MACHINE LEARNING MODELS APPLIED IN THE ESTIMATION OF REFERENCE EVAPOTRANSPIRATION FROM THE WESTERN PLATEAU OF PAULISTA
Autor(a) principal: | |
---|---|
Data de Publicação: | 2022 |
Outros Autores: | , , , , , , , |
Tipo de documento: | Artigo |
Idioma: | por |
Título da fonte: | Nativa (Sinop) |
Texto Completo: | https://periodicoscientificos.ufmt.br/ojs/index.php/nativa/article/view/13922 |
Resumo: | Evapotranspiration depends on the interaction between meteorological variables (solar radiation, air temperature, precipitation, relative humidity and wind speed) and phytosanitary conditions of agricultural crops. It is complex to build reliable evapotranspiration measurements due to the high costs of implementing micrometeorological techniques, in addition to difficulties in the operation and maintenance of the necessary equipment. The purpose of this research was to model the reference evapotranspiration through machine learning techniques in climatic data from 30 automatic weather stations in the Planalto Ocidental Paulista, State of São Paulo, Brazil, in the period 2013-2017. A comparison of the statistical performance between the techniques used was carried out, where the best performance of the EToMLP4 model (rRMSE = 0.62%), followed by EToANFIS4 (rRMSE = 0.75%), EToSVM4 (rRMSE = 1.19%) and EToGRNN4 (rRMSE = 11.05 %). Performance measures of the validation base show that the proposed models are able to estimate the reference evapotranspiration, with emphasis on the MPL technique. |
id |
UFMT-2_1f09a128275be1a77723393ce893e4f6 |
---|---|
oai_identifier_str |
oai:periodicoscientificos.ufmt.br:article/13922 |
network_acronym_str |
UFMT-2 |
network_name_str |
Nativa (Sinop) |
repository_id_str |
|
spelling |
MACHINE LEARNING MODELS APPLIED IN THE ESTIMATION OF REFERENCE EVAPOTRANSPIRATION FROM THE WESTERN PLATEAU OF PAULISTAMODELOS DE APRENDIZAJE DE MÁQUINAS APLICADOS EN LA ESTIMACIÓN DE LA EVAPOTRANSPIRACIÓN DE REFERENCIA DE LA MESETA OCCIDENTAL DE PAULISTAMODELOS DE MACHINE LEARNING APLICADOS NA ESTIMAÇÃO DA EVAPOTRANSPIRAÇÃO DE REFERÊNCIA DO PLANALTO OCIDENTAL PAULISTAevapotranspiraciónaprendizaje automáticomodelado de evapotranspiración de referenciaaprendizaje automático.evapotranspirationmachine learningreference evapotranspiration modelingmachine learning.evapotranspiraçãomachine learningmodelagem da evapotranspiração de referênciaaprendizagem de máquina.Evapotranspiration depends on the interaction between meteorological variables (solar radiation, air temperature, precipitation, relative humidity and wind speed) and phytosanitary conditions of agricultural crops. It is complex to build reliable evapotranspiration measurements due to the high costs of implementing micrometeorological techniques, in addition to difficulties in the operation and maintenance of the necessary equipment. The purpose of this research was to model the reference evapotranspiration through machine learning techniques in climatic data from 30 automatic weather stations in the Planalto Ocidental Paulista, State of São Paulo, Brazil, in the period 2013-2017. A comparison of the statistical performance between the techniques used was carried out, where the best performance of the EToMLP4 model (rRMSE = 0.62%), followed by EToANFIS4 (rRMSE = 0.75%), EToSVM4 (rRMSE = 1.19%) and EToGRNN4 (rRMSE = 11.05 %). Performance measures of the validation base show that the proposed models are able to estimate the reference evapotranspiration, with emphasis on the MPL technique.La evapotranspiración depende de la interacción entre las variables meteorológicas (radiación solar, temperatura del aire, precipitación, humedad relativa y velocidad del viento) y las condiciones fitosanitarias de los cultivos agrícolas. Es complejo construir mediciones confiables de evapotranspiración debido a los altos costos de implementar técnicas micrometeorológicas, además de las dificultades en la operación y mantenimiento de los equipos necesarios. El objetivo de esta investigación fue modelar la evapotranspiración de referencia a través de técnicas de aprendizaje automático en datos climáticos de 30 estaciones meteorológicas automáticas en el Planalto Ocidental Paulista, Estado de São Paulo, Brasil, en el período 2013-2017. Se realizó una comparación del rendimiento estadístico entre las técnicas utilizadas, donde el mejor rendimiento del modelo EToMLP4 (rRMSE = 0,62%), seguido de EToANFIS4 (rRMSE = 0,75%), EToSVM4 (rRMSE = 1,19%) y EToGRNN4 (rRMSE = 11,05 %). Las medidas de desempeño de la base de validación muestran que los modelos propuestos son capaces de estimar la evapotranspiración de referencia, con énfasis en la técnica MPL.A evapotranspiração depende da interação entre variáveis meteorológicas (radiação solar, temperatura do ar, precipitação, umidade relativa do ar e velocidade do vento) e condições fitossanitárias das culturas agrícolas. É complexo construir medidas confiáveis de evapotranspiração devido aos elevados custos para implantação de técnicas micrometeorológicas, além de dificuldades na operação e manutenção dos equipamentos necessários. O propósito desta pesquisa foi modelar a evapotranspiração de referência (ETo) por meio de técnicas de machine learning em dados climáticos de 30 estações meteorológicas automáticas do Planalto Ocidental Paulista, Estado de São Paulo, Brasil, no período de 2013-2017. Uma comparação do desempenho estatístico entre as técnicas utilizadas foi realizada onde constatou-se melhor desempenho do modelo EToMLP4 (rRMSE = 0.62%), seguido por EToANFIS4 (rRMSE = 0.75%), EToSVM4 (rRMSE = 1.19%) e EToGRNN4 (rRMSE = 11.05%). Medidas de performance da base de validação evidenciam que os modelos propostos são aptos à estimativa da evapotranspiração de referência com destaque para a técnica MPL. Palavras-chave: evapotranspiração; modelagem matemática; aprendizagem de máquina. Machine learning models applied in the estimation of reference evapotranspiration from the Western Plateau of Paulista ABSTRACT: Evapotranspiration depends on the interaction between meteorological variables (solar radiation, air temperature, precipitation, relative humidity and wind speed) and phytosanitary conditions of agricultural crops. It is complex to build reliable evapotranspiration measurements due to the high costs of implementing micrometeorological techniques, in addition to difficulties in the operation and maintenance of the necessary equipment. The purpose of this research was to model the reference evapotranspiration through machine learning techniques in climatic data from 30 automatic weather stations in the Planalto Ocidental Paulista, State of São Paulo, Brazil, in the period 2013-2017. A comparison of the statistical performance between the techniques used was carried out, where the best performance of the EToMLP4 model (rRMSE = 0.62%), followed by EToANFIS4 (rRMSE = 0.75%), EToSVM4 (rRMSE = 1.19%) and EToGRNN4 (rRMSE = 11.05 %). Performance measures of the validation base show that the proposed models are able to estimate the reference evapotranspiration, with emphasis on the MPL technique. Keywords: evapotranspiration; modeling; machine learning.Universidade Federal de Mato Grosso2022-11-16info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://periodicoscientificos.ufmt.br/ojs/index.php/nativa/article/view/1392210.31413/nativa.v10i4.13922Nativa; v. 10 n. 4 (2022); 506-515Nativa; Vol. 10 Núm. 4 (2022); 506-515Nativa; Vol. 10 No. 4 (2022); 506-5152318-7670reponame:Nativa (Sinop)instname:Universidade Federal de Mato Grosso (UFMT)instacron:UFMTporhttps://periodicoscientificos.ufmt.br/ojs/index.php/nativa/article/view/13922/11625Copyright (c) 2022 Nativahttps://creativecommons.org/licenses/by-nc/4.0info:eu-repo/semantics/openAccessSilva, Maurício Bruno Prado daSouza, Valter Cesar dePires Cremasco, CarolineCalça, Marcus Vinícius ContesSantos, Cícero Manoel dosCremasco, Camila PiresGabriel Filho, Luís Roberto AlmeidaRodrigues, Sergio AugustoEscobedo, João Francisco2022-11-02T00:23:39Zoai:periodicoscientificos.ufmt.br:article/13922Revistahttps://periodicoscientificos.ufmt.br/ojs/index.php/nativaPUBhttps://periodicoscientificos.ufmt.br/ojs/index.php/nativa/oai||rrmelo2@yahoo.com.br2318-76702318-7670opendoar:2022-11-02T00:23:39Nativa (Sinop) - Universidade Federal de Mato Grosso (UFMT)false |
dc.title.none.fl_str_mv |
MACHINE LEARNING MODELS APPLIED IN THE ESTIMATION OF REFERENCE EVAPOTRANSPIRATION FROM THE WESTERN PLATEAU OF PAULISTA MODELOS DE APRENDIZAJE DE MÁQUINAS APLICADOS EN LA ESTIMACIÓN DE LA EVAPOTRANSPIRACIÓN DE REFERENCIA DE LA MESETA OCCIDENTAL DE PAULISTA MODELOS DE MACHINE LEARNING APLICADOS NA ESTIMAÇÃO DA EVAPOTRANSPIRAÇÃO DE REFERÊNCIA DO PLANALTO OCIDENTAL PAULISTA |
title |
MACHINE LEARNING MODELS APPLIED IN THE ESTIMATION OF REFERENCE EVAPOTRANSPIRATION FROM THE WESTERN PLATEAU OF PAULISTA |
spellingShingle |
MACHINE LEARNING MODELS APPLIED IN THE ESTIMATION OF REFERENCE EVAPOTRANSPIRATION FROM THE WESTERN PLATEAU OF PAULISTA Silva, Maurício Bruno Prado da evapotranspiración aprendizaje automático modelado de evapotranspiración de referencia aprendizaje automático. evapotranspiration machine learning reference evapotranspiration modeling machine learning. evapotranspiração machine learning modelagem da evapotranspiração de referência aprendizagem de máquina. |
title_short |
MACHINE LEARNING MODELS APPLIED IN THE ESTIMATION OF REFERENCE EVAPOTRANSPIRATION FROM THE WESTERN PLATEAU OF PAULISTA |
title_full |
MACHINE LEARNING MODELS APPLIED IN THE ESTIMATION OF REFERENCE EVAPOTRANSPIRATION FROM THE WESTERN PLATEAU OF PAULISTA |
title_fullStr |
MACHINE LEARNING MODELS APPLIED IN THE ESTIMATION OF REFERENCE EVAPOTRANSPIRATION FROM THE WESTERN PLATEAU OF PAULISTA |
title_full_unstemmed |
MACHINE LEARNING MODELS APPLIED IN THE ESTIMATION OF REFERENCE EVAPOTRANSPIRATION FROM THE WESTERN PLATEAU OF PAULISTA |
title_sort |
MACHINE LEARNING MODELS APPLIED IN THE ESTIMATION OF REFERENCE EVAPOTRANSPIRATION FROM THE WESTERN PLATEAU OF PAULISTA |
author |
Silva, Maurício Bruno Prado da |
author_facet |
Silva, Maurício Bruno Prado da Souza, Valter Cesar de Pires Cremasco, Caroline Calça, Marcus Vinícius Contes Santos, Cícero Manoel dos Cremasco, Camila Pires Gabriel Filho, Luís Roberto Almeida Rodrigues, Sergio Augusto Escobedo, João Francisco |
author_role |
author |
author2 |
Souza, Valter Cesar de Pires Cremasco, Caroline Calça, Marcus Vinícius Contes Santos, Cícero Manoel dos Cremasco, Camila Pires Gabriel Filho, Luís Roberto Almeida Rodrigues, Sergio Augusto Escobedo, João Francisco |
author2_role |
author author author author author author author author |
dc.contributor.author.fl_str_mv |
Silva, Maurício Bruno Prado da Souza, Valter Cesar de Pires Cremasco, Caroline Calça, Marcus Vinícius Contes Santos, Cícero Manoel dos Cremasco, Camila Pires Gabriel Filho, Luís Roberto Almeida Rodrigues, Sergio Augusto Escobedo, João Francisco |
dc.subject.por.fl_str_mv |
evapotranspiración aprendizaje automático modelado de evapotranspiración de referencia aprendizaje automático. evapotranspiration machine learning reference evapotranspiration modeling machine learning. evapotranspiração machine learning modelagem da evapotranspiração de referência aprendizagem de máquina. |
topic |
evapotranspiración aprendizaje automático modelado de evapotranspiración de referencia aprendizaje automático. evapotranspiration machine learning reference evapotranspiration modeling machine learning. evapotranspiração machine learning modelagem da evapotranspiração de referência aprendizagem de máquina. |
description |
Evapotranspiration depends on the interaction between meteorological variables (solar radiation, air temperature, precipitation, relative humidity and wind speed) and phytosanitary conditions of agricultural crops. It is complex to build reliable evapotranspiration measurements due to the high costs of implementing micrometeorological techniques, in addition to difficulties in the operation and maintenance of the necessary equipment. The purpose of this research was to model the reference evapotranspiration through machine learning techniques in climatic data from 30 automatic weather stations in the Planalto Ocidental Paulista, State of São Paulo, Brazil, in the period 2013-2017. A comparison of the statistical performance between the techniques used was carried out, where the best performance of the EToMLP4 model (rRMSE = 0.62%), followed by EToANFIS4 (rRMSE = 0.75%), EToSVM4 (rRMSE = 1.19%) and EToGRNN4 (rRMSE = 11.05 %). Performance measures of the validation base show that the proposed models are able to estimate the reference evapotranspiration, with emphasis on the MPL technique. |
publishDate |
2022 |
dc.date.none.fl_str_mv |
2022-11-16 |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
https://periodicoscientificos.ufmt.br/ojs/index.php/nativa/article/view/13922 10.31413/nativa.v10i4.13922 |
url |
https://periodicoscientificos.ufmt.br/ojs/index.php/nativa/article/view/13922 |
identifier_str_mv |
10.31413/nativa.v10i4.13922 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.relation.none.fl_str_mv |
https://periodicoscientificos.ufmt.br/ojs/index.php/nativa/article/view/13922/11625 |
dc.rights.driver.fl_str_mv |
Copyright (c) 2022 Nativa https://creativecommons.org/licenses/by-nc/4.0 info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
Copyright (c) 2022 Nativa https://creativecommons.org/licenses/by-nc/4.0 |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
Universidade Federal de Mato Grosso |
publisher.none.fl_str_mv |
Universidade Federal de Mato Grosso |
dc.source.none.fl_str_mv |
Nativa; v. 10 n. 4 (2022); 506-515 Nativa; Vol. 10 Núm. 4 (2022); 506-515 Nativa; Vol. 10 No. 4 (2022); 506-515 2318-7670 reponame:Nativa (Sinop) instname:Universidade Federal de Mato Grosso (UFMT) instacron:UFMT |
instname_str |
Universidade Federal de Mato Grosso (UFMT) |
instacron_str |
UFMT |
institution |
UFMT |
reponame_str |
Nativa (Sinop) |
collection |
Nativa (Sinop) |
repository.name.fl_str_mv |
Nativa (Sinop) - Universidade Federal de Mato Grosso (UFMT) |
repository.mail.fl_str_mv |
||rrmelo2@yahoo.com.br |
_version_ |
1799711198668652544 |