Scholarship 23/17435-1 - Aprendizado computacional, Materiais bidimensionais - BV FAPESP
Advanced search
Start date
Betweenand

Development of Generative Machine Learning Models for the Design of Materials for Photovoltaic Applications

Grant number: 23/17435-1
Support Opportunities:Scholarships in Brazil - Post-Doctoral
Start date until: March 01, 2024
End date until: February 28, 2026
Field of knowledge:Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
Principal Investigator:Juarez Lopes Ferreira da Silva
Grantee:Douglas Willian Duarte de Vargas
Host Institution: Instituto de Química de São Carlos (IQSC). Universidade de São Paulo (USP). São Carlos , SP, Brazil
Company:Universidade de São Paulo (USP). Instituto de Química de São Carlos (IQSC)
Associated research grant:17/11631-2 - CINE: computational materials design based on atomistic simulations, meso-scale, multi-physics, and artificial intelligence for energy applications, AP.PCPE

Abstract

This project explores novel frontiers in materials science through the application of generative algorithms, targeting efficient material discovery. The vast and largely unexplored chemical space presents challenges in accurately identifying both periodic and non-periodic systems, selecting optimal representations, and integrating databases. Leveraging state-of-the-art computational techniques, such as Graph Neural Networks (GNN), the study aims to generate and validate new candidates for photovoltaic cells in both three-dimensional (3D) and two-dimensional (2D) structures. The research unfolds in a six-semester plan, focusing on key objectives: exploring generative algorithms in molecular contexts, studying the efficiency of 3D periodic system representations for generative artificial intelligence, enhancing generative algorithms using single and multiple datasets through data fusion and transfer learning, and applying generative models for the discovery and optimization of perovskite and 2D materials for photovoltaic and optoelectronic applications. Overcoming challenges in accurately identifying diverse systems and optimizing representations is crucial for the success of generative algorithms. The anticipated outcomes involve the development of proficient generative machine learning models, offering a faster and more efficient approach to material discovery. The results are expected to contribute to the advancement of materials science, fostering qualified human resources in machine learning for materials science, and complementing existing research within the QTNano group and CINE.

News published in Agência FAPESP Newsletter about the scholarship:
More itemsLess items
Articles published in other media outlets ( ):
More itemsLess items
VEICULO: TITULO (DATA)
VEICULO: TITULO (DATA)

Please report errors in scientific publications list using this form.