SOIL MOISTURE ESTIMATION THROUGH MACHINE LEARNING USING UNMANNED AERIAL VEHICLE (UAV) IMAGES
Autor(a) principal: | |
---|---|
Data de Publicação: | 2021 |
Outros Autores: | , |
Tipo de documento: | Artigo |
Idioma: | por |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.15809/irriga.2021v26n3p684-700 http://hdl.handle.net/11449/240944 |
Resumo: | The soil moisture is an important parameter for the calculation of water depth and irrigation management since it is directly related to the soil water content. Remote sensing techniques combined with statistical models can be used to estimate the spatial variability of soil moisture, extrapolating point measurements. The objective of this study was to determine the soil moisture through machine learning algorithms such as Support Vector Regression (SVR), Random Forests (RF), and Artificial Neural Networks (ANN). High resolution multispectral images obtained by an Unmanned Aerial Vehicle (UAV) in an irrigated bean area at the Experimental Lageado Farm at Unesp in Botucatu, SP, Brazil, were used. The reflectances in the Green, Red and Near Infrared bands along with the NDVI vegetation index were used as inputs for the models. All the algorithms performed well; however, the model that best fitted the data was the SVR, with mean square error (RMSE) of 0.46% of the estimated soil moisture and determination coefficient (R²) of 0.71. |
id |
UNSP_6fd38252212d6b1f2decae1e0431fa4f |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/240944 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
SOIL MOISTURE ESTIMATION THROUGH MACHINE LEARNING USING UNMANNED AERIAL VEHICLE (UAV) IMAGESESTIMATIVA DE UMIDADE DO SOLO POR MEIO DE APRENDIZADO DE MÁQUINA USANDO IMAGENS DE VEICULO AÉREO NÃO TRIPULADO (VANT)artificial neural networksmachine learningsoil moistureUAVThe soil moisture is an important parameter for the calculation of water depth and irrigation management since it is directly related to the soil water content. Remote sensing techniques combined with statistical models can be used to estimate the spatial variability of soil moisture, extrapolating point measurements. The objective of this study was to determine the soil moisture through machine learning algorithms such as Support Vector Regression (SVR), Random Forests (RF), and Artificial Neural Networks (ANN). High resolution multispectral images obtained by an Unmanned Aerial Vehicle (UAV) in an irrigated bean area at the Experimental Lageado Farm at Unesp in Botucatu, SP, Brazil, were used. The reflectances in the Green, Red and Near Infrared bands along with the NDVI vegetation index were used as inputs for the models. All the algorithms performed well; however, the model that best fitted the data was the SVR, with mean square error (RMSE) of 0.46% of the estimated soil moisture and determination coefficient (R²) of 0.71.Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)Departamento de Engenharia Rural UNESP-Faculdade de Ciências Agronômicas, R. José Barbosa de Barros, 1780, SPDepartamento de Engenharia Rural UNESP-Faculdade de Ciências Agronômicas, R. José Barbosa de Barros, 1780, SPCNPq: 131325/2020-5CAPES: DS 88882.433001/2019-01Universidade Estadual Paulista (UNESP)Safre, Anderson Luiz dos Santos [UNESP]Fernandes, Caio Nascimento [UNESP]Saad, João Carlos Cury [UNESP]2023-03-01T20:39:52Z2023-03-01T20:39:52Z2021-07-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article684-700http://dx.doi.org/10.15809/irriga.2021v26n3p684-700IRRIGA, v. 26, n. 3, p. 684-700, 2021.1808-37651413-7895http://hdl.handle.net/11449/24094410.15809/irriga.2021v26n3p684-7002-s2.0-85129495947Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPporIRRIGAinfo:eu-repo/semantics/openAccess2024-04-30T14:01:20Zoai:repositorio.unesp.br:11449/240944Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T19:21:36.627309Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
SOIL MOISTURE ESTIMATION THROUGH MACHINE LEARNING USING UNMANNED AERIAL VEHICLE (UAV) IMAGES ESTIMATIVA DE UMIDADE DO SOLO POR MEIO DE APRENDIZADO DE MÁQUINA USANDO IMAGENS DE VEICULO AÉREO NÃO TRIPULADO (VANT) |
title |
SOIL MOISTURE ESTIMATION THROUGH MACHINE LEARNING USING UNMANNED AERIAL VEHICLE (UAV) IMAGES |
spellingShingle |
SOIL MOISTURE ESTIMATION THROUGH MACHINE LEARNING USING UNMANNED AERIAL VEHICLE (UAV) IMAGES Safre, Anderson Luiz dos Santos [UNESP] artificial neural networks machine learning soil moisture UAV |
title_short |
SOIL MOISTURE ESTIMATION THROUGH MACHINE LEARNING USING UNMANNED AERIAL VEHICLE (UAV) IMAGES |
title_full |
SOIL MOISTURE ESTIMATION THROUGH MACHINE LEARNING USING UNMANNED AERIAL VEHICLE (UAV) IMAGES |
title_fullStr |
SOIL MOISTURE ESTIMATION THROUGH MACHINE LEARNING USING UNMANNED AERIAL VEHICLE (UAV) IMAGES |
title_full_unstemmed |
SOIL MOISTURE ESTIMATION THROUGH MACHINE LEARNING USING UNMANNED AERIAL VEHICLE (UAV) IMAGES |
title_sort |
SOIL MOISTURE ESTIMATION THROUGH MACHINE LEARNING USING UNMANNED AERIAL VEHICLE (UAV) IMAGES |
author |
Safre, Anderson Luiz dos Santos [UNESP] |
author_facet |
Safre, Anderson Luiz dos Santos [UNESP] Fernandes, Caio Nascimento [UNESP] Saad, João Carlos Cury [UNESP] |
author_role |
author |
author2 |
Fernandes, Caio Nascimento [UNESP] Saad, João Carlos Cury [UNESP] |
author2_role |
author author |
dc.contributor.none.fl_str_mv |
Universidade Estadual Paulista (UNESP) |
dc.contributor.author.fl_str_mv |
Safre, Anderson Luiz dos Santos [UNESP] Fernandes, Caio Nascimento [UNESP] Saad, João Carlos Cury [UNESP] |
dc.subject.por.fl_str_mv |
artificial neural networks machine learning soil moisture UAV |
topic |
artificial neural networks machine learning soil moisture UAV |
description |
The soil moisture is an important parameter for the calculation of water depth and irrigation management since it is directly related to the soil water content. Remote sensing techniques combined with statistical models can be used to estimate the spatial variability of soil moisture, extrapolating point measurements. The objective of this study was to determine the soil moisture through machine learning algorithms such as Support Vector Regression (SVR), Random Forests (RF), and Artificial Neural Networks (ANN). High resolution multispectral images obtained by an Unmanned Aerial Vehicle (UAV) in an irrigated bean area at the Experimental Lageado Farm at Unesp in Botucatu, SP, Brazil, were used. The reflectances in the Green, Red and Near Infrared bands along with the NDVI vegetation index were used as inputs for the models. All the algorithms performed well; however, the model that best fitted the data was the SVR, with mean square error (RMSE) of 0.46% of the estimated soil moisture and determination coefficient (R²) of 0.71. |
publishDate |
2021 |
dc.date.none.fl_str_mv |
2021-07-01 2023-03-01T20:39:52Z 2023-03-01T20:39:52Z |
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/10.15809/irriga.2021v26n3p684-700 IRRIGA, v. 26, n. 3, p. 684-700, 2021. 1808-3765 1413-7895 http://hdl.handle.net/11449/240944 10.15809/irriga.2021v26n3p684-700 2-s2.0-85129495947 |
url |
http://dx.doi.org/10.15809/irriga.2021v26n3p684-700 http://hdl.handle.net/11449/240944 |
identifier_str_mv |
IRRIGA, v. 26, n. 3, p. 684-700, 2021. 1808-3765 1413-7895 10.15809/irriga.2021v26n3p684-700 2-s2.0-85129495947 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.relation.none.fl_str_mv |
IRRIGA |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
684-700 |
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_ |
1808129058011086848 |