A machine learning framework to predict nutrient content in valencia-orange leaf hyperspectral measurements
Autor(a) principal: | |
---|---|
Data de Publicação: | 2020 |
Outros Autores: | , , , , , , , , , , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.3390/rs12060906 http://hdl.handle.net/11449/200205 |
Resumo: | This paper presents a framework based on machine learning algorithms to predict nutrient content in leaf hyperspectral measurements. This is the first approach to evaluate macro-and micronutrient content with both machine learning and reflectance/first-derivative data. For this, citrus-leaves collected at a Valencia-orange orchard were used. Their spectral data was measured with a Fieldspec ASD FieldSpec® HandHeld 2 spectroradiometer and the surface reflectance and first-derivative spectra from the spectral range of 380 to 1020 nm (640 spectral bands) was evaluated. A total of 320 spectral signatures were collected, and the leaf-nutrient content (N, P, K, Mg, S, Cu, Fe, Mn, and Zn) was associated with them. For this, 204,800 (320 x 640) combinations were used. The following machine learning algorithms were used in this framework: k-Nearest Neighbor (kNN), Lasso Regression, Ridge Regression, Support Vector Machine (SVM), Artificial Neural Network (ANN), Decision Tree (DT), and Random Forest (RF). The training methods were assessed based on Cross-Validation and Leave-One-Out. The Relief-F metric of the algorithms' prediction was used to determine the most contributive wavelength or spectral region associated with each nutrient. This approach was able to return, with high predictions (R2), nutrients like N (0.912), Mg (0.832), Cu (0.861), Mn (0.898), and Zn (0.855), and, to a lesser extent, P (0.771), K (0.763), and S (0.727). These accuracies were obtained with different algorithms, but RF was the most suitable to model most of them. The results indicate that, for the Valencia-orange leaves, surface reflectance data is more suitable to predict macronutrients, while first-derivative spectra is better linked to micronutrients. A final contribution of this study is the identification of the wavelengths responsible for contributing to these predictions |
id |
UNSP_fe45a8b17d59ee9d00baf3010d9786a7 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/200205 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
A machine learning framework to predict nutrient content in valencia-orange leaf hyperspectral measurementsArtificial intelligenceMacronutrientMicronutrientProximal sensorSpectroscopyThis paper presents a framework based on machine learning algorithms to predict nutrient content in leaf hyperspectral measurements. This is the first approach to evaluate macro-and micronutrient content with both machine learning and reflectance/first-derivative data. For this, citrus-leaves collected at a Valencia-orange orchard were used. Their spectral data was measured with a Fieldspec ASD FieldSpec® HandHeld 2 spectroradiometer and the surface reflectance and first-derivative spectra from the spectral range of 380 to 1020 nm (640 spectral bands) was evaluated. A total of 320 spectral signatures were collected, and the leaf-nutrient content (N, P, K, Mg, S, Cu, Fe, Mn, and Zn) was associated with them. For this, 204,800 (320 x 640) combinations were used. The following machine learning algorithms were used in this framework: k-Nearest Neighbor (kNN), Lasso Regression, Ridge Regression, Support Vector Machine (SVM), Artificial Neural Network (ANN), Decision Tree (DT), and Random Forest (RF). The training methods were assessed based on Cross-Validation and Leave-One-Out. The Relief-F metric of the algorithms' prediction was used to determine the most contributive wavelength or spectral region associated with each nutrient. This approach was able to return, with high predictions (R2), nutrients like N (0.912), Mg (0.832), Cu (0.861), Mn (0.898), and Zn (0.855), and, to a lesser extent, P (0.771), K (0.763), and S (0.727). These accuracies were obtained with different algorithms, but RF was the most suitable to model most of them. The results indicate that, for the Valencia-orange leaves, surface reflectance data is more suitable to predict macronutrients, while first-derivative spectra is better linked to micronutrients. A final contribution of this study is the identification of the wavelengths responsible for contributing to these predictionsFederal University of Mato Grosso do Sul (UFMS)Environmental and Regional Development University of Western São Paulo (UNOESTE)Department of Cartographic Science São Paulo State University (UNESP)Department of Agronomy University of Western São Paulo (UNOESTE)Forest Engineering Department Santa Catarina State University (UDESC)National Research Center of Development of Agricultural Instrumentation Brazilian Agricultural Research Agency (EMBRAPA)Department of Geography and Environmental Management and Department of Systems Design Engineering University of Waterloo (UW)Department of Cartographic Science São Paulo State University (UNESP)Universidade Federal de Mato Grosso do Sul (UFMS)University of Western São Paulo (UNOESTE)Universidade Estadual Paulista (Unesp)Santa Catarina State University (UDESC)Empresa Brasileira de Pesquisa Agropecuária (EMBRAPA)University of Waterloo (UW)Osco, Lucas PradoRamos, Ana Paula MarquesPinheiro, Mayara Maezano FaitaMoriya, Érika Akemi Saito [UNESP]Imai, Nilton Nobuhiro [UNESP]Estrabis, NayaraIanczyk, Felipede Araújo, Fábio FernandoLiesenberg, Veraldode Castro Jorge, Lúcio AndréLi, JonathanMa, LingfeiGonçalves, Wesley NunesMarcato, JoséCreste, José Eduardo2020-12-12T02:00:26Z2020-12-12T02:00:26Z2020-03-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlehttp://dx.doi.org/10.3390/rs12060906Remote Sensing, v. 12, n. 6, 2020.2072-4292http://hdl.handle.net/11449/20020510.3390/rs120609062-s2.0-8508230434229857711025053300000-0003-0516-0567Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengRemote Sensinginfo:eu-repo/semantics/openAccess2021-10-23T12:31:23Zoai:repositorio.unesp.br:11449/200205Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462021-10-23T12:31:23Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
A machine learning framework to predict nutrient content in valencia-orange leaf hyperspectral measurements |
title |
A machine learning framework to predict nutrient content in valencia-orange leaf hyperspectral measurements |
spellingShingle |
A machine learning framework to predict nutrient content in valencia-orange leaf hyperspectral measurements Osco, Lucas Prado Artificial intelligence Macronutrient Micronutrient Proximal sensor Spectroscopy |
title_short |
A machine learning framework to predict nutrient content in valencia-orange leaf hyperspectral measurements |
title_full |
A machine learning framework to predict nutrient content in valencia-orange leaf hyperspectral measurements |
title_fullStr |
A machine learning framework to predict nutrient content in valencia-orange leaf hyperspectral measurements |
title_full_unstemmed |
A machine learning framework to predict nutrient content in valencia-orange leaf hyperspectral measurements |
title_sort |
A machine learning framework to predict nutrient content in valencia-orange leaf hyperspectral measurements |
author |
Osco, Lucas Prado |
author_facet |
Osco, Lucas Prado Ramos, Ana Paula Marques Pinheiro, Mayara Maezano Faita Moriya, Érika Akemi Saito [UNESP] Imai, Nilton Nobuhiro [UNESP] Estrabis, Nayara Ianczyk, Felipe de Araújo, Fábio Fernando Liesenberg, Veraldo de Castro Jorge, Lúcio André Li, Jonathan Ma, Lingfei Gonçalves, Wesley Nunes Marcato, José Creste, José Eduardo |
author_role |
author |
author2 |
Ramos, Ana Paula Marques Pinheiro, Mayara Maezano Faita Moriya, Érika Akemi Saito [UNESP] Imai, Nilton Nobuhiro [UNESP] Estrabis, Nayara Ianczyk, Felipe de Araújo, Fábio Fernando Liesenberg, Veraldo de Castro Jorge, Lúcio André Li, Jonathan Ma, Lingfei Gonçalves, Wesley Nunes Marcato, José Creste, José Eduardo |
author2_role |
author author 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) University of Western São Paulo (UNOESTE) Universidade Estadual Paulista (Unesp) Santa Catarina State University (UDESC) Empresa Brasileira de Pesquisa Agropecuária (EMBRAPA) University of Waterloo (UW) |
dc.contributor.author.fl_str_mv |
Osco, Lucas Prado Ramos, Ana Paula Marques Pinheiro, Mayara Maezano Faita Moriya, Érika Akemi Saito [UNESP] Imai, Nilton Nobuhiro [UNESP] Estrabis, Nayara Ianczyk, Felipe de Araújo, Fábio Fernando Liesenberg, Veraldo de Castro Jorge, Lúcio André Li, Jonathan Ma, Lingfei Gonçalves, Wesley Nunes Marcato, José Creste, José Eduardo |
dc.subject.por.fl_str_mv |
Artificial intelligence Macronutrient Micronutrient Proximal sensor Spectroscopy |
topic |
Artificial intelligence Macronutrient Micronutrient Proximal sensor Spectroscopy |
description |
This paper presents a framework based on machine learning algorithms to predict nutrient content in leaf hyperspectral measurements. This is the first approach to evaluate macro-and micronutrient content with both machine learning and reflectance/first-derivative data. For this, citrus-leaves collected at a Valencia-orange orchard were used. Their spectral data was measured with a Fieldspec ASD FieldSpec® HandHeld 2 spectroradiometer and the surface reflectance and first-derivative spectra from the spectral range of 380 to 1020 nm (640 spectral bands) was evaluated. A total of 320 spectral signatures were collected, and the leaf-nutrient content (N, P, K, Mg, S, Cu, Fe, Mn, and Zn) was associated with them. For this, 204,800 (320 x 640) combinations were used. The following machine learning algorithms were used in this framework: k-Nearest Neighbor (kNN), Lasso Regression, Ridge Regression, Support Vector Machine (SVM), Artificial Neural Network (ANN), Decision Tree (DT), and Random Forest (RF). The training methods were assessed based on Cross-Validation and Leave-One-Out. The Relief-F metric of the algorithms' prediction was used to determine the most contributive wavelength or spectral region associated with each nutrient. This approach was able to return, with high predictions (R2), nutrients like N (0.912), Mg (0.832), Cu (0.861), Mn (0.898), and Zn (0.855), and, to a lesser extent, P (0.771), K (0.763), and S (0.727). These accuracies were obtained with different algorithms, but RF was the most suitable to model most of them. The results indicate that, for the Valencia-orange leaves, surface reflectance data is more suitable to predict macronutrients, while first-derivative spectra is better linked to micronutrients. A final contribution of this study is the identification of the wavelengths responsible for contributing to these predictions |
publishDate |
2020 |
dc.date.none.fl_str_mv |
2020-12-12T02:00:26Z 2020-12-12T02:00:26Z 2020-03-01 |
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/rs12060906 Remote Sensing, v. 12, n. 6, 2020. 2072-4292 http://hdl.handle.net/11449/200205 10.3390/rs12060906 2-s2.0-85082304342 2985771102505330 0000-0003-0516-0567 |
url |
http://dx.doi.org/10.3390/rs12060906 http://hdl.handle.net/11449/200205 |
identifier_str_mv |
Remote Sensing, v. 12, n. 6, 2020. 2072-4292 10.3390/rs12060906 2-s2.0-85082304342 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.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_ |
1799964775779663872 |