Predicting coffee water potential from spectral reflectance indices with neural networks.

Detalhes bibliográficos
Autor(a) principal: NUNES, P. H.
Data de Publicação: 2023
Outros Autores: PIERANGELI, E. V., SANTOS, M. O., SILVEIRA, H. R. O., MATOS, C. S. M. de, PEREIRA, A. B., ALVES, H. M. R., VOLPATO, M. M. L., SILVA, V. A., FERREIRA, D. D.
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Institucional da EMBRAPA (Repository Open Access to Scientific Information from EMBRAPA - Alice)
Texto Completo: http://www.alice.cnptia.embrapa.br/alice/handle/doc/1152292
https://doi.org/10.1016/j.atech.2023.100213
Resumo: Leaf water potential is one of the main parameters used to assess water relations in plants by revealing levels of tissue hydration. It is commonly measured with the Scholander pressure chamber; which demands hard work and a time-consuming process. On the other hand, there is a diversified literature demonstrating the assessments of several plant variables via indices of leaf reflectance, that also present direct and indirect relationships with water potential. The aim of this work is to exploit spectral variables to estimate the water potential of coffee plants by using computational intelligence approaches. Data was collected in the cities of Santo Antônio do Amparo and Diamantina, Brazil, from 2014 to 2018. Two neural networks (Multi-Layer Perceptron) were designed to estimate and classify leaf water potential based on spectral variables. Moreover, a classifier and an estimator based on decision tree were also developed. The results showed that the artificial neural network model was superior as an estimator when compared with the decision tree model, with an average confidence index of 0.8550. On the other hand, decision trees showed a slightly higher performance as a classifier, with an overall accuracy of 88.8% and a Kappa index of 70.07%. We concluded that the leaf reflectance indices may be properly used to build accurate models for estimating coffee water potential. The indices PRI, NDVI, CRI1 and SIPI were the most relevant ones for estimating and classifying the coffee water potential.
id EMBR_b0eb0b1ac620ac162f9f3ceac9903d54
oai_identifier_str oai:www.alice.cnptia.embrapa.br:doc/1152292
network_acronym_str EMBR
network_name_str Repositório Institucional da EMBRAPA (Repository Open Access to Scientific Information from EMBRAPA - Alice)
repository_id_str 2154
spelling Predicting coffee water potential from spectral reflectance indices with neural networks.Artificial intelligenceNeural networksTreesWater potentialCoffeaLeaf water potential is one of the main parameters used to assess water relations in plants by revealing levels of tissue hydration. It is commonly measured with the Scholander pressure chamber; which demands hard work and a time-consuming process. On the other hand, there is a diversified literature demonstrating the assessments of several plant variables via indices of leaf reflectance, that also present direct and indirect relationships with water potential. The aim of this work is to exploit spectral variables to estimate the water potential of coffee plants by using computational intelligence approaches. Data was collected in the cities of Santo Antônio do Amparo and Diamantina, Brazil, from 2014 to 2018. Two neural networks (Multi-Layer Perceptron) were designed to estimate and classify leaf water potential based on spectral variables. Moreover, a classifier and an estimator based on decision tree were also developed. The results showed that the artificial neural network model was superior as an estimator when compared with the decision tree model, with an average confidence index of 0.8550. On the other hand, decision trees showed a slightly higher performance as a classifier, with an overall accuracy of 88.8% and a Kappa index of 70.07%. We concluded that the leaf reflectance indices may be properly used to build accurate models for estimating coffee water potential. The indices PRI, NDVI, CRI1 and SIPI were the most relevant ones for estimating and classifying the coffee water potential.PEDRO HENRIQUE NUNES, UNIVERSIDADE FEDERAL DE LAVRAS; EDUARDO VILELA PIERANGELI, UNIVERSIDADE FEDERAL DE LAVRAS; MELINE OLIVEIRA SANTOS, EMPRESA DE PESQUISA AGROPECUÁRIA DE MINAS GERAIS; HELBERT REZENDE OLIVEIRA SILVEIRA, EMPRESA DE PESQUISA AGROPECUÁRIA DE MINAS GERAIS; CHRISTIANO SOUSA MACHADO DE MATOS, EMPRESA DE PESQUISA AGROPECUÁRIA DE MINAS GERAIS; ALESSANDRO BOTELHO PEREIRA, EMPRESA DE PESQUISA AGROPECUÁRIA DE MINAS GERAIS; HELENA MARIA RAMOS ALVES, CNPCa; MARGARETE MARIN LORDELO VOLPATO, EMPRESA DE PESQUISA AGROPECUÁRIA DE MINAS GERAIS; VÂNIA APARECIDA SILVA, EMPRESA DE PESQUISA AGROPECUÁRIA DE MINAS GERAIS; DANTON DIEGO FERREIRA, UNIVERSIDADE FEDERAL DE LAVRAS.NUNES, P. H.PIERANGELI, E. V.SANTOS, M. O.SILVEIRA, H. R. O.MATOS, C. S. M. dePEREIRA, A. B.ALVES, H. M. R.VOLPATO, M. M. L.SILVA, V. A.FERREIRA, D. D.2023-03-13T13:50:26Z2023-03-13T13:50:26Z2023-03-132023info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article6 p.Smart Agricultural Technology, v. 4, 100213, 2023.http://www.alice.cnptia.embrapa.br/alice/handle/doc/1152292https://doi.org/10.1016/j.atech.2023.100213enginfo:eu-repo/semantics/openAccessreponame:Repositório Institucional da EMBRAPA (Repository Open Access to Scientific Information from EMBRAPA - Alice)instname:Empresa Brasileira de Pesquisa Agropecuária (Embrapa)instacron:EMBRAPA2023-03-13T13:50:26Zoai:www.alice.cnptia.embrapa.br:doc/1152292Repositório InstitucionalPUBhttps://www.alice.cnptia.embrapa.br/oai/requestopendoar:21542023-03-13T13:50:26falseRepositório InstitucionalPUBhttps://www.alice.cnptia.embrapa.br/oai/requestcg-riaa@embrapa.bropendoar:21542023-03-13T13:50:26Repositório Institucional da EMBRAPA (Repository Open Access to Scientific Information from EMBRAPA - Alice) - Empresa Brasileira de Pesquisa Agropecuária (Embrapa)false
dc.title.none.fl_str_mv Predicting coffee water potential from spectral reflectance indices with neural networks.
title Predicting coffee water potential from spectral reflectance indices with neural networks.
spellingShingle Predicting coffee water potential from spectral reflectance indices with neural networks.
NUNES, P. H.
Artificial intelligence
Neural networks
Trees
Water potential
Coffea
title_short Predicting coffee water potential from spectral reflectance indices with neural networks.
title_full Predicting coffee water potential from spectral reflectance indices with neural networks.
title_fullStr Predicting coffee water potential from spectral reflectance indices with neural networks.
title_full_unstemmed Predicting coffee water potential from spectral reflectance indices with neural networks.
title_sort Predicting coffee water potential from spectral reflectance indices with neural networks.
author NUNES, P. H.
author_facet NUNES, P. H.
PIERANGELI, E. V.
SANTOS, M. O.
SILVEIRA, H. R. O.
MATOS, C. S. M. de
PEREIRA, A. B.
ALVES, H. M. R.
VOLPATO, M. M. L.
SILVA, V. A.
FERREIRA, D. D.
author_role author
author2 PIERANGELI, E. V.
SANTOS, M. O.
SILVEIRA, H. R. O.
MATOS, C. S. M. de
PEREIRA, A. B.
ALVES, H. M. R.
VOLPATO, M. M. L.
SILVA, V. A.
FERREIRA, D. D.
author2_role author
author
author
author
author
author
author
author
author
dc.contributor.none.fl_str_mv PEDRO HENRIQUE NUNES, UNIVERSIDADE FEDERAL DE LAVRAS; EDUARDO VILELA PIERANGELI, UNIVERSIDADE FEDERAL DE LAVRAS; MELINE OLIVEIRA SANTOS, EMPRESA DE PESQUISA AGROPECUÁRIA DE MINAS GERAIS; HELBERT REZENDE OLIVEIRA SILVEIRA, EMPRESA DE PESQUISA AGROPECUÁRIA DE MINAS GERAIS; CHRISTIANO SOUSA MACHADO DE MATOS, EMPRESA DE PESQUISA AGROPECUÁRIA DE MINAS GERAIS; ALESSANDRO BOTELHO PEREIRA, EMPRESA DE PESQUISA AGROPECUÁRIA DE MINAS GERAIS; HELENA MARIA RAMOS ALVES, CNPCa; MARGARETE MARIN LORDELO VOLPATO, EMPRESA DE PESQUISA AGROPECUÁRIA DE MINAS GERAIS; VÂNIA APARECIDA SILVA, EMPRESA DE PESQUISA AGROPECUÁRIA DE MINAS GERAIS; DANTON DIEGO FERREIRA, UNIVERSIDADE FEDERAL DE LAVRAS.
dc.contributor.author.fl_str_mv NUNES, P. H.
PIERANGELI, E. V.
SANTOS, M. O.
SILVEIRA, H. R. O.
MATOS, C. S. M. de
PEREIRA, A. B.
ALVES, H. M. R.
VOLPATO, M. M. L.
SILVA, V. A.
FERREIRA, D. D.
dc.subject.por.fl_str_mv Artificial intelligence
Neural networks
Trees
Water potential
Coffea
topic Artificial intelligence
Neural networks
Trees
Water potential
Coffea
description Leaf water potential is one of the main parameters used to assess water relations in plants by revealing levels of tissue hydration. It is commonly measured with the Scholander pressure chamber; which demands hard work and a time-consuming process. On the other hand, there is a diversified literature demonstrating the assessments of several plant variables via indices of leaf reflectance, that also present direct and indirect relationships with water potential. The aim of this work is to exploit spectral variables to estimate the water potential of coffee plants by using computational intelligence approaches. Data was collected in the cities of Santo Antônio do Amparo and Diamantina, Brazil, from 2014 to 2018. Two neural networks (Multi-Layer Perceptron) were designed to estimate and classify leaf water potential based on spectral variables. Moreover, a classifier and an estimator based on decision tree were also developed. The results showed that the artificial neural network model was superior as an estimator when compared with the decision tree model, with an average confidence index of 0.8550. On the other hand, decision trees showed a slightly higher performance as a classifier, with an overall accuracy of 88.8% and a Kappa index of 70.07%. We concluded that the leaf reflectance indices may be properly used to build accurate models for estimating coffee water potential. The indices PRI, NDVI, CRI1 and SIPI were the most relevant ones for estimating and classifying the coffee water potential.
publishDate 2023
dc.date.none.fl_str_mv 2023-03-13T13:50:26Z
2023-03-13T13:50:26Z
2023-03-13
2023
dc.type.driver.fl_str_mv info:eu-repo/semantics/publishedVersion
info:eu-repo/semantics/article
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv Smart Agricultural Technology, v. 4, 100213, 2023.
http://www.alice.cnptia.embrapa.br/alice/handle/doc/1152292
https://doi.org/10.1016/j.atech.2023.100213
identifier_str_mv Smart Agricultural Technology, v. 4, 100213, 2023.
url http://www.alice.cnptia.embrapa.br/alice/handle/doc/1152292
https://doi.org/10.1016/j.atech.2023.100213
dc.language.iso.fl_str_mv eng
language eng
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv 6 p.
dc.source.none.fl_str_mv reponame:Repositório Institucional da EMBRAPA (Repository Open Access to Scientific Information from EMBRAPA - Alice)
instname:Empresa Brasileira de Pesquisa Agropecuária (Embrapa)
instacron:EMBRAPA
instname_str Empresa Brasileira de Pesquisa Agropecuária (Embrapa)
instacron_str EMBRAPA
institution EMBRAPA
reponame_str Repositório Institucional da EMBRAPA (Repository Open Access to Scientific Information from EMBRAPA - Alice)
collection Repositório Institucional da EMBRAPA (Repository Open Access to Scientific Information from EMBRAPA - Alice)
repository.name.fl_str_mv Repositório Institucional da EMBRAPA (Repository Open Access to Scientific Information from EMBRAPA - Alice) - Empresa Brasileira de Pesquisa Agropecuária (Embrapa)
repository.mail.fl_str_mv cg-riaa@embrapa.br
_version_ 1794503541135507456