CHLOROPHYLL-a MAPPING IN THE NOVA AVANHANDAVA RESERVOIR USING OLI LANDSAT IMAGES AND MACHINE LEARNING

• Grant number: 25/14495-9
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: October 01, 2025
• End date: September 30, 2026
• Field of knowledge: Physical Sciences and Mathematics - Geosciences - Geophysics
• Principal Investigator: Fernanda Sayuri Yoshino Watanabe
• Grantee: Mila Abifadel Fernandes
• Host Institution: Faculdade de Ciências e Tecnologia (FCT). Universidade Estadual Paulista (UNESP). Campus de Presidente Prudente. Presidente Prudente , SP, Brazil
• Associated research grant: 24/06526-9 - Weaving knowledge together for healthy and resilient aquatic socio-ecosystems: towards a methodological and modelling framework (WaterWeave), AP.BTA.R

Abstract

Water quality in reservoirs has been increasingly affected by processes such as eutrophication due to increased water retention time and high nutrient availability in low-turbulence environments, resulting in algal blooms. In the context of inland water monitoring, the concentrations of photosynthetic pigments, especially chlorophyll-a, have great potential for analyzing water quality. This project, therefore, aims to develop a bio-optical model to estimate chlorophyll-a concentration in the Nova Avanhandava reservoir, using multispectral images from the OLI Landsat sensor and machine learning techniques, with an emphasis on the Random Forest algorithm. The work will use radiometric measurements and chlorophyll-a (Chla) content data from the GLORIA database and collected in situ. Band simulations of OLI Landsat will done and used to calibrate and validate bio-optical models. Accuracy will be assessed using statistical metrics such as the coefficient of determination (R²), root mean square error (RMSE), normalized root mean square error (NRMSE), and bias. The final result will be a map of the spatial distribution of chlorophyll-a concentration in the reservoir. The outcomes are expected to contribute to improving remote water quality monitoring and identify the areas most affected by the eutrophication process in the reservoir.