Artificial neural networks and multiple linear regression model using principal components to estimate rainfall over South America

Detalhes bibliográficos
Autor(a) principal: Santos, T. Soares dos
Data de Publicação: 2016
Outros Autores: Mendes, David, Torres, R. Rodrigues
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Institucional da UFRN
Texto Completo: https://repositorio.ufrn.br/jspui/handle/123456789/29096
https://doi.org/10.5194/npg-23-13-2016
Resumo: Several studies have been devoted to dynamic and statistical downscaling for analysis of both climate variability and climate change. This paper introduces an application of artificial neural networks (ANNs) and multiple linear regression (MLR) by principal components to estimate rainfall in South America. This method is proposed for downscaling monthly precipitation time series over South America for three regions: the Amazon; northeastern Brazil; and the La Plata Basin, which is one of the regions of the planet that will be most affected by the climate change projected for the end of the 21st century. The downscaling models were developed and validated using CMIP5 model output and observed monthly precipitation. We used general circulation model (GCM) experiments for the 20th century (RCP historical; 1970–1999) and two scenarios (RCP 2.6 and 8.5; 2070–2100). The model test results indicate that the ANNs significantly outperform the MLR downscaling of monthly precipitation variability
id UFRN_8cd510db986961f7b143af879fe199f0
oai_identifier_str oai:https://repositorio.ufrn.br:123456789/29096
network_acronym_str UFRN
network_name_str Repositório Institucional da UFRN
repository_id_str
spelling Santos, T. Soares dosMendes, DavidTorres, R. Rodrigues2020-05-30T13:55:04Z2020-05-30T13:55:04Z2016SANTOS, T. Soares dos ; Mendes, D. ; TORRES, R. Rodrigues. Artificial neural networks and multiple linear regression model using principal components to estimate rainfall over South America. Nonlinear processes in Geophysics, v. 23, p. 13-20, 2016. Disponível em: https://www.nonlin-processes-geophys.net/23/13/2016/npg-23-13-2016.pdf. Acesso em: 29 Maio 2020. https://doi.org/10.5194/npg-23-13-2016https://repositorio.ufrn.br/jspui/handle/123456789/29096https://doi.org/10.5194/npg-23-13-2016Nonlinear Processes GeophysicsAttribution 3.0 Brazilhttp://creativecommons.org/licenses/by/3.0/br/info:eu-repo/semantics/openAccessApplication of artificial neural networksArtificial neural networks and multiple linear regression model using principal components to estimate rainfall over South Americainfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleSeveral studies have been devoted to dynamic and statistical downscaling for analysis of both climate variability and climate change. This paper introduces an application of artificial neural networks (ANNs) and multiple linear regression (MLR) by principal components to estimate rainfall in South America. This method is proposed for downscaling monthly precipitation time series over South America for three regions: the Amazon; northeastern Brazil; and the La Plata Basin, which is one of the regions of the planet that will be most affected by the climate change projected for the end of the 21st century. The downscaling models were developed and validated using CMIP5 model output and observed monthly precipitation. We used general circulation model (GCM) experiments for the 20th century (RCP historical; 1970–1999) and two scenarios (RCP 2.6 and 8.5; 2070–2100). The model test results indicate that the ANNs significantly outperform the MLR downscaling of monthly precipitation variabilityengreponame:Repositório Institucional da UFRNinstname:Universidade Federal do Rio Grande do Norte (UFRN)instacron:UFRNORIGINALArtificialNeuralNetworksandMultipleLinearRegression_Mendes_2016.pdfArtificialNeuralNetworksandMultipleLinearRegression_Mendes_2016.pdfapplication/pdf2562159https://repositorio.ufrn.br/bitstream/123456789/29096/1/ArtificialNeuralNetworksandMultipleLinearRegression_Mendes_2016.pdfa2a9e2795decd40bb3f2fe5a25af690eMD51CC-LICENSElicense_rdflicense_rdfapplication/rdf+xml; charset=utf-8914https://repositorio.ufrn.br/bitstream/123456789/29096/2/license_rdf4d2950bda3d176f570a9f8b328dfbbefMD52LICENSElicense.txtlicense.txttext/plain; charset=utf-81484https://repositorio.ufrn.br/bitstream/123456789/29096/3/license.txte9597aa2854d128fd968be5edc8a28d9MD53TEXTArtificialNeuralNetworksandMultipleLinearRegression_Mendes_2016.pdf.txtArtificialNeuralNetworksandMultipleLinearRegression_Mendes_2016.pdf.txtExtracted texttext/plain26709https://repositorio.ufrn.br/bitstream/123456789/29096/4/ArtificialNeuralNetworksandMultipleLinearRegression_Mendes_2016.pdf.txt2cf579455e05da8383e53b13bb84c3fdMD54THUMBNAILArtificialNeuralNetworksandMultipleLinearRegression_Mendes_2016.pdf.jpgArtificialNeuralNetworksandMultipleLinearRegression_Mendes_2016.pdf.jpgGenerated Thumbnailimage/jpeg1782https://repositorio.ufrn.br/bitstream/123456789/29096/5/ArtificialNeuralNetworksandMultipleLinearRegression_Mendes_2016.pdf.jpgac15658952a1d9e440e3d2f7a8630d6eMD55123456789/290962020-05-31 04:54:12.989oai:https://repositorio.ufrn.br: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Repositório de PublicaçõesPUBhttp://repositorio.ufrn.br/oai/opendoar:2020-05-31T07:54:12Repositório Institucional da UFRN - Universidade Federal do Rio Grande do Norte (UFRN)false
dc.title.pt_BR.fl_str_mv Artificial neural networks and multiple linear regression model using principal components to estimate rainfall over South America
title Artificial neural networks and multiple linear regression model using principal components to estimate rainfall over South America
spellingShingle Artificial neural networks and multiple linear regression model using principal components to estimate rainfall over South America
Santos, T. Soares dos
Application of artificial neural networks
title_short Artificial neural networks and multiple linear regression model using principal components to estimate rainfall over South America
title_full Artificial neural networks and multiple linear regression model using principal components to estimate rainfall over South America
title_fullStr Artificial neural networks and multiple linear regression model using principal components to estimate rainfall over South America
title_full_unstemmed Artificial neural networks and multiple linear regression model using principal components to estimate rainfall over South America
title_sort Artificial neural networks and multiple linear regression model using principal components to estimate rainfall over South America
author Santos, T. Soares dos
author_facet Santos, T. Soares dos
Mendes, David
Torres, R. Rodrigues
author_role author
author2 Mendes, David
Torres, R. Rodrigues
author2_role author
author
dc.contributor.author.fl_str_mv Santos, T. Soares dos
Mendes, David
Torres, R. Rodrigues
dc.subject.por.fl_str_mv Application of artificial neural networks
topic Application of artificial neural networks
description Several studies have been devoted to dynamic and statistical downscaling for analysis of both climate variability and climate change. This paper introduces an application of artificial neural networks (ANNs) and multiple linear regression (MLR) by principal components to estimate rainfall in South America. This method is proposed for downscaling monthly precipitation time series over South America for three regions: the Amazon; northeastern Brazil; and the La Plata Basin, which is one of the regions of the planet that will be most affected by the climate change projected for the end of the 21st century. The downscaling models were developed and validated using CMIP5 model output and observed monthly precipitation. We used general circulation model (GCM) experiments for the 20th century (RCP historical; 1970–1999) and two scenarios (RCP 2.6 and 8.5; 2070–2100). The model test results indicate that the ANNs significantly outperform the MLR downscaling of monthly precipitation variability
publishDate 2016
dc.date.issued.fl_str_mv 2016
dc.date.accessioned.fl_str_mv 2020-05-30T13:55:04Z
dc.date.available.fl_str_mv 2020-05-30T13:55:04Z
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.citation.fl_str_mv SANTOS, T. Soares dos ; Mendes, D. ; TORRES, R. Rodrigues. Artificial neural networks and multiple linear regression model using principal components to estimate rainfall over South America. Nonlinear processes in Geophysics, v. 23, p. 13-20, 2016. Disponível em: https://www.nonlin-processes-geophys.net/23/13/2016/npg-23-13-2016.pdf. Acesso em: 29 Maio 2020. https://doi.org/10.5194/npg-23-13-2016
dc.identifier.uri.fl_str_mv https://repositorio.ufrn.br/jspui/handle/123456789/29096
dc.identifier.doi.none.fl_str_mv https://doi.org/10.5194/npg-23-13-2016
identifier_str_mv SANTOS, T. Soares dos ; Mendes, D. ; TORRES, R. Rodrigues. Artificial neural networks and multiple linear regression model using principal components to estimate rainfall over South America. Nonlinear processes in Geophysics, v. 23, p. 13-20, 2016. Disponível em: https://www.nonlin-processes-geophys.net/23/13/2016/npg-23-13-2016.pdf. Acesso em: 29 Maio 2020. https://doi.org/10.5194/npg-23-13-2016
url https://repositorio.ufrn.br/jspui/handle/123456789/29096
https://doi.org/10.5194/npg-23-13-2016
dc.language.iso.fl_str_mv eng
language eng
dc.rights.driver.fl_str_mv Attribution 3.0 Brazil
http://creativecommons.org/licenses/by/3.0/br/
info:eu-repo/semantics/openAccess
rights_invalid_str_mv Attribution 3.0 Brazil
http://creativecommons.org/licenses/by/3.0/br/
eu_rights_str_mv openAccess
dc.publisher.none.fl_str_mv Nonlinear Processes Geophysics
publisher.none.fl_str_mv Nonlinear Processes Geophysics
dc.source.none.fl_str_mv reponame:Repositório Institucional da UFRN
instname:Universidade Federal do Rio Grande do Norte (UFRN)
instacron:UFRN
instname_str Universidade Federal do Rio Grande do Norte (UFRN)
instacron_str UFRN
institution UFRN
reponame_str Repositório Institucional da UFRN
collection Repositório Institucional da UFRN
bitstream.url.fl_str_mv https://repositorio.ufrn.br/bitstream/123456789/29096/1/ArtificialNeuralNetworksandMultipleLinearRegression_Mendes_2016.pdf
https://repositorio.ufrn.br/bitstream/123456789/29096/2/license_rdf
https://repositorio.ufrn.br/bitstream/123456789/29096/3/license.txt
https://repositorio.ufrn.br/bitstream/123456789/29096/4/ArtificialNeuralNetworksandMultipleLinearRegression_Mendes_2016.pdf.txt
https://repositorio.ufrn.br/bitstream/123456789/29096/5/ArtificialNeuralNetworksandMultipleLinearRegression_Mendes_2016.pdf.jpg
bitstream.checksum.fl_str_mv a2a9e2795decd40bb3f2fe5a25af690e
4d2950bda3d176f570a9f8b328dfbbef
e9597aa2854d128fd968be5edc8a28d9
2cf579455e05da8383e53b13bb84c3fd
ac15658952a1d9e440e3d2f7a8630d6e
bitstream.checksumAlgorithm.fl_str_mv MD5
MD5
MD5
MD5
MD5
repository.name.fl_str_mv Repositório Institucional da UFRN - Universidade Federal do Rio Grande do Norte (UFRN)
repository.mail.fl_str_mv
_version_ 1814832944132390912

Registros relacionados