A comparison of data mining techniques and multi-sensor analysis for inland marshes delineation
Autor(a) principal: | |
---|---|
Data de Publicação: | 2020 |
Outros Autores: | , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UFRGS |
Texto Completo: | http://hdl.handle.net/10183/250035 |
Resumo: | Inland Marsh (IM) is a type of wetland characterized by the presence of non-woody plants as grasses, reeds or sedges, with a water surface smaller than 25% of the area. Historically, these areas have been suffering impacts related to pollution by urban, industrial and agrochemical waste, as well as drainage for agriculture. The IM delineation allows to understand the vegetation and hydrodynamic dynamics and also to monitor the degradation caused by human-induced activities. This work aimed to compare four machine learning algorithms (classification and regression tree (CART), artificial neural network (ANN), random forest (RF), and k-nearest neighbors (k-NN)) using active and passive remote sensing data in order to address the following questions: (1) which of the four machine learning methods has the greatest potential for inland marshes delineation? (2) are SAR features more important for inland marshes delineation than optical features? and (3) what are the most accurate classification parameters for inland marshes delineation? To address these questions, we used data from Sentinel 1A and Alos Palsar I (SAR) and Sentinel 2A (optical) sensors, in a geographic object-based image analysis (GEOBIA) approach. In addition, we performed a vectorization of a 1975 Brazilian Army topographic chart (first official document presenting marsh boundaries) in order to quantify the marsh area losses between 1975 and 2018 by comparing it with a Sentinel 2A image. Our results showed that the method with the highest overall accuracy was k-NN, with 98.5%. The accuracies for the RF, ANN, and CART methods were 98.3%, 96.0% and 95.5%, respectively. The four classifiers presented accuracies exceeding 95%, showing that all methods have potential for inland marsh delineation. However, we note that the classification results have a great dependence on the input layers. Regarding the importance of the features, SAR images were more important in RF and ANN models, especially in the HV, HV + VH and VH channels of the Alos Palsar I L-band satellite, while spectral indices from optical images were more important in the marshes delineation with the CART method. In addition, we found that the CART and ANN methods presented the largest variations of the overall accuracy (OA) in relation to the different parameters tested. The multi-sensor approach was critical for the high OA values found in the IM delineation (> 95%). The four machine learning methods can be accurately applied for IM delineation, acting as an important low-cost tool for monitoring and managing these environments, in the face of advances in agriculture, soil degradation and pollution of water resources due to agrochemical dumping. |
id |
UFRGS-2_084ec18c54eeb250a6f0d5a8aeae473e |
---|---|
oai_identifier_str |
oai:www.lume.ufrgs.br:10183/250035 |
network_acronym_str |
UFRGS-2 |
network_name_str |
Repositório Institucional da UFRGS |
repository_id_str |
|
spelling |
Simioni, João Paulo DelapasseGuasselli, Laurindo AntônioOliveira, Guilherme Garcia deRuiz, Luis Fernando ChimeloOliveira, Gabriel de2022-10-20T04:43:52Z20201572-9834http://hdl.handle.net/10183/250035001117333Inland Marsh (IM) is a type of wetland characterized by the presence of non-woody plants as grasses, reeds or sedges, with a water surface smaller than 25% of the area. Historically, these areas have been suffering impacts related to pollution by urban, industrial and agrochemical waste, as well as drainage for agriculture. The IM delineation allows to understand the vegetation and hydrodynamic dynamics and also to monitor the degradation caused by human-induced activities. This work aimed to compare four machine learning algorithms (classification and regression tree (CART), artificial neural network (ANN), random forest (RF), and k-nearest neighbors (k-NN)) using active and passive remote sensing data in order to address the following questions: (1) which of the four machine learning methods has the greatest potential for inland marshes delineation? (2) are SAR features more important for inland marshes delineation than optical features? and (3) what are the most accurate classification parameters for inland marshes delineation? To address these questions, we used data from Sentinel 1A and Alos Palsar I (SAR) and Sentinel 2A (optical) sensors, in a geographic object-based image analysis (GEOBIA) approach. In addition, we performed a vectorization of a 1975 Brazilian Army topographic chart (first official document presenting marsh boundaries) in order to quantify the marsh area losses between 1975 and 2018 by comparing it with a Sentinel 2A image. Our results showed that the method with the highest overall accuracy was k-NN, with 98.5%. The accuracies for the RF, ANN, and CART methods were 98.3%, 96.0% and 95.5%, respectively. The four classifiers presented accuracies exceeding 95%, showing that all methods have potential for inland marsh delineation. However, we note that the classification results have a great dependence on the input layers. Regarding the importance of the features, SAR images were more important in RF and ANN models, especially in the HV, HV + VH and VH channels of the Alos Palsar I L-band satellite, while spectral indices from optical images were more important in the marshes delineation with the CART method. In addition, we found that the CART and ANN methods presented the largest variations of the overall accuracy (OA) in relation to the different parameters tested. The multi-sensor approach was critical for the high OA values found in the IM delineation (> 95%). The four machine learning methods can be accurately applied for IM delineation, acting as an important low-cost tool for monitoring and managing these environments, in the face of advances in agriculture, soil degradation and pollution of water resources due to agrochemical dumping.application/pdfengWetlands Ecology and Management. Switzerland. Vol. 28, no. 4 (2020), p. 577-594Gerenciamento remotoImagens SARA comparison of data mining techniques and multi-sensor analysis for inland marshes delineationEstrangeiroinfo:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/openAccessreponame:Repositório Institucional da UFRGSinstname:Universidade Federal do Rio Grande do Sul (UFRGS)instacron:UFRGSTEXT001117333.pdf.txt001117333.pdf.txtExtracted Texttext/plain67763http://www.lume.ufrgs.br/bitstream/10183/250035/2/001117333.pdf.txtb5db828d92c4873d6b644833139fe168MD52ORIGINAL001117333.pdfTexto completo (inglês)application/pdf2320439http://www.lume.ufrgs.br/bitstream/10183/250035/1/001117333.pdf3fa8d516b77b5cfbb8a69720b2b95f75MD5110183/2500352022-10-21 04:57:13.456882oai:www.lume.ufrgs.br:10183/250035Repositório de PublicaçõesPUBhttps://lume.ufrgs.br/oai/requestopendoar:2022-10-21T07:57:13Repositório Institucional da UFRGS - Universidade Federal do Rio Grande do Sul (UFRGS)false |
dc.title.pt_BR.fl_str_mv |
A comparison of data mining techniques and multi-sensor analysis for inland marshes delineation |
title |
A comparison of data mining techniques and multi-sensor analysis for inland marshes delineation |
spellingShingle |
A comparison of data mining techniques and multi-sensor analysis for inland marshes delineation Simioni, João Paulo Delapasse Gerenciamento remoto Imagens SAR |
title_short |
A comparison of data mining techniques and multi-sensor analysis for inland marshes delineation |
title_full |
A comparison of data mining techniques and multi-sensor analysis for inland marshes delineation |
title_fullStr |
A comparison of data mining techniques and multi-sensor analysis for inland marshes delineation |
title_full_unstemmed |
A comparison of data mining techniques and multi-sensor analysis for inland marshes delineation |
title_sort |
A comparison of data mining techniques and multi-sensor analysis for inland marshes delineation |
author |
Simioni, João Paulo Delapasse |
author_facet |
Simioni, João Paulo Delapasse Guasselli, Laurindo Antônio Oliveira, Guilherme Garcia de Ruiz, Luis Fernando Chimelo Oliveira, Gabriel de |
author_role |
author |
author2 |
Guasselli, Laurindo Antônio Oliveira, Guilherme Garcia de Ruiz, Luis Fernando Chimelo Oliveira, Gabriel de |
author2_role |
author author author author |
dc.contributor.author.fl_str_mv |
Simioni, João Paulo Delapasse Guasselli, Laurindo Antônio Oliveira, Guilherme Garcia de Ruiz, Luis Fernando Chimelo Oliveira, Gabriel de |
dc.subject.por.fl_str_mv |
Gerenciamento remoto Imagens SAR |
topic |
Gerenciamento remoto Imagens SAR |
description |
Inland Marsh (IM) is a type of wetland characterized by the presence of non-woody plants as grasses, reeds or sedges, with a water surface smaller than 25% of the area. Historically, these areas have been suffering impacts related to pollution by urban, industrial and agrochemical waste, as well as drainage for agriculture. The IM delineation allows to understand the vegetation and hydrodynamic dynamics and also to monitor the degradation caused by human-induced activities. This work aimed to compare four machine learning algorithms (classification and regression tree (CART), artificial neural network (ANN), random forest (RF), and k-nearest neighbors (k-NN)) using active and passive remote sensing data in order to address the following questions: (1) which of the four machine learning methods has the greatest potential for inland marshes delineation? (2) are SAR features more important for inland marshes delineation than optical features? and (3) what are the most accurate classification parameters for inland marshes delineation? To address these questions, we used data from Sentinel 1A and Alos Palsar I (SAR) and Sentinel 2A (optical) sensors, in a geographic object-based image analysis (GEOBIA) approach. In addition, we performed a vectorization of a 1975 Brazilian Army topographic chart (first official document presenting marsh boundaries) in order to quantify the marsh area losses between 1975 and 2018 by comparing it with a Sentinel 2A image. Our results showed that the method with the highest overall accuracy was k-NN, with 98.5%. The accuracies for the RF, ANN, and CART methods were 98.3%, 96.0% and 95.5%, respectively. The four classifiers presented accuracies exceeding 95%, showing that all methods have potential for inland marsh delineation. However, we note that the classification results have a great dependence on the input layers. Regarding the importance of the features, SAR images were more important in RF and ANN models, especially in the HV, HV + VH and VH channels of the Alos Palsar I L-band satellite, while spectral indices from optical images were more important in the marshes delineation with the CART method. In addition, we found that the CART and ANN methods presented the largest variations of the overall accuracy (OA) in relation to the different parameters tested. The multi-sensor approach was critical for the high OA values found in the IM delineation (> 95%). The four machine learning methods can be accurately applied for IM delineation, acting as an important low-cost tool for monitoring and managing these environments, in the face of advances in agriculture, soil degradation and pollution of water resources due to agrochemical dumping. |
publishDate |
2020 |
dc.date.issued.fl_str_mv |
2020 |
dc.date.accessioned.fl_str_mv |
2022-10-20T04:43:52Z |
dc.type.driver.fl_str_mv |
Estrangeiro info:eu-repo/semantics/article |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/10183/250035 |
dc.identifier.issn.pt_BR.fl_str_mv |
1572-9834 |
dc.identifier.nrb.pt_BR.fl_str_mv |
001117333 |
identifier_str_mv |
1572-9834 001117333 |
url |
http://hdl.handle.net/10183/250035 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.ispartof.pt_BR.fl_str_mv |
Wetlands Ecology and Management. Switzerland. Vol. 28, no. 4 (2020), p. 577-594 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.source.none.fl_str_mv |
reponame:Repositório Institucional da UFRGS instname:Universidade Federal do Rio Grande do Sul (UFRGS) instacron:UFRGS |
instname_str |
Universidade Federal do Rio Grande do Sul (UFRGS) |
instacron_str |
UFRGS |
institution |
UFRGS |
reponame_str |
Repositório Institucional da UFRGS |
collection |
Repositório Institucional da UFRGS |
bitstream.url.fl_str_mv |
http://www.lume.ufrgs.br/bitstream/10183/250035/2/001117333.pdf.txt http://www.lume.ufrgs.br/bitstream/10183/250035/1/001117333.pdf |
bitstream.checksum.fl_str_mv |
b5db828d92c4873d6b644833139fe168 3fa8d516b77b5cfbb8a69720b2b95f75 |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 |
repository.name.fl_str_mv |
Repositório Institucional da UFRGS - Universidade Federal do Rio Grande do Sul (UFRGS) |
repository.mail.fl_str_mv |
|
_version_ |
1801225071190081536 |