Site-Specific Nutrient Diagnosis of Orange Groves
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/horticulturae8121126 http://hdl.handle.net/11449/249512 |
Resumo: | Nutrient diagnosis of orange (Citrus sinensis) groves in Brazil relies on regional information from a limited number of studies transferred to other environments under the ceteris paribus assumption. Interpretation methods are based on crude nutrient compositions that are intrinsically biased by genetics X environment interactions. Our objective was to develop accurate and unbiased nutrient diagnosis of orange groves combining machine learning (ML) and compositional methods. Fruit yield and foliar nutrients were quantified in 551 rainfed 7–15-year-old orange groves of ‘Hamlin’, ‘Valência’, and ‘Pêra’ in the state of São Paulo, Brazil. The data set was further documented using soil classification, soil tests, and meteorological indices. Tissue compositions were log-ratio transformed to account for nutrient interactions. Ionomes differed among scions. Regression ML models showed evidence of overfitting. Binary ML classification models showed acceptable values of areas under the curve (>0.7). Regional standards delineating the multivariate elliptical hyperspace depended on the yield cutoff. A shapeless blob hyperspace was delineated using the k-nearest successful neighbors that showed comparable features and reported realistic yield goals. Regionally derived and site-specific reference compositions may lead to differential interpretation. Large-size and diversified data sets must be collected to inform ML models along the learning curve, tackle model overfitting, and evaluate the merit of blob-scale diagnosis. |
id |
UNSP_95c03ad7b8f7d22a1565626950439d7b |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/249512 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Site-Specific Nutrient Diagnosis of Orange Grovescentered log ratiolocal diagnosismachine learningnutrient balanceNutrient diagnosis of orange (Citrus sinensis) groves in Brazil relies on regional information from a limited number of studies transferred to other environments under the ceteris paribus assumption. Interpretation methods are based on crude nutrient compositions that are intrinsically biased by genetics X environment interactions. Our objective was to develop accurate and unbiased nutrient diagnosis of orange groves combining machine learning (ML) and compositional methods. Fruit yield and foliar nutrients were quantified in 551 rainfed 7–15-year-old orange groves of ‘Hamlin’, ‘Valência’, and ‘Pêra’ in the state of São Paulo, Brazil. The data set was further documented using soil classification, soil tests, and meteorological indices. Tissue compositions were log-ratio transformed to account for nutrient interactions. Ionomes differed among scions. Regression ML models showed evidence of overfitting. Binary ML classification models showed acceptable values of areas under the curve (>0.7). Regional standards delineating the multivariate elliptical hyperspace depended on the yield cutoff. A shapeless blob hyperspace was delineated using the k-nearest successful neighbors that showed comparable features and reported realistic yield goals. Regionally derived and site-specific reference compositions may lead to differential interpretation. Large-size and diversified data sets must be collected to inform ML models along the learning curve, tackle model overfitting, and evaluate the merit of blob-scale diagnosis.Natural Sciences and Engineering Research Council of CanadaDepartment of Plant Production São Paulo State University (UNESP), SPDepartment of Soils and Agri-Food Engineering Université LavalDepartment of Plant Science Federal University of Ceará, CEDepartment of Agronomy São Paulo State University (UNESP), SPInstituto Agronômico de Campinas (IAC) Centro de Citricultura Sylvio Moreira, SPDepartment of Soils Federal University of Santa Maria, RSDepartment of Plant Production São Paulo State University (UNESP), SPDepartment of Agronomy São Paulo State University (UNESP), SPNatural Sciences and Engineering Research Council of Canada: #2254Universidade Estadual Paulista (UNESP)Université LavalFederal University of CearáCentro de Citricultura Sylvio MoreiraFederal University of Santa MariaYamane, Danilo Ricardo [UNESP]Parent, Serge-ÉtienneNatale, WilliamCecílio Filho, Arthur Bernardes [UNESP]Rozane, Danilo Eduardo [UNESP]Nowaki, Rodrigo Hiyoshi Dalmazzo [UNESP]Mattos Junior, Dirceu deParent, Léon Etienne2023-07-29T16:01:39Z2023-07-29T16:01:39Z2022-12-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlehttp://dx.doi.org/10.3390/horticulturae8121126Horticulturae, v. 8, n. 12, 2022.2311-7524http://hdl.handle.net/11449/24951210.3390/horticulturae81211262-s2.0-85144905436Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengHorticulturaeinfo:eu-repo/semantics/openAccess2024-06-07T13:57:21Zoai:repositorio.unesp.br:11449/249512Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T22:03:56.221299Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Site-Specific Nutrient Diagnosis of Orange Groves |
title |
Site-Specific Nutrient Diagnosis of Orange Groves |
spellingShingle |
Site-Specific Nutrient Diagnosis of Orange Groves Yamane, Danilo Ricardo [UNESP] centered log ratio local diagnosis machine learning nutrient balance |
title_short |
Site-Specific Nutrient Diagnosis of Orange Groves |
title_full |
Site-Specific Nutrient Diagnosis of Orange Groves |
title_fullStr |
Site-Specific Nutrient Diagnosis of Orange Groves |
title_full_unstemmed |
Site-Specific Nutrient Diagnosis of Orange Groves |
title_sort |
Site-Specific Nutrient Diagnosis of Orange Groves |
author |
Yamane, Danilo Ricardo [UNESP] |
author_facet |
Yamane, Danilo Ricardo [UNESP] Parent, Serge-Étienne Natale, William Cecílio Filho, Arthur Bernardes [UNESP] Rozane, Danilo Eduardo [UNESP] Nowaki, Rodrigo Hiyoshi Dalmazzo [UNESP] Mattos Junior, Dirceu de Parent, Léon Etienne |
author_role |
author |
author2 |
Parent, Serge-Étienne Natale, William Cecílio Filho, Arthur Bernardes [UNESP] Rozane, Danilo Eduardo [UNESP] Nowaki, Rodrigo Hiyoshi Dalmazzo [UNESP] Mattos Junior, Dirceu de Parent, Léon Etienne |
author2_role |
author author author author author author author |
dc.contributor.none.fl_str_mv |
Universidade Estadual Paulista (UNESP) Université Laval Federal University of Ceará Centro de Citricultura Sylvio Moreira Federal University of Santa Maria |
dc.contributor.author.fl_str_mv |
Yamane, Danilo Ricardo [UNESP] Parent, Serge-Étienne Natale, William Cecílio Filho, Arthur Bernardes [UNESP] Rozane, Danilo Eduardo [UNESP] Nowaki, Rodrigo Hiyoshi Dalmazzo [UNESP] Mattos Junior, Dirceu de Parent, Léon Etienne |
dc.subject.por.fl_str_mv |
centered log ratio local diagnosis machine learning nutrient balance |
topic |
centered log ratio local diagnosis machine learning nutrient balance |
description |
Nutrient diagnosis of orange (Citrus sinensis) groves in Brazil relies on regional information from a limited number of studies transferred to other environments under the ceteris paribus assumption. Interpretation methods are based on crude nutrient compositions that are intrinsically biased by genetics X environment interactions. Our objective was to develop accurate and unbiased nutrient diagnosis of orange groves combining machine learning (ML) and compositional methods. Fruit yield and foliar nutrients were quantified in 551 rainfed 7–15-year-old orange groves of ‘Hamlin’, ‘Valência’, and ‘Pêra’ in the state of São Paulo, Brazil. The data set was further documented using soil classification, soil tests, and meteorological indices. Tissue compositions were log-ratio transformed to account for nutrient interactions. Ionomes differed among scions. Regression ML models showed evidence of overfitting. Binary ML classification models showed acceptable values of areas under the curve (>0.7). Regional standards delineating the multivariate elliptical hyperspace depended on the yield cutoff. A shapeless blob hyperspace was delineated using the k-nearest successful neighbors that showed comparable features and reported realistic yield goals. Regionally derived and site-specific reference compositions may lead to differential interpretation. Large-size and diversified data sets must be collected to inform ML models along the learning curve, tackle model overfitting, and evaluate the merit of blob-scale diagnosis. |
publishDate |
2022 |
dc.date.none.fl_str_mv |
2022-12-01 2023-07-29T16:01:39Z 2023-07-29T16:01:39Z |
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/horticulturae8121126 Horticulturae, v. 8, n. 12, 2022. 2311-7524 http://hdl.handle.net/11449/249512 10.3390/horticulturae8121126 2-s2.0-85144905436 |
url |
http://dx.doi.org/10.3390/horticulturae8121126 http://hdl.handle.net/11449/249512 |
identifier_str_mv |
Horticulturae, v. 8, n. 12, 2022. 2311-7524 10.3390/horticulturae8121126 2-s2.0-85144905436 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Horticulturae |
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_ |
1808129388001099776 |