Application of Physics-Informed Machine Learning (PIML) for wave forecasting along São Paulo coast

• Grant number: 25/06458-6
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: May 01, 2025
• End date: December 31, 2025
• Field of knowledge: Engineering - Naval and Oceanic Engineering
• Agreement: BG E&P Brasil (Shell Group)
• Principal Investigator: Eduardo Aoun Tannuri
• Grantee: Felipe José Vidal Souza
• Host Institution: Escola Politécnica (EP). Universidade de São Paulo (USP). São Paulo , SP, Brazil
• Company: Universidade de São Paulo (USP). Escola Politécnica (EP)
• Associated research grant: 22/03698-8 - OTIC Offshore Technology Innovation Centre, AP.PCPE

Abstract

Wave forecasting is essential for maritime operations, navigational safety, and coastal management. Traditional wave propagation models, although widely used, have limitations due to the complexity of the physical phenomena involved and the lack of continuous and accurate local data. Advances in machine learning, particularly Physics-Informed Machine Learning (PIML) techniques, enable the integration of physical knowledge and observational data to enhance environmental modeling. This project aims to develop a PIML-based system for wave forecasting along São Paulo coast, using data from buoys and coastal sensors, combined with wave propagation models and offshore data from global models. The proposed system will employ space-time graph neural networks to fill data gaps and improve the accuracy of wave forecast. (AU)