Modelos estatísticos empregados para a previsão sazonal da precipitação no Brasil
Ano de defesa: | 2021 |
---|---|
Autor(a) principal: | |
Orientador(a): | |
Banca de defesa: | , , |
Tipo de documento: | Tese |
Tipo de acesso: | Acesso aberto |
Idioma: | por |
Instituição de defesa: |
Universidade Federal de Santa Maria
Centro de Ciências Naturais e Exatas |
Programa de Pós-Graduação: |
Programa de Pós-Graduação em Meteorologia
|
Departamento: |
Meteorologia
|
País: |
Brasil
|
Palavras-chave em Português: | |
Palavras-chave em Inglês: | |
Área do conhecimento CNPq: | |
Link de acesso: | http://repositorio.ufsm.br/handle/1/22349 |
Resumo: | This present research aims to apply statistical models of time series for the forecast of seasonal rainfall in sub-regions of the South, Southeast and Midwest regions of Brazil, investigating whether the models of Integrated Autoregressive classes and Moving Averages that take into account the seasonal component (SARIMA), Integrated Autoregressive and Moving Averages that considers a seasonal component and allows the entry of exogenous variables (SARIMAX), Exponential Smoothing and Combined can be used as a support tool for the dynamic models in forecasting monthly accumulation. In order to carry out the study, data from the historical series corresponding to the accumulated monthly combination, extracted from Xavier et al., (2015) from the South, Southeast and Midwest regions of Brazil, between latitudes (20,625° S and 33, 62° S) and longitudes (42.62° W and 57.62° W) in the period from January 1st, 1980 to December 31st, 2013. These data were interpolated to 1o latitude by 1o longitude, being the series the central point. In total, 107 historical series of accumulated monthly graduation were defined, containing each 408 basic series (months). The Sea Surface Temperature (SST) series selected for the same period with 5º latitude by 5º longitude, being the series a central point, comprised in the range between 60ºN and 60ºS, belonging to the ERSSTv5 data set from NOAA (Huang et al., 2017). 1418 historical series of SST were obtained, with each series containing 408 observations. To adjust the models, RStudio software was used. The influence of SST in the sub-regions was determined through the Person correlation. The quality of point forecasts was evaluated by means of the absolute percentage of errors. The predictions were categorized using the quantile technique. The Deibol-Mariano test was used to verify if there is a statistically significant difference between the predictions of the models. The sub-regions with similarities in monthly accumulated precipitation were defined by cluster analysis. The technique determined five similar sub-regions: South Sub-region 1, South Sub-region 2, South Sub-region 3, Southeast / Center 1 and Southeast / Midwest 2. The models proposed for the quarterly seasonal forecasts are adjusted: summer, autumn, winter and spring. The best forecast results for the three South sub-regions were obtained from the autumn and spring period, followed by summer. In the winter period, the models encountered difficulties in adjusting and forecasting, in view of the high variability contained in the time series for these periods. In the Southeast / Midwest regions, models were tested for the months from November to March (extended summer), which is considered a rainy season. The models demonstrated an excellent fit and performance for both regions with errors in point forecasts of around 14% Southeast / Midwest 1 sub-region and 18% Southeast / Midwest 2 sub-region, with no statistically significant difference between the predictions of the tested models. For these sub regions, a strong influence of the SST in the accumulated monthly rainfall must be considered. It is concluded that the proposed ST forecasting models can be used as a tool to support the dynamic models for the forecast of monthly accumulated precipitation in the surveyed regions, with emphasis on the SARIMA model. |
id |
UFSM_4933c7cb798806b99f857914be53ffbf |
---|---|
oai_identifier_str |
oai:repositorio.ufsm.br:1/22349 |
network_acronym_str |
UFSM |
network_name_str |
Biblioteca Digital de Teses e Dissertações do UFSM |
repository_id_str |
|
spelling |
2021-10-06T17:14:20Z2021-10-06T17:14:20Z2021-05-06http://repositorio.ufsm.br/handle/1/22349This present research aims to apply statistical models of time series for the forecast of seasonal rainfall in sub-regions of the South, Southeast and Midwest regions of Brazil, investigating whether the models of Integrated Autoregressive classes and Moving Averages that take into account the seasonal component (SARIMA), Integrated Autoregressive and Moving Averages that considers a seasonal component and allows the entry of exogenous variables (SARIMAX), Exponential Smoothing and Combined can be used as a support tool for the dynamic models in forecasting monthly accumulation. In order to carry out the study, data from the historical series corresponding to the accumulated monthly combination, extracted from Xavier et al., (2015) from the South, Southeast and Midwest regions of Brazil, between latitudes (20,625° S and 33, 62° S) and longitudes (42.62° W and 57.62° W) in the period from January 1st, 1980 to December 31st, 2013. These data were interpolated to 1o latitude by 1o longitude, being the series the central point. In total, 107 historical series of accumulated monthly graduation were defined, containing each 408 basic series (months). The Sea Surface Temperature (SST) series selected for the same period with 5º latitude by 5º longitude, being the series a central point, comprised in the range between 60ºN and 60ºS, belonging to the ERSSTv5 data set from NOAA (Huang et al., 2017). 1418 historical series of SST were obtained, with each series containing 408 observations. To adjust the models, RStudio software was used. The influence of SST in the sub-regions was determined through the Person correlation. The quality of point forecasts was evaluated by means of the absolute percentage of errors. The predictions were categorized using the quantile technique. The Deibol-Mariano test was used to verify if there is a statistically significant difference between the predictions of the models. The sub-regions with similarities in monthly accumulated precipitation were defined by cluster analysis. The technique determined five similar sub-regions: South Sub-region 1, South Sub-region 2, South Sub-region 3, Southeast / Center 1 and Southeast / Midwest 2. The models proposed for the quarterly seasonal forecasts are adjusted: summer, autumn, winter and spring. The best forecast results for the three South sub-regions were obtained from the autumn and spring period, followed by summer. In the winter period, the models encountered difficulties in adjusting and forecasting, in view of the high variability contained in the time series for these periods. In the Southeast / Midwest regions, models were tested for the months from November to March (extended summer), which is considered a rainy season. The models demonstrated an excellent fit and performance for both regions with errors in point forecasts of around 14% Southeast / Midwest 1 sub-region and 18% Southeast / Midwest 2 sub-region, with no statistically significant difference between the predictions of the tested models. For these sub regions, a strong influence of the SST in the accumulated monthly rainfall must be considered. It is concluded that the proposed ST forecasting models can be used as a tool to support the dynamic models for the forecast of monthly accumulated precipitation in the surveyed regions, with emphasis on the SARIMA model.A presente pesquisa tem como objetivo aplicar modelos estatísticos de séries temporais para a previsão da precipitação pluviométrica sazonal em sub-regiões das regiões Sul, Sudeste e Centro-Oeste do Brasil, investigando se os modelos das classes Autoregressivos Integrados e de Médias Móveis que levam em consideração a componente sazonal (SARIMA), Autoregressivos Integrados e de Médias Móveis que consideram a componente sazonal e permitem a entrada de variáveis exógenas (SARIMAX), Alisamento Exponencial e Combinados podem ser usados como ferramenta de apoio aos modelos dinâmicos na previsão da precipitação acumulada mensal. Para realização deste estudo foram considerados os dados da série histórica correspondente à precipitação acumulada mensal, extraídos de Xavier et al., (2015) das regiões Sul, Sudeste e Centro-Oeste do Brasil, compreendidas entre as latitudes (20,625°S e 33,62°S) e longitudes (42,62°W e 57,62°W) no período de 01 de janeiro de 1980 a 31 de dezembro de 2013. Estes dados foram interpolados para 1º latitude por 1º de longitude, sendo a série um ponto central. No total foram obtidas 107 séries históricas de precipitação acumulada mensal, contendo cada série 408 observações (meses). As séries de Temperatura da Superfície do Mar (TSM) selecionadas para o mesmo período com 5º de latitude por 5º de longitude, sendo a série um ponto central, compreendida na faixa entre 60º Norte e 60º Sul pertencentes ao conjunto de dados ERSSTv5 da NOAA (Huang et al., 2017). Obteve-se 1418 séries históricas de TSM, contendo cada série 408 observações. Para ajuste dos modelos utilizou-se o software RStudio. Determinou-se a influência da TSM nas sub-regiões através da correlação de Person. Avaliou-se a qualidade das previsões pontuais por meio da média percentual absoluta dos erros. Categorizou-se as previsões mediante a técnica quantílica. Utilizou-se o teste Deibol-Mariano para verificar se há diferença estatística significativa entre as previsões dos modelos. As sub-regiões com similaridades de precipitação acumulada mensal foram definidas pela análise de agrupamento. A técnica determinou cinco sub-regiões similares: Sub-região Sul 1, Sub-região Sul 2, Sub-região Sul 3, Sub-região Sudeste/Centro 1 e Sub-região Sudeste/Centro-Oeste 2. Para a região Sul foram ajustados os modelos propostos para as previsões sazonais trimestrais: verão, outono, inverno e primavera. Os melhores resultados de previsão para as três sub-regiões Sul foram obtidos para o período de outono e primavera, seguidas do verão. No período de inverno os modelos encontraram dificuldades de ajuste e previsões, tendo em vista a alta variabilidade contida nas séries temporais para esses períodos. Nas regiões Sudeste/Centro-Oeste testou-se os modelos para os meses de novembro a março (verão estendido), que é considerado período chuvoso. Os modelos demonstraram um excelente ajuste e desempenho para ambas as regiões com erros nas previsões pontuais em torno de 14% sub-região Sudeste/Centro-Oeste 1 e 18% sub-região Sudeste/Centro-Oeste 2, não havendo diferença estatística significativa entre as previsões dos modelos testados. Há de se considerar para essas sub-regiões uma forte influência da TSM na precipitação acumulada mensal. Conclui-se que os modelos propostos de previsão de ST podem ser usados como uma ferramenta de apoio aos modelos dinâmicos para a previsão da precipitação acumulada mensal nas regiões pesquisadas, com destaque para o modelo SARIMA.porUniversidade Federal de Santa MariaCentro de Ciências Naturais e ExatasPrograma de Pós-Graduação em MeteorologiaUFSMBrasilMeteorologiaAttribution-NonCommercial-NoDerivatives 4.0 Internationalhttp://creativecommons.org/licenses/by-nc-nd/4.0/info:eu-repo/semantics/openAccessPrecipitaçãoPrevisão sazonalModelos estatísticosPrecipitationSeasonal forecastStatistical modelsCNPQ::CIENCIAS EXATAS E DA TERRA::GEOCIENCIAS::METEOROLOGIAModelos estatísticos empregados para a previsão sazonal da precipitação no BrasilStatistical models employed for the seasonal forecasting of precipitation in the south, southeast and midwest of Brazil.info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/doctoralThesisFerraz, Simone Erotildes Teleginskihttp://lattes.cnpq.br/5545006407615789Boiaski, Nathalie TissotArsego, Diogo AlessandroJacobi, Luciane Floreshttp://lattes.cnpq.br/2021705206656224Tibulo, Cleiton100700300004600600600600600890e04b2-49dc-4fe7-a16e-07665d183a7debd5be8f-8e8e-4369-ac68-2004964989d66db3b33c-2029-4d21-8433-c027fbb66c1df7b65e4e-46d3-426b-893f-6da258d389abdf4bf88e-6c99-45e3-9f41-6d01b5998359reponame:Biblioteca Digital de Teses e Dissertações do UFSMinstname:Universidade Federal de Santa Maria (UFSM)instacron:UFSMORIGINALTES_PPGMETEOROLOGIA_2021_TIBULO_CLEITON.pdfTES_PPGMETEOROLOGIA_2021_TIBULO_CLEITON.pdfTese de Doutoradoapplication/pdf7942901http://repositorio.ufsm.br/bitstream/1/22349/1/TES_PPGMETEOROLOGIA_2021_TIBULO_CLEITON.pdf1b6d6a434b5af38a5b2940a79db19ffcMD51CC-LICENSElicense_rdflicense_rdfapplication/rdf+xml; charset=utf-8805http://repositorio.ufsm.br/bitstream/1/22349/2/license_rdf4460e5956bc1d1639be9ae6146a50347MD52LICENSElicense.txtlicense.txttext/plain; charset=utf-816http://repositorio.ufsm.br/bitstream/1/22349/3/license.txt6eeec7985884eb94336b41cc5308bf0fMD53TEXTTES_PPGMETEOROLOGIA_2021_TIBULO_CLEITON.pdf.txtTES_PPGMETEOROLOGIA_2021_TIBULO_CLEITON.pdf.txtExtracted texttext/plain380331http://repositorio.ufsm.br/bitstream/1/22349/4/TES_PPGMETEOROLOGIA_2021_TIBULO_CLEITON.pdf.txt7d52fd01063d3fe6a9932ae7e2f4849fMD54THUMBNAILTES_PPGMETEOROLOGIA_2021_TIBULO_CLEITON.pdf.jpgTES_PPGMETEOROLOGIA_2021_TIBULO_CLEITON.pdf.jpgIM Thumbnailimage/jpeg4311http://repositorio.ufsm.br/bitstream/1/22349/5/TES_PPGMETEOROLOGIA_2021_TIBULO_CLEITON.pdf.jpg673100d4443e1e78cf26d691f6f052eeMD551/223492021-10-07 03:04:33.621oai:repositorio.ufsm.br:1/22349Q3JlYXRpdmUgQ29tbXVucw==Biblioteca Digital de Teses e Dissertaçõeshttps://repositorio.ufsm.br/ONGhttps://repositorio.ufsm.br/oai/requestatendimento.sib@ufsm.br||tedebc@gmail.comopendoar:2021-10-07T06:04:33Biblioteca Digital de Teses e Dissertações do UFSM - Universidade Federal de Santa Maria (UFSM)false |
dc.title.por.fl_str_mv |
Modelos estatísticos empregados para a previsão sazonal da precipitação no Brasil |
dc.title.alternative.eng.fl_str_mv |
Statistical models employed for the seasonal forecasting of precipitation in the south, southeast and midwest of Brazil. |
title |
Modelos estatísticos empregados para a previsão sazonal da precipitação no Brasil |
spellingShingle |
Modelos estatísticos empregados para a previsão sazonal da precipitação no Brasil Tibulo, Cleiton Precipitação Previsão sazonal Modelos estatísticos Precipitation Seasonal forecast Statistical models CNPQ::CIENCIAS EXATAS E DA TERRA::GEOCIENCIAS::METEOROLOGIA |
title_short |
Modelos estatísticos empregados para a previsão sazonal da precipitação no Brasil |
title_full |
Modelos estatísticos empregados para a previsão sazonal da precipitação no Brasil |
title_fullStr |
Modelos estatísticos empregados para a previsão sazonal da precipitação no Brasil |
title_full_unstemmed |
Modelos estatísticos empregados para a previsão sazonal da precipitação no Brasil |
title_sort |
Modelos estatísticos empregados para a previsão sazonal da precipitação no Brasil |
author |
Tibulo, Cleiton |
author_facet |
Tibulo, Cleiton |
author_role |
author |
dc.contributor.advisor1.fl_str_mv |
Ferraz, Simone Erotildes Teleginski |
dc.contributor.advisor1Lattes.fl_str_mv |
http://lattes.cnpq.br/5545006407615789 |
dc.contributor.referee1.fl_str_mv |
Boiaski, Nathalie Tissot |
dc.contributor.referee2.fl_str_mv |
Arsego, Diogo Alessandro |
dc.contributor.referee3.fl_str_mv |
Jacobi, Luciane Flores |
dc.contributor.authorLattes.fl_str_mv |
http://lattes.cnpq.br/2021705206656224 |
dc.contributor.author.fl_str_mv |
Tibulo, Cleiton |
contributor_str_mv |
Ferraz, Simone Erotildes Teleginski Boiaski, Nathalie Tissot Arsego, Diogo Alessandro Jacobi, Luciane Flores |
dc.subject.por.fl_str_mv |
Precipitação Previsão sazonal Modelos estatísticos |
topic |
Precipitação Previsão sazonal Modelos estatísticos Precipitation Seasonal forecast Statistical models CNPQ::CIENCIAS EXATAS E DA TERRA::GEOCIENCIAS::METEOROLOGIA |
dc.subject.eng.fl_str_mv |
Precipitation Seasonal forecast Statistical models |
dc.subject.cnpq.fl_str_mv |
CNPQ::CIENCIAS EXATAS E DA TERRA::GEOCIENCIAS::METEOROLOGIA |
description |
This present research aims to apply statistical models of time series for the forecast of seasonal rainfall in sub-regions of the South, Southeast and Midwest regions of Brazil, investigating whether the models of Integrated Autoregressive classes and Moving Averages that take into account the seasonal component (SARIMA), Integrated Autoregressive and Moving Averages that considers a seasonal component and allows the entry of exogenous variables (SARIMAX), Exponential Smoothing and Combined can be used as a support tool for the dynamic models in forecasting monthly accumulation. In order to carry out the study, data from the historical series corresponding to the accumulated monthly combination, extracted from Xavier et al., (2015) from the South, Southeast and Midwest regions of Brazil, between latitudes (20,625° S and 33, 62° S) and longitudes (42.62° W and 57.62° W) in the period from January 1st, 1980 to December 31st, 2013. These data were interpolated to 1o latitude by 1o longitude, being the series the central point. In total, 107 historical series of accumulated monthly graduation were defined, containing each 408 basic series (months). The Sea Surface Temperature (SST) series selected for the same period with 5º latitude by 5º longitude, being the series a central point, comprised in the range between 60ºN and 60ºS, belonging to the ERSSTv5 data set from NOAA (Huang et al., 2017). 1418 historical series of SST were obtained, with each series containing 408 observations. To adjust the models, RStudio software was used. The influence of SST in the sub-regions was determined through the Person correlation. The quality of point forecasts was evaluated by means of the absolute percentage of errors. The predictions were categorized using the quantile technique. The Deibol-Mariano test was used to verify if there is a statistically significant difference between the predictions of the models. The sub-regions with similarities in monthly accumulated precipitation were defined by cluster analysis. The technique determined five similar sub-regions: South Sub-region 1, South Sub-region 2, South Sub-region 3, Southeast / Center 1 and Southeast / Midwest 2. The models proposed for the quarterly seasonal forecasts are adjusted: summer, autumn, winter and spring. The best forecast results for the three South sub-regions were obtained from the autumn and spring period, followed by summer. In the winter period, the models encountered difficulties in adjusting and forecasting, in view of the high variability contained in the time series for these periods. In the Southeast / Midwest regions, models were tested for the months from November to March (extended summer), which is considered a rainy season. The models demonstrated an excellent fit and performance for both regions with errors in point forecasts of around 14% Southeast / Midwest 1 sub-region and 18% Southeast / Midwest 2 sub-region, with no statistically significant difference between the predictions of the tested models. For these sub regions, a strong influence of the SST in the accumulated monthly rainfall must be considered. It is concluded that the proposed ST forecasting models can be used as a tool to support the dynamic models for the forecast of monthly accumulated precipitation in the surveyed regions, with emphasis on the SARIMA model. |
publishDate |
2021 |
dc.date.accessioned.fl_str_mv |
2021-10-06T17:14:20Z |
dc.date.available.fl_str_mv |
2021-10-06T17:14:20Z |
dc.date.issued.fl_str_mv |
2021-05-06 |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/doctoralThesis |
format |
doctoralThesis |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://repositorio.ufsm.br/handle/1/22349 |
url |
http://repositorio.ufsm.br/handle/1/22349 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.relation.cnpq.fl_str_mv |
100700300004 |
dc.relation.confidence.fl_str_mv |
600 600 600 600 600 |
dc.relation.authority.fl_str_mv |
890e04b2-49dc-4fe7-a16e-07665d183a7d ebd5be8f-8e8e-4369-ac68-2004964989d6 6db3b33c-2029-4d21-8433-c027fbb66c1d f7b65e4e-46d3-426b-893f-6da258d389ab df4bf88e-6c99-45e3-9f41-6d01b5998359 |
dc.rights.driver.fl_str_mv |
Attribution-NonCommercial-NoDerivatives 4.0 International http://creativecommons.org/licenses/by-nc-nd/4.0/ info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
Attribution-NonCommercial-NoDerivatives 4.0 International http://creativecommons.org/licenses/by-nc-nd/4.0/ |
eu_rights_str_mv |
openAccess |
dc.publisher.none.fl_str_mv |
Universidade Federal de Santa Maria Centro de Ciências Naturais e Exatas |
dc.publisher.program.fl_str_mv |
Programa de Pós-Graduação em Meteorologia |
dc.publisher.initials.fl_str_mv |
UFSM |
dc.publisher.country.fl_str_mv |
Brasil |
dc.publisher.department.fl_str_mv |
Meteorologia |
publisher.none.fl_str_mv |
Universidade Federal de Santa Maria Centro de Ciências Naturais e Exatas |
dc.source.none.fl_str_mv |
reponame:Biblioteca Digital de Teses e Dissertações do UFSM instname:Universidade Federal de Santa Maria (UFSM) instacron:UFSM |
instname_str |
Universidade Federal de Santa Maria (UFSM) |
instacron_str |
UFSM |
institution |
UFSM |
reponame_str |
Biblioteca Digital de Teses e Dissertações do UFSM |
collection |
Biblioteca Digital de Teses e Dissertações do UFSM |
bitstream.url.fl_str_mv |
http://repositorio.ufsm.br/bitstream/1/22349/1/TES_PPGMETEOROLOGIA_2021_TIBULO_CLEITON.pdf http://repositorio.ufsm.br/bitstream/1/22349/2/license_rdf http://repositorio.ufsm.br/bitstream/1/22349/3/license.txt http://repositorio.ufsm.br/bitstream/1/22349/4/TES_PPGMETEOROLOGIA_2021_TIBULO_CLEITON.pdf.txt http://repositorio.ufsm.br/bitstream/1/22349/5/TES_PPGMETEOROLOGIA_2021_TIBULO_CLEITON.pdf.jpg |
bitstream.checksum.fl_str_mv |
1b6d6a434b5af38a5b2940a79db19ffc 4460e5956bc1d1639be9ae6146a50347 6eeec7985884eb94336b41cc5308bf0f 7d52fd01063d3fe6a9932ae7e2f4849f 673100d4443e1e78cf26d691f6f052ee |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 MD5 MD5 |
repository.name.fl_str_mv |
Biblioteca Digital de Teses e Dissertações do UFSM - Universidade Federal de Santa Maria (UFSM) |
repository.mail.fl_str_mv |
atendimento.sib@ufsm.br||tedebc@gmail.com |
_version_ |
1793240111045935104 |