CEPIV - Center for Teaching, Research and Innovation in Glass, AP.CEPID
• Associated scholarship(s): 24/21050-0 - EVALUATION OF THE JZCA MODEL IN PREDICTING GLASS FORMING ABILITY WITH FOCUS ON LOW VISCOSITY AT LIQUIDUS TEMPERATURE, BE.EP.IC

Abstract

In this project we intend to: 1) develop a computer code that combines several data-driven predictive Machine Learning models (Random Forest, Artificial Neural Networks and others using stackedgeneralization) coupled with a Genetic Algorithm to design oxide glass formulations having desired combinations of physical-chemical properties (such as, glass transition temperature, thermal expansion coefficient, density, hardness, elastic modulus, refractive index, etc.). We also plan to: 2) employ combinations of element properties that could, perhaps, predict the vitrifiability or glass forming ability (GFA) of the suggested formulations, such as, for instance: electronegativity, cation-oxygen dissociation energy, cation field strength, and average number of bridging oxygens per (-O-cation-O-cation-O-) structural unit. The first part has been pioneered by our group 4 years ago and several teams in the world are now working on this problem; however, to the best of our knowledge, nobody has used the stakingprocedure for this particular problem. Also, the second part is original at international level; so far there is no published report on the prediction of GFA of ML-derived oxide glass compositions. This sounds like a post-graduate level proposal; however, the candidate (Rafael) has been working with us for several months already and has clearly proven to have great ability with coding and ML algorithms.