Use of hyperspectral image data outperforms vegetation indices in prediction of maize yield

Autores
Aguate, Fernando Matías; Trachsel, Samuel; González Pérez, Lorena; Burgueño, Juan; Crossa, José; Balzarini, Monica Graciela; Gouache, David; Bogard, Matthieu; de los Campos, Gustavo
Año de publicación
2017
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
Hyperspectral cameras can provide reflectance data at hundreds of wavelengths. This information can be used to derive vegetation indices (VIs) that are correlated with agronomic and physiological traits. However, the data generated by hyperspectral cameras are richer than what can be summarized in a VI. Therefore, in this study, we examined whether prediction equations using hyperspectral image data can lead to better predictive performance for grain yield than what can be achieved using VIs. For hyperspectral prediction equations, we considered three estimation methods: ordinary least squares, partial least squares (a dimension reduction method), and a Bayesian shrinkage and variable selection procedure. We also examined the benefits of combining reflectance data collected at different time points. Data were generated by CIMMYT in 11 maize (Zea mays L.) yield trials conducted in 2014 under heat and drought stress. Our results indicate that using data from 62 bands leads to higher prediction accuracy than what can be achieved using individual VIs. Overall, the shrinkage and variable selection method was the best-performing one. Among the models using data from a single time point, the one using reflectance collected at 28 d after flowering gave the highest prediction accuracy. Combining image data collected at multiple time points led to an increase in prediction accuracy compared with using single-time-point data.
Fil: Aguate, Fernando Matías. Universidad Nacional de Córdoba. Facultad de Ciencias Agropecuarias. Departamento de Desarrollo Rural. Area de Estadística y Biometría; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Córdoba; Argentina
Fil: Trachsel, Samuel. Centro Internacional de Mejoramiento de Maiz y Trigo; México
Fil: González Pérez, Lorena. Universidad Nacional de Córdoba. Facultad de Ciencias Agropecuarias. Departamento de Desarrollo Rural. Area de Estadística y Biometría; Argentina. Sustainable Intensification Program; México
Fil: Burgueño, Juan. Centro Internacional de Mejoramiento de Maiz y Trigo; México
Fil: Crossa, José. Centro Internacional de Mejoramiento de Maiz y Trigo; México
Fil: Balzarini, Monica Graciela. Universidad Nacional de Córdoba. Facultad de Ciencias Agropecuarias. Departamento de Desarrollo Rural. Area de Estadística y Biometría; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Córdoba; Argentina
Fil: Gouache, David. Arvalis - Institut Du Vegetal; Francia
Fil: Bogard, Matthieu. Arvalis - Institut Du Vegetal; Francia
Fil: de los Campos, Gustavo. Michigan State University; Estados Unidos
Materia
PLS
NDVI
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/72524
Acceder
id CONICETDig_43cd80b0c9b844ba8a92e1003fe3eaf6
oai_identifier_str oai:ri.conicet.gov.ar:11336/72524
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling Use of hyperspectral image data outperforms vegetation indices in prediction of maize yieldAguate, Fernando MatíasTrachsel, SamuelGonzález Pérez, LorenaBurgueño, JuanCrossa, JoséBalzarini, Monica GracielaGouache, DavidBogard, Matthieude los Campos, GustavoPLSNDVIhttps://purl.org/becyt/ford/4.5https://purl.org/becyt/ford/4Hyperspectral cameras can provide reflectance data at hundreds of wavelengths. This information can be used to derive vegetation indices (VIs) that are correlated with agronomic and physiological traits. However, the data generated by hyperspectral cameras are richer than what can be summarized in a VI. Therefore, in this study, we examined whether prediction equations using hyperspectral image data can lead to better predictive performance for grain yield than what can be achieved using VIs. For hyperspectral prediction equations, we considered three estimation methods: ordinary least squares, partial least squares (a dimension reduction method), and a Bayesian shrinkage and variable selection procedure. We also examined the benefits of combining reflectance data collected at different time points. Data were generated by CIMMYT in 11 maize (Zea mays L.) yield trials conducted in 2014 under heat and drought stress. Our results indicate that using data from 62 bands leads to higher prediction accuracy than what can be achieved using individual VIs. Overall, the shrinkage and variable selection method was the best-performing one. Among the models using data from a single time point, the one using reflectance collected at 28 d after flowering gave the highest prediction accuracy. Combining image data collected at multiple time points led to an increase in prediction accuracy compared with using single-time-point data.Fil: Aguate, Fernando Matías. Universidad Nacional de Córdoba. Facultad de Ciencias Agropecuarias. Departamento de Desarrollo Rural. Area de Estadística y Biometría; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Córdoba; ArgentinaFil: Trachsel, Samuel. Centro Internacional de Mejoramiento de Maiz y Trigo; MéxicoFil: González Pérez, Lorena. Universidad Nacional de Córdoba. Facultad de Ciencias Agropecuarias. Departamento de Desarrollo Rural. Area de Estadística y Biometría; Argentina. Sustainable Intensification Program; MéxicoFil: Burgueño, Juan. Centro Internacional de Mejoramiento de Maiz y Trigo; MéxicoFil: Crossa, José. Centro Internacional de Mejoramiento de Maiz y Trigo; MéxicoFil: Balzarini, Monica Graciela. Universidad Nacional de Córdoba. Facultad de Ciencias Agropecuarias. Departamento de Desarrollo Rural. Area de Estadística y Biometría; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Córdoba; ArgentinaFil: Gouache, David. Arvalis - Institut Du Vegetal; FranciaFil: Bogard, Matthieu. Arvalis - Institut Du Vegetal; FranciaFil: de los Campos, Gustavo. Michigan State University; Estados UnidosCrop Science Society of America2017-09info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/72524Aguate, Fernando Matías; Trachsel, Samuel; González Pérez, Lorena; Burgueño, Juan; Crossa, José; et al.; Use of hyperspectral image data outperforms vegetation indices in prediction of maize yield; Crop Science Society of America; Crop Science; 57; 5; 9-2017; 2517-25240011-183XCONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/url/https://dl.sciencesocieties.org/publications/cs/abstracts/0/0/cropsci2017.01.0007info:eu-repo/semantics/altIdentifier/doi/10.2135/cropsci2017.01.0007info:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by-nc-sa/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2025-09-03T09:52:02Zoai:ri.conicet.gov.ar:11336/72524instacron:CONICETInstitucionalhttp://ri.conicet.gov.ar/Organismo científico-tecnológicoNo correspondehttp://ri.conicet.gov.ar/oai/requestdasensio@conicet.gov.ar; lcarlino@conicet.gov.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:34982025-09-03 09:52:02.966CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv Use of hyperspectral image data outperforms vegetation indices in prediction of maize yield
title Use of hyperspectral image data outperforms vegetation indices in prediction of maize yield
spellingShingle Use of hyperspectral image data outperforms vegetation indices in prediction of maize yield
Aguate, Fernando Matías
PLS
NDVI
title_short Use of hyperspectral image data outperforms vegetation indices in prediction of maize yield
title_full Use of hyperspectral image data outperforms vegetation indices in prediction of maize yield
title_fullStr Use of hyperspectral image data outperforms vegetation indices in prediction of maize yield
title_full_unstemmed Use of hyperspectral image data outperforms vegetation indices in prediction of maize yield
title_sort Use of hyperspectral image data outperforms vegetation indices in prediction of maize yield
dc.creator.none.fl_str_mv Aguate, Fernando Matías
Trachsel, Samuel
González Pérez, Lorena
Burgueño, Juan
Crossa, José
Balzarini, Monica Graciela
Gouache, David
Bogard, Matthieu
de los Campos, Gustavo
author Aguate, Fernando Matías
author_facet Aguate, Fernando Matías
Trachsel, Samuel
González Pérez, Lorena
Burgueño, Juan
Crossa, José
Balzarini, Monica Graciela
Gouache, David
Bogard, Matthieu
de los Campos, Gustavo
author_role author
author2 Trachsel, Samuel
González Pérez, Lorena
Burgueño, Juan
Crossa, José
Balzarini, Monica Graciela
Gouache, David
Bogard, Matthieu
de los Campos, Gustavo
author2_role author
author
author
author
author
author
author
author
dc.subject.none.fl_str_mv PLS
NDVI
topic PLS
NDVI
purl_subject.fl_str_mv https://purl.org/becyt/ford/4.5
https://purl.org/becyt/ford/4
dc.description.none.fl_txt_mv Hyperspectral cameras can provide reflectance data at hundreds of wavelengths. This information can be used to derive vegetation indices (VIs) that are correlated with agronomic and physiological traits. However, the data generated by hyperspectral cameras are richer than what can be summarized in a VI. Therefore, in this study, we examined whether prediction equations using hyperspectral image data can lead to better predictive performance for grain yield than what can be achieved using VIs. For hyperspectral prediction equations, we considered three estimation methods: ordinary least squares, partial least squares (a dimension reduction method), and a Bayesian shrinkage and variable selection procedure. We also examined the benefits of combining reflectance data collected at different time points. Data were generated by CIMMYT in 11 maize (Zea mays L.) yield trials conducted in 2014 under heat and drought stress. Our results indicate that using data from 62 bands leads to higher prediction accuracy than what can be achieved using individual VIs. Overall, the shrinkage and variable selection method was the best-performing one. Among the models using data from a single time point, the one using reflectance collected at 28 d after flowering gave the highest prediction accuracy. Combining image data collected at multiple time points led to an increase in prediction accuracy compared with using single-time-point data.
Fil: Aguate, Fernando Matías. Universidad Nacional de Córdoba. Facultad de Ciencias Agropecuarias. Departamento de Desarrollo Rural. Area de Estadística y Biometría; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Córdoba; Argentina
Fil: Trachsel, Samuel. Centro Internacional de Mejoramiento de Maiz y Trigo; México
Fil: González Pérez, Lorena. Universidad Nacional de Córdoba. Facultad de Ciencias Agropecuarias. Departamento de Desarrollo Rural. Area de Estadística y Biometría; Argentina. Sustainable Intensification Program; México
Fil: Burgueño, Juan. Centro Internacional de Mejoramiento de Maiz y Trigo; México
Fil: Crossa, José. Centro Internacional de Mejoramiento de Maiz y Trigo; México
Fil: Balzarini, Monica Graciela. Universidad Nacional de Córdoba. Facultad de Ciencias Agropecuarias. Departamento de Desarrollo Rural. Area de Estadística y Biometría; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Córdoba; Argentina
Fil: Gouache, David. Arvalis - Institut Du Vegetal; Francia
Fil: Bogard, Matthieu. Arvalis - Institut Du Vegetal; Francia
Fil: de los Campos, Gustavo. Michigan State University; Estados Unidos
description Hyperspectral cameras can provide reflectance data at hundreds of wavelengths. This information can be used to derive vegetation indices (VIs) that are correlated with agronomic and physiological traits. However, the data generated by hyperspectral cameras are richer than what can be summarized in a VI. Therefore, in this study, we examined whether prediction equations using hyperspectral image data can lead to better predictive performance for grain yield than what can be achieved using VIs. For hyperspectral prediction equations, we considered three estimation methods: ordinary least squares, partial least squares (a dimension reduction method), and a Bayesian shrinkage and variable selection procedure. We also examined the benefits of combining reflectance data collected at different time points. Data were generated by CIMMYT in 11 maize (Zea mays L.) yield trials conducted in 2014 under heat and drought stress. Our results indicate that using data from 62 bands leads to higher prediction accuracy than what can be achieved using individual VIs. Overall, the shrinkage and variable selection method was the best-performing one. Among the models using data from a single time point, the one using reflectance collected at 28 d after flowering gave the highest prediction accuracy. Combining image data collected at multiple time points led to an increase in prediction accuracy compared with using single-time-point data.
publishDate 2017
dc.date.none.fl_str_mv 2017-09
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/11336/72524
Aguate, Fernando Matías; Trachsel, Samuel; González Pérez, Lorena; Burgueño, Juan; Crossa, José; et al.; Use of hyperspectral image data outperforms vegetation indices in prediction of maize yield; Crop Science Society of America; Crop Science; 57; 5; 9-2017; 2517-2524
0011-183X
CONICET Digital
CONICET
url http://hdl.handle.net/11336/72524
identifier_str_mv Aguate, Fernando Matías; Trachsel, Samuel; González Pérez, Lorena; Burgueño, Juan; Crossa, José; et al.; Use of hyperspectral image data outperforms vegetation indices in prediction of maize yield; Crop Science Society of America; Crop Science; 57; 5; 9-2017; 2517-2524
0011-183X
CONICET Digital
CONICET
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/url/https://dl.sciencesocieties.org/publications/cs/abstracts/0/0/cropsci2017.01.0007
info:eu-repo/semantics/altIdentifier/doi/10.2135/cropsci2017.01.0007
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
application/pdf
dc.publisher.none.fl_str_mv Crop Science Society of America
publisher.none.fl_str_mv Crop Science Society of America
dc.source.none.fl_str_mv reponame:CONICET Digital (CONICET)
instname:Consejo Nacional de Investigaciones Científicas y Técnicas
reponame_str CONICET Digital (CONICET)
collection CONICET Digital (CONICET)
instname_str Consejo Nacional de Investigaciones Científicas y Técnicas
repository.name.fl_str_mv CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicas
repository.mail.fl_str_mv dasensio@conicet.gov.ar; lcarlino@conicet.gov.ar
_version_ 1842269132271124480
score 13.13397

Publicaciones similares