Predicting Canopy Nitrogen Content in Citrus-Trees Using Random Forest Algorithm Associated to Spectral Vegetation Indices from UAV-Imagery
Autor(a) principal: | |
---|---|
Data de Publicação: | 2019 |
Outros Autores: | , , , , , , , , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.3390/rs11242925 http://hdl.handle.net/11449/196489 |
Resumo: | The traditional method of measuring nitrogen content in plants is a time-consuming and labor-intensive task. Spectral vegetation indices extracted from unmanned aerial vehicle (UAV) images and machine learning algorithms have been proved effective in assisting nutritional analysis in plants. Still, this analysis has not considered the combination of spectral indices and machine learning algorithms to predict nitrogen in tree-canopy structures. This paper proposes a new framework to infer the nitrogen content in citrus-tree at a canopy-level using spectral vegetation indices processed with the random forest algorithm. A total of 33 spectral indices were estimated from multispectral images acquired with a UAV-based sensor. Leaf samples were gathered from different planting-fields and the leaf nitrogen content (LNC) was measured in the laboratory, and later converted into the canopy nitrogen content (CNC). To evaluate the robustness of the proposed framework, we compared it with other machine learning algorithms. We used 33,600 citrus trees to evaluate the performance of the machine learning models. The random forest algorithm had higher performance in predicting CNC than all models tested, reaching an R-2 of 0.90, MAE of 0.341 gkg(-1) and MSE of 0.307 gkg(-1). We demonstrated that our approach is able to reduce the need for chemical analysis of the leaf tissue and optimizes citrus orchard CNC monitoring. |
id |
UNSP_817a1db6e60ba6d2ae6a59d1bfc74d68 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/196489 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Predicting Canopy Nitrogen Content in Citrus-Trees Using Random Forest Algorithm Associated to Spectral Vegetation Indices from UAV-ImageryUAV multispectral imageryspectral vegetation indicesmachine learningplant nutritionThe traditional method of measuring nitrogen content in plants is a time-consuming and labor-intensive task. Spectral vegetation indices extracted from unmanned aerial vehicle (UAV) images and machine learning algorithms have been proved effective in assisting nutritional analysis in plants. Still, this analysis has not considered the combination of spectral indices and machine learning algorithms to predict nitrogen in tree-canopy structures. This paper proposes a new framework to infer the nitrogen content in citrus-tree at a canopy-level using spectral vegetation indices processed with the random forest algorithm. A total of 33 spectral indices were estimated from multispectral images acquired with a UAV-based sensor. Leaf samples were gathered from different planting-fields and the leaf nitrogen content (LNC) was measured in the laboratory, and later converted into the canopy nitrogen content (CNC). To evaluate the robustness of the proposed framework, we compared it with other machine learning algorithms. We used 33,600 citrus trees to evaluate the performance of the machine learning models. The random forest algorithm had higher performance in predicting CNC than all models tested, reaching an R-2 of 0.90, MAE of 0.341 gkg(-1) and MSE of 0.307 gkg(-1). We demonstrated that our approach is able to reduce the need for chemical analysis of the leaf tissue and optimizes citrus orchard CNC monitoring.Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)FAPESCConselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)Univ Fed Mato Grosso do Sul, Fac Engn Architecture & Urbanism & Geog, Ave Costa E Silva, BR-79070900 Campo Grande, MS, BrazilUniv Western Sao Paulo, Environm & Reg Dev, R Jose Bongiovani,700-Cidade Univ, BR-19050920 Presidente Prudente, BrazilSao Paulo State Univ, Dept Cartog Sci, BR-19060900 Presidente Prudente, BrazilUniv Fed Mato Grosso do Sul, Fac Comp Sci, Ave Costa E Silva, BR-79070900 Campo Grande, MS, BrazilUniv Waterloo, Dept Geog & Environm Management, Waterloo, ON N2L 3G1, CanadaUniv Waterloo, Dept Syst Design Engn, Waterloo, ON N2L 3G1, CanadaSanta Catarina State Univ UDESC, Forest Engn Dept, Ave Luiz de Camoes 2090, BR-88520000 Conta Dinheiro, SC, BrazilUniv Western Sao Paulo, Agron Dev, R Jose Bongiovani,700 Cidade Univ, BR-19050920 Presidente Prudente, BrazilSao Paulo State Univ, Dept Cartog Sci, BR-19060900 Presidente Prudente, BrazilCAPES: p: 88881.311850/2018-01FAPESC: 2017TR1762CNPq: 313887/2018-7MdpiUniversidade Federal de Mato Grosso do Sul (UFMS)Univ Western Sao PauloUniversidade Estadual Paulista (Unesp)Univ WaterlooSanta Catarina State Univ UDESCOsco, Lucas PradoMarques Ramos, Ana PaulaPereira, Danilo RobertoSaito Moriya, Erika Akemi [UNESP]Imai, Nilton Nobuhiro [UNESP]Matsubara, Edson TakashiEstrabis, NayaraSouza, Mauricio deMarcato Junior, JoseGoncalves, Wesley NunesLi, JonathanLiesenberg, VeraldoCreste, Jose Eduardo2020-12-10T19:46:39Z2020-12-10T19:46:39Z2019-12-02info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article17http://dx.doi.org/10.3390/rs11242925Remote Sensing. Basel: Mdpi, v. 11, n. 24, 17 p., 2019.http://hdl.handle.net/11449/19648910.3390/rs11242925WOS:00050733340004129857711025053300000-0003-0516-0567Web of Sciencereponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengRemote Sensinginfo:eu-repo/semantics/openAccess2024-06-18T15:01:52Zoai:repositorio.unesp.br:11449/196489Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T21:28:57.528164Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Predicting Canopy Nitrogen Content in Citrus-Trees Using Random Forest Algorithm Associated to Spectral Vegetation Indices from UAV-Imagery |
title |
Predicting Canopy Nitrogen Content in Citrus-Trees Using Random Forest Algorithm Associated to Spectral Vegetation Indices from UAV-Imagery |
spellingShingle |
Predicting Canopy Nitrogen Content in Citrus-Trees Using Random Forest Algorithm Associated to Spectral Vegetation Indices from UAV-Imagery Osco, Lucas Prado UAV multispectral imagery spectral vegetation indices machine learning plant nutrition |
title_short |
Predicting Canopy Nitrogen Content in Citrus-Trees Using Random Forest Algorithm Associated to Spectral Vegetation Indices from UAV-Imagery |
title_full |
Predicting Canopy Nitrogen Content in Citrus-Trees Using Random Forest Algorithm Associated to Spectral Vegetation Indices from UAV-Imagery |
title_fullStr |
Predicting Canopy Nitrogen Content in Citrus-Trees Using Random Forest Algorithm Associated to Spectral Vegetation Indices from UAV-Imagery |
title_full_unstemmed |
Predicting Canopy Nitrogen Content in Citrus-Trees Using Random Forest Algorithm Associated to Spectral Vegetation Indices from UAV-Imagery |
title_sort |
Predicting Canopy Nitrogen Content in Citrus-Trees Using Random Forest Algorithm Associated to Spectral Vegetation Indices from UAV-Imagery |
author |
Osco, Lucas Prado |
author_facet |
Osco, Lucas Prado Marques Ramos, Ana Paula Pereira, Danilo Roberto Saito Moriya, Erika Akemi [UNESP] Imai, Nilton Nobuhiro [UNESP] Matsubara, Edson Takashi Estrabis, Nayara Souza, Mauricio de Marcato Junior, Jose Goncalves, Wesley Nunes Li, Jonathan Liesenberg, Veraldo Creste, Jose Eduardo |
author_role |
author |
author2 |
Marques Ramos, Ana Paula Pereira, Danilo Roberto Saito Moriya, Erika Akemi [UNESP] Imai, Nilton Nobuhiro [UNESP] Matsubara, Edson Takashi Estrabis, Nayara Souza, Mauricio de Marcato Junior, Jose Goncalves, Wesley Nunes Li, Jonathan Liesenberg, Veraldo Creste, Jose Eduardo |
author2_role |
author author author author author author author author author author author author |
dc.contributor.none.fl_str_mv |
Universidade Federal de Mato Grosso do Sul (UFMS) Univ Western Sao Paulo Universidade Estadual Paulista (Unesp) Univ Waterloo Santa Catarina State Univ UDESC |
dc.contributor.author.fl_str_mv |
Osco, Lucas Prado Marques Ramos, Ana Paula Pereira, Danilo Roberto Saito Moriya, Erika Akemi [UNESP] Imai, Nilton Nobuhiro [UNESP] Matsubara, Edson Takashi Estrabis, Nayara Souza, Mauricio de Marcato Junior, Jose Goncalves, Wesley Nunes Li, Jonathan Liesenberg, Veraldo Creste, Jose Eduardo |
dc.subject.por.fl_str_mv |
UAV multispectral imagery spectral vegetation indices machine learning plant nutrition |
topic |
UAV multispectral imagery spectral vegetation indices machine learning plant nutrition |
description |
The traditional method of measuring nitrogen content in plants is a time-consuming and labor-intensive task. Spectral vegetation indices extracted from unmanned aerial vehicle (UAV) images and machine learning algorithms have been proved effective in assisting nutritional analysis in plants. Still, this analysis has not considered the combination of spectral indices and machine learning algorithms to predict nitrogen in tree-canopy structures. This paper proposes a new framework to infer the nitrogen content in citrus-tree at a canopy-level using spectral vegetation indices processed with the random forest algorithm. A total of 33 spectral indices were estimated from multispectral images acquired with a UAV-based sensor. Leaf samples were gathered from different planting-fields and the leaf nitrogen content (LNC) was measured in the laboratory, and later converted into the canopy nitrogen content (CNC). To evaluate the robustness of the proposed framework, we compared it with other machine learning algorithms. We used 33,600 citrus trees to evaluate the performance of the machine learning models. The random forest algorithm had higher performance in predicting CNC than all models tested, reaching an R-2 of 0.90, MAE of 0.341 gkg(-1) and MSE of 0.307 gkg(-1). We demonstrated that our approach is able to reduce the need for chemical analysis of the leaf tissue and optimizes citrus orchard CNC monitoring. |
publishDate |
2019 |
dc.date.none.fl_str_mv |
2019-12-02 2020-12-10T19:46:39Z 2020-12-10T19:46:39Z |
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/10.3390/rs11242925 Remote Sensing. Basel: Mdpi, v. 11, n. 24, 17 p., 2019. http://hdl.handle.net/11449/196489 10.3390/rs11242925 WOS:000507333400041 2985771102505330 0000-0003-0516-0567 |
url |
http://dx.doi.org/10.3390/rs11242925 http://hdl.handle.net/11449/196489 |
identifier_str_mv |
Remote Sensing. Basel: Mdpi, v. 11, n. 24, 17 p., 2019. 10.3390/rs11242925 WOS:000507333400041 2985771102505330 0000-0003-0516-0567 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Remote Sensing |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
17 |
dc.publisher.none.fl_str_mv |
Mdpi |
publisher.none.fl_str_mv |
Mdpi |
dc.source.none.fl_str_mv |
Web of Science 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_ |
1808129324460539904 |