Application of Artificial Neural Networks (ANNs) in the Gap Filling of Meteorological Time Series

Detalhes bibliográficos
Autor(a) principal: Coutinho,Eluã Ramos
Data de Publicação: 2018
Outros Autores: Silva,Robson Mariano da, Madeira,Jonni Guiller Ferreira, Coutinho,Pollyanna Rodrigues de Oliveira dos Santos, Boloy,Ronney Arismel Mancebo, Delgado,Angel Ramon Sanchez
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Revista Brasileira de Meteorologia (Online)
Texto Completo: http://old.scielo.br/scielo.php?script=sci_arttext&pid=S0102-77862018000200317
Resumo: Abstract This study estimates and fills real flaws in a series of meteorological data belonging to four regions of the state of Rio de Janeiro. For this, an Artificial Neural Network (ANN) of Multilayer Perceptron (MLP) was applied. In order to evaluate its adequacy, the monthly variables of maximum air temperature and relative humidity of the period between 05/31/2002 and 12/31/2014 were estimated and compared with the results obtained by Multiple Linear Regression (MLR) and Regions Average (RA), and still faced with the recorded data. To analyze the estimated values and define the best model for filling, statistical techniques were applied such as correlation coefficient (r), Mean Percentage Error (MPE) and others. The results showed a high relation with the recorded data, presenting indexes between 0.94 to 0.98 of (r) for maximum air temperature and between 2.32% to 1.05% of (MPE), maintaining the precision between 97% A 99%. For the relative air humidity, the index (r) with MLP remained between 0.77 and 0.94 and (MPE) between 2.41% and 1.85%, maintaining estimates between 97% and 98%. These results highlight MLP as being effective in estimating and filling missing values.
id SBMET-1_706b4cb20efa6d5505a3d51956060403
oai_identifier_str oai:scielo:S0102-77862018000200317
network_acronym_str SBMET-1
network_name_str Revista Brasileira de Meteorologia (Online)
repository_id_str
spelling Application of Artificial Neural Networks (ANNs) in the Gap Filling of Meteorological Time Seriesfault fillingmeteorological dataArtificial Neural Network (ANN)Multilayer Perceptron (MLP)Multiple Linear Regression (MLR)Abstract This study estimates and fills real flaws in a series of meteorological data belonging to four regions of the state of Rio de Janeiro. For this, an Artificial Neural Network (ANN) of Multilayer Perceptron (MLP) was applied. In order to evaluate its adequacy, the monthly variables of maximum air temperature and relative humidity of the period between 05/31/2002 and 12/31/2014 were estimated and compared with the results obtained by Multiple Linear Regression (MLR) and Regions Average (RA), and still faced with the recorded data. To analyze the estimated values and define the best model for filling, statistical techniques were applied such as correlation coefficient (r), Mean Percentage Error (MPE) and others. The results showed a high relation with the recorded data, presenting indexes between 0.94 to 0.98 of (r) for maximum air temperature and between 2.32% to 1.05% of (MPE), maintaining the precision between 97% A 99%. For the relative air humidity, the index (r) with MLP remained between 0.77 and 0.94 and (MPE) between 2.41% and 1.85%, maintaining estimates between 97% and 98%. These results highlight MLP as being effective in estimating and filling missing values.Sociedade Brasileira de Meteorologia2018-06-01info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersiontext/htmlhttp://old.scielo.br/scielo.php?script=sci_arttext&pid=S0102-77862018000200317Revista Brasileira de Meteorologia v.33 n.2 2018reponame:Revista Brasileira de Meteorologia (Online)instname:Sociedade Brasileira de Meteorologia (SBMET)instacron:SBMET10.1590/0102-7786332013info:eu-repo/semantics/openAccessCoutinho,Eluã RamosSilva,Robson Mariano daMadeira,Jonni Guiller FerreiraCoutinho,Pollyanna Rodrigues de Oliveira dos SantosBoloy,Ronney Arismel ManceboDelgado,Angel Ramon Sanchezeng2019-05-27T00:00:00Zoai:scielo:S0102-77862018000200317Revistahttp://www.rbmet.org.br/port/index.phpONGhttps://old.scielo.br/oai/scielo-oai.php||rbmet@rbmet.org.br1982-43510102-7786opendoar:2019-05-27T00:00Revista Brasileira de Meteorologia (Online) - Sociedade Brasileira de Meteorologia (SBMET)false
dc.title.none.fl_str_mv Application of Artificial Neural Networks (ANNs) in the Gap Filling of Meteorological Time Series
title Application of Artificial Neural Networks (ANNs) in the Gap Filling of Meteorological Time Series
spellingShingle Application of Artificial Neural Networks (ANNs) in the Gap Filling of Meteorological Time Series
Coutinho,Eluã Ramos
fault filling
meteorological data
Artificial Neural Network (ANN)
Multilayer Perceptron (MLP)
Multiple Linear Regression (MLR)
title_short Application of Artificial Neural Networks (ANNs) in the Gap Filling of Meteorological Time Series
title_full Application of Artificial Neural Networks (ANNs) in the Gap Filling of Meteorological Time Series
title_fullStr Application of Artificial Neural Networks (ANNs) in the Gap Filling of Meteorological Time Series
title_full_unstemmed Application of Artificial Neural Networks (ANNs) in the Gap Filling of Meteorological Time Series
title_sort Application of Artificial Neural Networks (ANNs) in the Gap Filling of Meteorological Time Series
author Coutinho,Eluã Ramos
author_facet Coutinho,Eluã Ramos
Silva,Robson Mariano da
Madeira,Jonni Guiller Ferreira
Coutinho,Pollyanna Rodrigues de Oliveira dos Santos
Boloy,Ronney Arismel Mancebo
Delgado,Angel Ramon Sanchez
author_role author
author2 Silva,Robson Mariano da
Madeira,Jonni Guiller Ferreira
Coutinho,Pollyanna Rodrigues de Oliveira dos Santos
Boloy,Ronney Arismel Mancebo
Delgado,Angel Ramon Sanchez
author2_role author
author
author
author
author
dc.contributor.author.fl_str_mv Coutinho,Eluã Ramos
Silva,Robson Mariano da
Madeira,Jonni Guiller Ferreira
Coutinho,Pollyanna Rodrigues de Oliveira dos Santos
Boloy,Ronney Arismel Mancebo
Delgado,Angel Ramon Sanchez
dc.subject.por.fl_str_mv fault filling
meteorological data
Artificial Neural Network (ANN)
Multilayer Perceptron (MLP)
Multiple Linear Regression (MLR)
topic fault filling
meteorological data
Artificial Neural Network (ANN)
Multilayer Perceptron (MLP)
Multiple Linear Regression (MLR)
description Abstract This study estimates and fills real flaws in a series of meteorological data belonging to four regions of the state of Rio de Janeiro. For this, an Artificial Neural Network (ANN) of Multilayer Perceptron (MLP) was applied. In order to evaluate its adequacy, the monthly variables of maximum air temperature and relative humidity of the period between 05/31/2002 and 12/31/2014 were estimated and compared with the results obtained by Multiple Linear Regression (MLR) and Regions Average (RA), and still faced with the recorded data. To analyze the estimated values and define the best model for filling, statistical techniques were applied such as correlation coefficient (r), Mean Percentage Error (MPE) and others. The results showed a high relation with the recorded data, presenting indexes between 0.94 to 0.98 of (r) for maximum air temperature and between 2.32% to 1.05% of (MPE), maintaining the precision between 97% A 99%. For the relative air humidity, the index (r) with MLP remained between 0.77 and 0.94 and (MPE) between 2.41% and 1.85%, maintaining estimates between 97% and 98%. These results highlight MLP as being effective in estimating and filling missing values.
publishDate 2018
dc.date.none.fl_str_mv 2018-06-01
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://old.scielo.br/scielo.php?script=sci_arttext&pid=S0102-77862018000200317
url http://old.scielo.br/scielo.php?script=sci_arttext&pid=S0102-77862018000200317
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv 10.1590/0102-7786332013
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv text/html
dc.publisher.none.fl_str_mv Sociedade Brasileira de Meteorologia
publisher.none.fl_str_mv Sociedade Brasileira de Meteorologia
dc.source.none.fl_str_mv Revista Brasileira de Meteorologia v.33 n.2 2018
reponame:Revista Brasileira de Meteorologia (Online)
instname:Sociedade Brasileira de Meteorologia (SBMET)
instacron:SBMET
instname_str Sociedade Brasileira de Meteorologia (SBMET)
instacron_str SBMET
institution SBMET
reponame_str Revista Brasileira de Meteorologia (Online)
collection Revista Brasileira de Meteorologia (Online)
repository.name.fl_str_mv Revista Brasileira de Meteorologia (Online) - Sociedade Brasileira de Meteorologia (SBMET)
repository.mail.fl_str_mv ||rbmet@rbmet.org.br
_version_ 1752122085782585344