Application of Artificial Intelligence Techniques for Forecasting Sugar Production and Prices in the European Union

• Grant number: 24/16195-0
• Support Opportunities: Scholarships abroad - Research Internship - Scientific Initiation
• Start date: December 14, 2024
• End date: March 10, 2025
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Marilaine Colnago
• Grantee: Lucas Alexandre Borges de Matos
• Supervisor: Jose Nuno Moura Marques Fidalgo
• Host Institution: Instituto de Química (IQ). Universidade Estadual Paulista (UNESP). Campus de Araraquara. Araraquara , SP, Brazil
• Institution abroad: Instituto de Engenharia de Sistemas e Computadores - Tecnologia e Ciência (INESC TEC), Portugal
• Associated to the scholarship: 23/05265-4 - Application of Artificial Intelligence in Sugar Production Forecasting in the State of São Paulo, BP.IC

Abstract

This project presents a request for a Scientific Initiation scholarship under the BEPE-FAPESP exchange program. The research will be conducted at the Institute for Systems and Computer Engineering, Technology and Science (INESC-TEC), located in Porto, Portugal, under the supervision of Prof. Dr. José Nuno Fidalgo, a researcher in the area of Machine Learning with an emphasis on energy resource data. The central objective of the research is to extend the predictability of sugar production and prices at a macrometric level in the European market, relating the results to the already explored national data. In terms of computational apparatus for conducting the research, two Machine Learning (ML) techniques will be explored: Random Forest and Recurrent Neural Networks. The expected outcomes of the research internship abroad include: new optimized ML architectures for the specific problem at hand, providing the scholar with academic experience in a leading international institute in their field of research; strengthening partnerships between the involved groups from UNESP and INESC-TEC. Additionally, it is intended to compare the results that will be achieved with the analyses already developed in the current FAPESP IC regular project.