A machine learning approach for monitoring Brazilian optical water types using Sentinel-2 MSI
Autor(a) principal: | |
---|---|
Data de Publicação: | 2021 |
Outros Autores: | , , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1016/j.rsase.2021.100577 http://hdl.handle.net/11449/229116 |
Resumo: | 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. |
id |
UNSP_229cc2b9bdb6413ff6a69ea4943c174c |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/229116 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
A machine learning approach for monitoring Brazilian optical water types using Sentinel-2 MSIClassificationMachine learningNovelty detectionOptical water typeOptical 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.Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)Remote Sensing Division National Institute for Space ResearchCDTec Federal University of PelotasImage Processing Division National Institute for Space ResearchCenter of Marine Studies Federal University of ParanáDepartment of Cartography São Paulo State UniversityDepartment of Cartography São Paulo State UniversityFAPESP: 2008/56252–0FAPESP: 2012/19821–1FAPESP: 2013/09045–7FAPESP: 2014/23903–9National Institute for Space ResearchFederal University of PelotasFederal University of ParanáUniversidade Estadual Paulista (UNESP)Filisbino Freire da Silva, EdsonMárcia Leão de Moraes Novo, Evlynde Lucia Lobo, FelipeClemente Faria Barbosa, CláudioTressmann Cairo, CarollineAlmeida Noernberg, MauricioHenrique da Silva Rotta, Luiz [UNESP]2022-04-29T08:30:36Z2022-04-29T08:30:36Z2021-08-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlehttp://dx.doi.org/10.1016/j.rsase.2021.100577Remote Sensing Applications: Society and Environment, v. 23.2352-9385http://hdl.handle.net/11449/22911610.1016/j.rsase.2021.1005772-s2.0-85109553891Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengRemote Sensing Applications: Society and Environmentinfo:eu-repo/semantics/openAccess2024-06-18T15:01:39Zoai:repositorio.unesp.br:11449/229116Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-06-18T15:01:39Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
A machine learning approach for monitoring Brazilian optical water types using Sentinel-2 MSI |
title |
A machine learning approach for monitoring Brazilian optical water types using Sentinel-2 MSI |
spellingShingle |
A machine learning approach for monitoring Brazilian optical water types using Sentinel-2 MSI Filisbino Freire da Silva, Edson Classification Machine learning Novelty detection Optical water type |
title_short |
A machine learning approach for monitoring Brazilian optical water types using Sentinel-2 MSI |
title_full |
A machine learning approach for monitoring Brazilian optical water types using Sentinel-2 MSI |
title_fullStr |
A machine learning approach for monitoring Brazilian optical water types using Sentinel-2 MSI |
title_full_unstemmed |
A machine learning approach for monitoring Brazilian optical water types using Sentinel-2 MSI |
title_sort |
A machine learning approach for monitoring Brazilian optical water types using Sentinel-2 MSI |
author |
Filisbino Freire da Silva, Edson |
author_facet |
Filisbino Freire da Silva, Edson Márcia Leão de Moraes Novo, Evlyn de Lucia Lobo, Felipe Clemente Faria Barbosa, Cláudio Tressmann Cairo, Carolline Almeida Noernberg, Mauricio Henrique da Silva Rotta, Luiz [UNESP] |
author_role |
author |
author2 |
Márcia Leão de Moraes Novo, Evlyn de Lucia Lobo, Felipe Clemente Faria Barbosa, Cláudio Tressmann Cairo, Carolline Almeida Noernberg, Mauricio Henrique da Silva Rotta, Luiz [UNESP] |
author2_role |
author author author author author author |
dc.contributor.none.fl_str_mv |
National Institute for Space Research Federal University of Pelotas Federal University of Paraná Universidade Estadual Paulista (UNESP) |
dc.contributor.author.fl_str_mv |
Filisbino Freire da Silva, Edson Márcia Leão de Moraes Novo, Evlyn de Lucia Lobo, Felipe Clemente Faria Barbosa, Cláudio Tressmann Cairo, Carolline Almeida Noernberg, Mauricio Henrique da Silva Rotta, Luiz [UNESP] |
dc.subject.por.fl_str_mv |
Classification Machine learning Novelty detection Optical water type |
topic |
Classification Machine learning Novelty detection Optical water type |
description |
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. |
publishDate |
2021 |
dc.date.none.fl_str_mv |
2021-08-01 2022-04-29T08:30:36Z 2022-04-29T08:30:36Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://dx.doi.org/10.1016/j.rsase.2021.100577 Remote Sensing Applications: Society and Environment, v. 23. 2352-9385 http://hdl.handle.net/11449/229116 10.1016/j.rsase.2021.100577 2-s2.0-85109553891 |
url |
http://dx.doi.org/10.1016/j.rsase.2021.100577 http://hdl.handle.net/11449/229116 |
identifier_str_mv |
Remote Sensing Applications: Society and Environment, v. 23. 2352-9385 10.1016/j.rsase.2021.100577 2-s2.0-85109553891 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Remote Sensing Applications: Society and Environment |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.source.none.fl_str_mv |
Scopus reponame:Repositório Institucional da UNESP instname:Universidade Estadual Paulista (UNESP) instacron:UNESP |
instname_str |
Universidade Estadual Paulista (UNESP) |
instacron_str |
UNESP |
institution |
UNESP |
reponame_str |
Repositório Institucional da UNESP |
collection |
Repositório Institucional da UNESP |
repository.name.fl_str_mv |
Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP) |
repository.mail.fl_str_mv |
|
_version_ |
1803045394414829568 |