Forecast wave modeling with physics and machine learning considering extreme events and climate change for the Southeast Brazil

• Grant number: 26/07849-1
• Support Opportunities: Scholarships in Brazil - Doctorate (Direct)
• Start date: May 01, 2026
• End date: April 30, 2029
• 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

This research project comprises the investigation of coastal and ocean waves, in order to estimate the temporal variability in the frequency, intensity and direction of waves. Gravity waves include both swell and local-wind generated short surface waves, in Southeast Brazil swell waves came from farther southeast, while short waves are generated by local northeast winds. They are modeled by the combination of open ocean and nearshore spectral wave models. We have four main goals: 1) Validate and calibrate a robust wave model using physics-informed machine learning (PIML) for the South Brazil Bight; 2) Obtain 25 years of modeling output for waves (from 2000 to 2025); 3) Run `what-if' scenarios for the IPCC climate change scenarios (mainly the brander and worst scenarios, SSP126 and SSP585) in order to predict 21st century extreme events; 4) Establish an operational forecast wave model for short-term predictions (1-2 days) for the South Brazil Bight. The use of machine learning technics is incorporated into the project and is expected to improve the physical models and forecasts. The use of the new high-resolution CMIP6 data from the IPCC will lead to more detailed predictions. (AU)