Soybean Cultivars Identification Using Remotely Sensed Image and Machine Learning Models
Autor(a) principal: | |
---|---|
Data de Publicação: | 2022 |
Outros Autores: | , , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.3390/su14127125 http://hdl.handle.net/11449/240272 |
Resumo: | Using remote sensing combined with machine learning (ML) techniques is a promising approach to classify soybean cultivars. Therefore, the objectives of this study are (i) to verify which input dataset configuration (using only spectral bands, only vegetation indices, or both) is more accurate in the identification of soybean cultivars, and (ii) to verify which ML technique is more accurate in the identification of soybean cultivars. Information was extracted from five central irrigation pivots in the same region and with the same sowing date in the 2015/2016 crop year, in which each pivot was cultivated with a different cultivar, in which the cultivars used were: CV1—P98y12 RR, CV2—Desafio RR, CV3—M6410 IPRO, CV4—M7110 IPRO, and CV5—NA5909 RR. A cloud-free orbital image of the site was acquired from the Google Earth Engine platform. In addition to the spectral bands alone, a total of 13 vegetation indices were calculated. The models tested were: artificial neural networks (ANN), radial basis function network (RBF), decision tree algorithms J48 (DT) and reduced error pruning tree (REP), random forest (RF), and support vector machine (SVM). The five soybean cultivars were classified by the six-machine learning (ML) models in stratified randomized cross-validation with k-fold = 10 and 10 repetitions (100 runs for each model). After obtaining the r and MAE statistics, analysis of variance was performed considering a 6 × 3 factorial scheme (models versus inputs) with 10 repetitions (folds). The means were grouped by the Scott–Knott test at 5% probability. The spectral bands were the most accurate among the tested inputs in the identification of soybean cultivars. ANN was the most accurate model in identifying soybean cultivars. |
id |
UNSP_76c8579164585476b753ad76db6cabb9 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/240272 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Soybean Cultivars Identification Using Remotely Sensed Image and Machine Learning Modelsartificial neural networkLandsatrandom forestremote sensingspectral bandsvegetation indicesUsing remote sensing combined with machine learning (ML) techniques is a promising approach to classify soybean cultivars. Therefore, the objectives of this study are (i) to verify which input dataset configuration (using only spectral bands, only vegetation indices, or both) is more accurate in the identification of soybean cultivars, and (ii) to verify which ML technique is more accurate in the identification of soybean cultivars. Information was extracted from five central irrigation pivots in the same region and with the same sowing date in the 2015/2016 crop year, in which each pivot was cultivated with a different cultivar, in which the cultivars used were: CV1—P98y12 RR, CV2—Desafio RR, CV3—M6410 IPRO, CV4—M7110 IPRO, and CV5—NA5909 RR. A cloud-free orbital image of the site was acquired from the Google Earth Engine platform. In addition to the spectral bands alone, a total of 13 vegetation indices were calculated. The models tested were: artificial neural networks (ANN), radial basis function network (RBF), decision tree algorithms J48 (DT) and reduced error pruning tree (REP), random forest (RF), and support vector machine (SVM). The five soybean cultivars were classified by the six-machine learning (ML) models in stratified randomized cross-validation with k-fold = 10 and 10 repetitions (100 runs for each model). After obtaining the r and MAE statistics, analysis of variance was performed considering a 6 × 3 factorial scheme (models versus inputs) with 10 repetitions (folds). The means were grouped by the Scott–Knott test at 5% probability. The spectral bands were the most accurate among the tested inputs in the identification of soybean cultivars. ANN was the most accurate model in identifying soybean cultivars.Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)Department of Agronomy Federal University of Mato Grosso do Sul (UFMS), Mato Grosso do SulGraduate Program in Plant Production State University of São Paulo (UNESP), São PauloGraduate Program in Soil Science State University of São Paulo (UNESP), São PauloDepartment of Geography State University of Mato Grosso (UNEMAT), Mato GrossoGraduate Program in Plant Production State University of São Paulo (UNESP), São PauloGraduate Program in Soil Science State University of São Paulo (UNESP), São PauloCAPES: 001CNPq: 303767/2020-0CNPq: 309250/2021-8Universidade Federal de Mato Grosso do Sul (UFMS)Universidade Estadual Paulista (UNESP)State University of Mato Grosso (UNEMAT)Gava, RicardoSantana, Dthenifer Cordeiro [UNESP]Cotrim, Mayara Favero [UNESP]Rossi, Fernando Saragosa [UNESP]Teodoro, Larissa Pereira RibeiroSilva Junior, Carlos Antonio daTeodoro, Paulo Eduardo2023-03-01T20:09:24Z2023-03-01T20:09:24Z2022-06-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlehttp://dx.doi.org/10.3390/su14127125Sustainability (Switzerland), v. 14, n. 12, 2022.2071-1050http://hdl.handle.net/11449/24027210.3390/su141271252-s2.0-85132207040Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengSustainability (Switzerland)info:eu-repo/semantics/openAccess2023-03-01T20:09:24Zoai:repositorio.unesp.br:11449/240272Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462023-03-01T20:09:24Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Soybean Cultivars Identification Using Remotely Sensed Image and Machine Learning Models |
title |
Soybean Cultivars Identification Using Remotely Sensed Image and Machine Learning Models |
spellingShingle |
Soybean Cultivars Identification Using Remotely Sensed Image and Machine Learning Models Gava, Ricardo artificial neural network Landsat random forest remote sensing spectral bands vegetation indices |
title_short |
Soybean Cultivars Identification Using Remotely Sensed Image and Machine Learning Models |
title_full |
Soybean Cultivars Identification Using Remotely Sensed Image and Machine Learning Models |
title_fullStr |
Soybean Cultivars Identification Using Remotely Sensed Image and Machine Learning Models |
title_full_unstemmed |
Soybean Cultivars Identification Using Remotely Sensed Image and Machine Learning Models |
title_sort |
Soybean Cultivars Identification Using Remotely Sensed Image and Machine Learning Models |
author |
Gava, Ricardo |
author_facet |
Gava, Ricardo Santana, Dthenifer Cordeiro [UNESP] Cotrim, Mayara Favero [UNESP] Rossi, Fernando Saragosa [UNESP] Teodoro, Larissa Pereira Ribeiro Silva Junior, Carlos Antonio da Teodoro, Paulo Eduardo |
author_role |
author |
author2 |
Santana, Dthenifer Cordeiro [UNESP] Cotrim, Mayara Favero [UNESP] Rossi, Fernando Saragosa [UNESP] Teodoro, Larissa Pereira Ribeiro Silva Junior, Carlos Antonio da Teodoro, Paulo Eduardo |
author2_role |
author author author author author author |
dc.contributor.none.fl_str_mv |
Universidade Federal de Mato Grosso do Sul (UFMS) Universidade Estadual Paulista (UNESP) State University of Mato Grosso (UNEMAT) |
dc.contributor.author.fl_str_mv |
Gava, Ricardo Santana, Dthenifer Cordeiro [UNESP] Cotrim, Mayara Favero [UNESP] Rossi, Fernando Saragosa [UNESP] Teodoro, Larissa Pereira Ribeiro Silva Junior, Carlos Antonio da Teodoro, Paulo Eduardo |
dc.subject.por.fl_str_mv |
artificial neural network Landsat random forest remote sensing spectral bands vegetation indices |
topic |
artificial neural network Landsat random forest remote sensing spectral bands vegetation indices |
description |
Using remote sensing combined with machine learning (ML) techniques is a promising approach to classify soybean cultivars. Therefore, the objectives of this study are (i) to verify which input dataset configuration (using only spectral bands, only vegetation indices, or both) is more accurate in the identification of soybean cultivars, and (ii) to verify which ML technique is more accurate in the identification of soybean cultivars. Information was extracted from five central irrigation pivots in the same region and with the same sowing date in the 2015/2016 crop year, in which each pivot was cultivated with a different cultivar, in which the cultivars used were: CV1—P98y12 RR, CV2—Desafio RR, CV3—M6410 IPRO, CV4—M7110 IPRO, and CV5—NA5909 RR. A cloud-free orbital image of the site was acquired from the Google Earth Engine platform. In addition to the spectral bands alone, a total of 13 vegetation indices were calculated. The models tested were: artificial neural networks (ANN), radial basis function network (RBF), decision tree algorithms J48 (DT) and reduced error pruning tree (REP), random forest (RF), and support vector machine (SVM). The five soybean cultivars were classified by the six-machine learning (ML) models in stratified randomized cross-validation with k-fold = 10 and 10 repetitions (100 runs for each model). After obtaining the r and MAE statistics, analysis of variance was performed considering a 6 × 3 factorial scheme (models versus inputs) with 10 repetitions (folds). The means were grouped by the Scott–Knott test at 5% probability. The spectral bands were the most accurate among the tested inputs in the identification of soybean cultivars. ANN was the most accurate model in identifying soybean cultivars. |
publishDate |
2022 |
dc.date.none.fl_str_mv |
2022-06-01 2023-03-01T20:09:24Z 2023-03-01T20:09:24Z |
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/su14127125 Sustainability (Switzerland), v. 14, n. 12, 2022. 2071-1050 http://hdl.handle.net/11449/240272 10.3390/su14127125 2-s2.0-85132207040 |
url |
http://dx.doi.org/10.3390/su14127125 http://hdl.handle.net/11449/240272 |
identifier_str_mv |
Sustainability (Switzerland), v. 14, n. 12, 2022. 2071-1050 10.3390/su14127125 2-s2.0-85132207040 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Sustainability (Switzerland) |
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_ |
1799965639585038336 |