Interpretable Models Using Clustering for Critical Temperature Prediction of Superconductors

• Grant number: 25/13052-6
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: September 01, 2025
• End date: August 31, 2026
• Field of knowledge: Engineering - Materials and Metallurgical Engineering
• Principal Investigator: Daniel Roberto Cassar
• Grantee: Júlia Guedes Almeida dos Santos
• Host Institution: Centro Nacional de Pesquisa em Energia e Materiais (CNPEM). Campinas , SP, Brazil
• Associated research grant: 23/09820-2 - Materials by design: from quantum materials to energy applications, AP.TEM

Abstract

Superconductivity is a physical phenomenon of great importance in various technological fields. However, the advancement and practical application of these technologies are still limited by the low Critical Temperature (Tc) values observed in most materials. This temperature corresponds to the point at which a material, when cooled, begins to exhibit characteristic superconducting properties-such as perfect diamagnetism and zero electrical resistance. Given that no comprehensive theory currently exists to explain this phenomenon across the full range of critical temperatures, computational techniques have been employed to predict materials with Tc values near room temperature. In this context, the present project aims to generate relevant insights for the development of new superconducting materials through the use of Generalized Linear Models (GLM) and Generalized Additive Models (GAM)- approaches that remain underexplored in the literature and are inherently interpretable - combined with explainability techniques, such as SHAP, and data clustering methods.