STUDY OF SEDIMENT TRANSPORT DURING EXTREME EVENTS USING CLASSICAL MATHEMATICAL MODELING AND ARTIFICIAL INTELLIGENCE

• Grant number: 25/04675-0
• Support Opportunities: Scholarships in Brazil - Master
• Start date: November 01, 2025
• End date: March 31, 2027
• Field of knowledge: Physical Sciences and Mathematics - Geosciences
• Principal Investigator: Hugo de Oliveira Fagundes
• Grantee: Ivan Mangini
• Host Institution: Faculdade de Engenharia Civil, Arquitetura e Urbanismo (FEC). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil

Abstract

Recent reports, such as the IPCC AR6 (2021), highlight the worsening climate impacts, including extreme events like floods and droughts. In Brazil, these effects are observed on large river basins, such as droughts in the Amazon River and floods in Rio Grande do Sul in 2023 and 2024. Another problem during flood events is soil erosion, sediment transport and deposition. As a solution, distributed numerical models have proven effective in sediment analysis, especially with the availability of historical data. However, calibrating these models can be a highly complex and time-consuming task. An alternative to classical models for simulating sediment flows is the use of machine learning tools and artificial neural networks, which offer promising solutions, enabling greater accuracy in predictions and efficiency in management. The international scientific literature has employed these techniques for flow prediction and sediment transport analysis. This project aims to integrate sediment numerical modeling and artificial intelligence to improve estimates and help understand how extreme events contribute to sediment transport. Using the Ivaí River basin as a case study, it also seeks to contribute to sustainability and water security in the face of climate change.