A machine learning approach for monitoring Brazilian optical water types using Sentinel-2 MSI

Author(s)

Freire da Silva, Edson Filisbino ^[1] ; Leao de Moraes Novo, Evlyn Marcia ^[1] ; Lobo, Felipe de Lucia ^[2] ; Faria Barbosa, Claudio Clemente ^[3] ; Cairo, Carolline Tressmann ^[3] ; Noernberg, Mauricio Almeida ^[4] ; da Silva Rotta, Luiz Henrique ^[5]

Affiliation

^[1] Natl Inst Space Res, Remote Sensing Div, Sao Jose Dos Campos - Brazil

^[2] Univ Fed Pelotas, CDTec, Pelotas, RS - Brazil

^[3] Natl Inst Space Res, Image Proc Div, Sao Jose Dos Campos - Brazil

^[4] Univ Fed Parana, Ctr Marine Studies, Pontal Do Parana - Brazil

^[5] Sao Paulo State Univ, Dept Cartog, Presidente Prudente - Brazil

• Document type: Journal article
• Source: REMOTE SENSING APPLICATIONS-SOCIETY AND ENVIRONMENT; v. 23, AUG 2021.
• Web of Science Citations: 0

Abstract

Optical Water Type (OWT) is a useful parameter for assessing water quality changes related to different turbidity levels, trophic state and colored dissolved organic matter (CDOM) while also helpful for tuning chlorophyll-a algorithms. For this reason, interest in the satellite remote sensing of OWTs has recently increased in recent years. This study develops a machine learning method for monitoring Brazilian OWTs using the Sentinel-2 MSI, which can detect OWTs already assessed by field measurements and recognize new OWTs. The already assessed OWTs used for calibrating the machine learning algorithm are clear, moderate turbid, eutrophic turbid, eutrophic clear, hypereutrophic, CDOM richest, turbid, and very turbid waters. The classification method consists of two Support Vector Machines for classifying the known OWTs, while a novelty detection method based on sigmoid functions is used for assessing new OWTs. Results show the classification based on Sentinel-2 MSI bands simulated using field radiometric data is accurate (accuracy = 0.94). However, when radiometric errors are simulated, the accuracy significantly decreases to 0.75, 0.56, 0.45, and 0.37 as the mean absolute percent error increases to 10%, 20%, 30%, and 40%, respectively. Considering the errors retrieved when comparing the field and satellite measurements, the expected accuracy of Sentinel-2 MSI images is 0.78. In the satellite images, the novelty detection distinguishes new OWTs originated from the mixture among the known OWTs and a new OWT that was not part of the training database (clear blue waters). Two examples of time series in the Funil reservoir and the Curuai lake are used to show the applicability of monitoring OWTs. In the Funil reservoir, OWTs could indicate eutrophication and turbid changes caused by river inflow and sediment sinking. In the Curuai lake, OWTs could indicate areas susceptible to algae bloom and turbidity increases related to river inflow and particle resuspension. In the future, the proposed algorithm could be used for large-scale assessment of water quality degradation and supports rapid mitigation and recovery responses. For improving the classification accuracy, adjacency correction and more robust glint removal methods should be developed. (AU)

• FAPESP's process: 12/19821-1 - Bio-optical model parametrization to study the chlorophyll-A concentration along a cascade of reservoirs
• Grantee: Enner Herenio de Alcântara
• Support Opportunities: Regular Research Grants
• FAPESP's process: 13/09045-7 - Submersed aquatic vegetation - SAV mapping based on radiative transfer theory - RTT in water bodies
• Grantee: Nilton Nobuhiro Imai
• Support Opportunities: Regular Research Grants
• FAPESP's process: 14/23903-9 - Bio-optical spatio-temporal characterization and development of analytical algorithms for the systematic monitoring of water masses circulating on the floodplain of medium and lower Amazon
• Grantee: Cláudio Clemente Faria Barbosa
• Support Opportunities: Regular Research Grants
• FAPESP's process: 08/56252-0 - Environmental and socioeconomic impacts associated with the production and consumption of sugarcane ethanol in south central Brazil
• Grantee: Evlyn Márcia Leão de Moraes Novo
• Support Opportunities: Program for Research on Bioenergy (BIOEN) - Thematic Grants