Local Factors Impact Accuracy of Garlic Tissue Test Diagnosis
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/agronomy12112714 http://hdl.handle.net/11449/246299 |
Resumo: | The low productivity of garlic in Brazil requires more efficient nutritional management. For this, environmental and fertilization-related factors must be adjusted to a set of local conditions. Our objective was to provide an accurate diagnosis of the nutrient status of garlic crops in southern Brazil. The dataset comprised 1024 observations, 962 as field tests conducted during the 2015–2017 period to train the model, and 61 field observations collected during the 2018–2019 period to validate the model. Machine learning models (MLM) related garlic yield to managerial, edaphic, plant, and climatic features. Compositional data analysis (CoDa) methods allowed classification of nutrients in the order of limitation to yield where MLM detected nutrient imbalance. Tissue analysis alone returned an accuracy of 0.750 in regression and 0.891 in classification about the yield cutoff of 11 ton ha−1. Adding all features documented in the dataset, accuracy reached 0.855 in regression and 0.912 in classification. Local diagnosis based on MLM and CoDa and accounting for local features differed from regional diagnosis across features. Local nutrient diagnosis may differ from regional diagnosis because several yield-impacting factors are taken into account and benchmark compositions are representative of local conditions. |
id |
UNSP_74f5580047ac6cd0ad3dbbd756d1e131 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/246299 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Local Factors Impact Accuracy of Garlic Tissue Test DiagnosisAdaboostAllium sativumcompositional distancegrowth-limiting factorsmachine learningperturbation vectorrandom forestThe low productivity of garlic in Brazil requires more efficient nutritional management. For this, environmental and fertilization-related factors must be adjusted to a set of local conditions. Our objective was to provide an accurate diagnosis of the nutrient status of garlic crops in southern Brazil. The dataset comprised 1024 observations, 962 as field tests conducted during the 2015–2017 period to train the model, and 61 field observations collected during the 2018–2019 period to validate the model. Machine learning models (MLM) related garlic yield to managerial, edaphic, plant, and climatic features. Compositional data analysis (CoDa) methods allowed classification of nutrients in the order of limitation to yield where MLM detected nutrient imbalance. Tissue analysis alone returned an accuracy of 0.750 in regression and 0.891 in classification about the yield cutoff of 11 ton ha−1. Adding all features documented in the dataset, accuracy reached 0.855 in regression and 0.912 in classification. Local diagnosis based on MLM and CoDa and accounting for local features differed from regional diagnosis across features. Local nutrient diagnosis may differ from regional diagnosis because several yield-impacting factors are taken into account and benchmark compositions are representative of local conditions.Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of CanadaNatural Sciences and Engineering Research Council of CanadaCaçador Experimental Station Santa Catarina State Agricultural Research and Rural Extension Agency (EPAGRI), SCDepartment of Soils and Agrifood Engineering Université LavalAgronomy Department São Paulo State University “Júlio Mesquita Filho”, SPAgronomy Department University of Alto Vale do Rio do Peixe (UNIARP), SCSoil Science Department Federal University of Santa Maria (UFSM), RSForest Science Department Federal University of Paraná (UFPR), RSAgronomy Department São Paulo State University “Júlio Mesquita Filho”, SPCanadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada: NSERC-2254Natural Sciences and Engineering Research Council of Canada: NSERC-2254(EPAGRI)Université LavalUniversidade Estadual Paulista (UNESP)University of Alto Vale do Rio do Peixe (UNIARP)Universidade Federal de Sergipe (UFS)Universidade Federal do Paraná (UFPR)Hahn, LeandroParent, Léon-ÉtienneFeltrim, Anderson LuizRozane, Danilo Eduardo [UNESP]Ender, Marcos MatosTassinari, AdrieleKrug, Amanda VeridianaBerghetti, Álvaro Luís PasquettiBrunetto, Gustavo2023-07-29T12:37:12Z2023-07-29T12:37:12Z2022-11-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlehttp://dx.doi.org/10.3390/agronomy12112714Agronomy, v. 12, n. 11, 2022.2073-4395http://hdl.handle.net/11449/24629910.3390/agronomy121127142-s2.0-85141887663Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengAgronomyinfo:eu-repo/semantics/openAccess2023-07-29T12:37:12Zoai:repositorio.unesp.br:11449/246299Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T16:24:03.821613Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Local Factors Impact Accuracy of Garlic Tissue Test Diagnosis |
title |
Local Factors Impact Accuracy of Garlic Tissue Test Diagnosis |
spellingShingle |
Local Factors Impact Accuracy of Garlic Tissue Test Diagnosis Hahn, Leandro Adaboost Allium sativum compositional distance growth-limiting factors machine learning perturbation vector random forest |
title_short |
Local Factors Impact Accuracy of Garlic Tissue Test Diagnosis |
title_full |
Local Factors Impact Accuracy of Garlic Tissue Test Diagnosis |
title_fullStr |
Local Factors Impact Accuracy of Garlic Tissue Test Diagnosis |
title_full_unstemmed |
Local Factors Impact Accuracy of Garlic Tissue Test Diagnosis |
title_sort |
Local Factors Impact Accuracy of Garlic Tissue Test Diagnosis |
author |
Hahn, Leandro |
author_facet |
Hahn, Leandro Parent, Léon-Étienne Feltrim, Anderson Luiz Rozane, Danilo Eduardo [UNESP] Ender, Marcos Matos Tassinari, Adriele Krug, Amanda Veridiana Berghetti, Álvaro Luís Pasquetti Brunetto, Gustavo |
author_role |
author |
author2 |
Parent, Léon-Étienne Feltrim, Anderson Luiz Rozane, Danilo Eduardo [UNESP] Ender, Marcos Matos Tassinari, Adriele Krug, Amanda Veridiana Berghetti, Álvaro Luís Pasquetti Brunetto, Gustavo |
author2_role |
author author author author author author author author |
dc.contributor.none.fl_str_mv |
(EPAGRI) Université Laval Universidade Estadual Paulista (UNESP) University of Alto Vale do Rio do Peixe (UNIARP) Universidade Federal de Sergipe (UFS) Universidade Federal do Paraná (UFPR) |
dc.contributor.author.fl_str_mv |
Hahn, Leandro Parent, Léon-Étienne Feltrim, Anderson Luiz Rozane, Danilo Eduardo [UNESP] Ender, Marcos Matos Tassinari, Adriele Krug, Amanda Veridiana Berghetti, Álvaro Luís Pasquetti Brunetto, Gustavo |
dc.subject.por.fl_str_mv |
Adaboost Allium sativum compositional distance growth-limiting factors machine learning perturbation vector random forest |
topic |
Adaboost Allium sativum compositional distance growth-limiting factors machine learning perturbation vector random forest |
description |
The low productivity of garlic in Brazil requires more efficient nutritional management. For this, environmental and fertilization-related factors must be adjusted to a set of local conditions. Our objective was to provide an accurate diagnosis of the nutrient status of garlic crops in southern Brazil. The dataset comprised 1024 observations, 962 as field tests conducted during the 2015–2017 period to train the model, and 61 field observations collected during the 2018–2019 period to validate the model. Machine learning models (MLM) related garlic yield to managerial, edaphic, plant, and climatic features. Compositional data analysis (CoDa) methods allowed classification of nutrients in the order of limitation to yield where MLM detected nutrient imbalance. Tissue analysis alone returned an accuracy of 0.750 in regression and 0.891 in classification about the yield cutoff of 11 ton ha−1. Adding all features documented in the dataset, accuracy reached 0.855 in regression and 0.912 in classification. Local diagnosis based on MLM and CoDa and accounting for local features differed from regional diagnosis across features. Local nutrient diagnosis may differ from regional diagnosis because several yield-impacting factors are taken into account and benchmark compositions are representative of local conditions. |
publishDate |
2022 |
dc.date.none.fl_str_mv |
2022-11-01 2023-07-29T12:37:12Z 2023-07-29T12:37:12Z |
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/agronomy12112714 Agronomy, v. 12, n. 11, 2022. 2073-4395 http://hdl.handle.net/11449/246299 10.3390/agronomy12112714 2-s2.0-85141887663 |
url |
http://dx.doi.org/10.3390/agronomy12112714 http://hdl.handle.net/11449/246299 |
identifier_str_mv |
Agronomy, v. 12, n. 11, 2022. 2073-4395 10.3390/agronomy12112714 2-s2.0-85141887663 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Agronomy |
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_ |
1808128644088856576 |