Using an Artificial Neural Network for Hidrological Warnings on the Claro River in Caraguatatuba, São Paulo State
Autor(a) principal: | |
---|---|
Data de Publicação: | 2017 |
Outros Autores: | , , |
Tipo de documento: | Artigo |
Idioma: | por |
Título da fonte: | Anuário do Instituto de Geociências (Online) |
Texto Completo: | https://revistas.ufrj.br/index.php/aigeo/article/view/7859 |
Resumo: | The river flow prediction of a hydrological basin with natural disaster risk, such as floods and flash floods, is an important feature of early warning programs. This work presents an approach based on the Artificial Neural Networks (ANNs) to predict (neuroforecast) the flow of the Claro River in Caraguatatuba-SP. The observed data of this hydrological basin were used to perform the training, test and validation of the neural networks. The ANN inputs are constituted by n past observed precipitation data and n-1 observed flow data. However, the output of the ANN is composed by n-ith calculated flow data. The choice of the input number (the quantity of past observed data) was made taking into account the following metrics: the NASH coefficient, which is calculated on the temporal data of the network response; and a set of indexes related to the providing an early warning when the estimated flow exceeds a critical flow. Based on performance metrics, the chosen ANN has a good adjustment to the observed flow data (NASH = 0.77) and good ability for providing an early warnings (efficiency of 0.91). |
id |
UFRJ-21_acca4f52baff5ad4549621bac7814769 |
---|---|
oai_identifier_str |
oai:www.revistas.ufrj.br:article/7859 |
network_acronym_str |
UFRJ-21 |
network_name_str |
Anuário do Instituto de Geociências (Online) |
repository_id_str |
|
spelling |
Using an Artificial Neural Network for Hidrological Warnings on the Claro River in Caraguatatuba, São Paulo StateUtilização de Redes Neurais Artificiais em Alertas Hidrológicos: Estudo de Caso na Bacia do Rio Claro em Caraguatatuba, Estado de São PauloArtificial neural network; Hydrological alerts; FloodsRedes neurais artificiais; Alertas hidrológicos; InundaçõesThe river flow prediction of a hydrological basin with natural disaster risk, such as floods and flash floods, is an important feature of early warning programs. This work presents an approach based on the Artificial Neural Networks (ANNs) to predict (neuroforecast) the flow of the Claro River in Caraguatatuba-SP. The observed data of this hydrological basin were used to perform the training, test and validation of the neural networks. The ANN inputs are constituted by n past observed precipitation data and n-1 observed flow data. However, the output of the ANN is composed by n-ith calculated flow data. The choice of the input number (the quantity of past observed data) was made taking into account the following metrics: the NASH coefficient, which is calculated on the temporal data of the network response; and a set of indexes related to the providing an early warning when the estimated flow exceeds a critical flow. Based on performance metrics, the chosen ANN has a good adjustment to the observed flow data (NASH = 0.77) and good ability for providing an early warnings (efficiency of 0.91).A previsão da vazão dos rios de uma bacia hidrográfica com risco de desastres naturais, como inundações e enxurradas, é um recurso fundamental a programas de monitoramento e alerta. Neste trabalho é apresentada uma abordagem baseada em Redes Neurais Artificiais (RNAs) a fim de prever (neuroprevisão) a vazão do rio Claro em Caraguatatuba-SP. Neste estudo, são utilizados dados reais desta bacia hidrográfica, e efetuados o treinamento, teste e validação da rede utilizada. As entradas da RNA são constituídas por n observações passadas de precipitação e n-1 observações de vazão. Já a saída da rede é composta pela n-ésima observação de vazão. A escolha do número de entradas (quantidade de observações passadas) foi feita levando em conta as seguintes métricas: o coeficiente de NASH, calculado sobre a série temporal de resposta da rede; e um conjunto de índices relacionados à emissão de alertas quando a vazão estimada ultrapassa uma vazão crítica. A RNA escolhida, com base nas métricas de desempenho utilizadas, apresentou um bom ajuste à série de vazões observadas (NASH = 0,77) e boa capacidade de emissão de alertas (eficiência de 0,91).Universidade Federal do Rio de Janeiro2017-02-15info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://revistas.ufrj.br/index.php/aigeo/article/view/785910.11137/2016_1_23_31Anuário do Instituto de Geociências; Vol 39, No 1 (2016); 23-31Anuário do Instituto de Geociências; Vol 39, No 1 (2016); 23-311982-39080101-9759reponame:Anuário do Instituto de Geociências (Online)instname:Universidade Federal do Rio de Janeiro (UFRJ)instacron:UFRJporhttps://revistas.ufrj.br/index.php/aigeo/article/view/7859/6340Copyright (c) 2016 Anuário do Instituto de Geociênciashttp://creativecommons.org/licenses/by/4.0info:eu-repo/semantics/openAccessSilva, Mauro Ricardo daSantos, Leonardo Bacelar LimaScofield, Graziela BaldaCortivo, Fabio Dall2017-02-15T18:21:34Zoai:www.revistas.ufrj.br:article/7859Revistahttps://revistas.ufrj.br/index.php/aigeo/indexPUBhttps://revistas.ufrj.br/index.php/aigeo/oaianuario@igeo.ufrj.br||1982-39080101-9759opendoar:2017-02-15T18:21:34Anuário do Instituto de Geociências (Online) - Universidade Federal do Rio de Janeiro (UFRJ)false |
dc.title.none.fl_str_mv |
Using an Artificial Neural Network for Hidrological Warnings on the Claro River in Caraguatatuba, São Paulo State Utilização de Redes Neurais Artificiais em Alertas Hidrológicos: Estudo de Caso na Bacia do Rio Claro em Caraguatatuba, Estado de São Paulo |
title |
Using an Artificial Neural Network for Hidrological Warnings on the Claro River in Caraguatatuba, São Paulo State |
spellingShingle |
Using an Artificial Neural Network for Hidrological Warnings on the Claro River in Caraguatatuba, São Paulo State Silva, Mauro Ricardo da Artificial neural network; Hydrological alerts; Floods Redes neurais artificiais; Alertas hidrológicos; Inundações |
title_short |
Using an Artificial Neural Network for Hidrological Warnings on the Claro River in Caraguatatuba, São Paulo State |
title_full |
Using an Artificial Neural Network for Hidrological Warnings on the Claro River in Caraguatatuba, São Paulo State |
title_fullStr |
Using an Artificial Neural Network for Hidrological Warnings on the Claro River in Caraguatatuba, São Paulo State |
title_full_unstemmed |
Using an Artificial Neural Network for Hidrological Warnings on the Claro River in Caraguatatuba, São Paulo State |
title_sort |
Using an Artificial Neural Network for Hidrological Warnings on the Claro River in Caraguatatuba, São Paulo State |
author |
Silva, Mauro Ricardo da |
author_facet |
Silva, Mauro Ricardo da Santos, Leonardo Bacelar Lima Scofield, Graziela Balda Cortivo, Fabio Dall |
author_role |
author |
author2 |
Santos, Leonardo Bacelar Lima Scofield, Graziela Balda Cortivo, Fabio Dall |
author2_role |
author author author |
dc.contributor.author.fl_str_mv |
Silva, Mauro Ricardo da Santos, Leonardo Bacelar Lima Scofield, Graziela Balda Cortivo, Fabio Dall |
dc.subject.por.fl_str_mv |
Artificial neural network; Hydrological alerts; Floods Redes neurais artificiais; Alertas hidrológicos; Inundações |
topic |
Artificial neural network; Hydrological alerts; Floods Redes neurais artificiais; Alertas hidrológicos; Inundações |
description |
The river flow prediction of a hydrological basin with natural disaster risk, such as floods and flash floods, is an important feature of early warning programs. This work presents an approach based on the Artificial Neural Networks (ANNs) to predict (neuroforecast) the flow of the Claro River in Caraguatatuba-SP. The observed data of this hydrological basin were used to perform the training, test and validation of the neural networks. The ANN inputs are constituted by n past observed precipitation data and n-1 observed flow data. However, the output of the ANN is composed by n-ith calculated flow data. The choice of the input number (the quantity of past observed data) was made taking into account the following metrics: the NASH coefficient, which is calculated on the temporal data of the network response; and a set of indexes related to the providing an early warning when the estimated flow exceeds a critical flow. Based on performance metrics, the chosen ANN has a good adjustment to the observed flow data (NASH = 0.77) and good ability for providing an early warnings (efficiency of 0.91). |
publishDate |
2017 |
dc.date.none.fl_str_mv |
2017-02-15 |
dc.type.none.fl_str_mv |
|
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://revistas.ufrj.br/index.php/aigeo/article/view/7859 10.11137/2016_1_23_31 |
url |
https://revistas.ufrj.br/index.php/aigeo/article/view/7859 |
identifier_str_mv |
10.11137/2016_1_23_31 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.relation.none.fl_str_mv |
https://revistas.ufrj.br/index.php/aigeo/article/view/7859/6340 |
dc.rights.driver.fl_str_mv |
Copyright (c) 2016 Anuário do Instituto de Geociências http://creativecommons.org/licenses/by/4.0 info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
Copyright (c) 2016 Anuário do Instituto de Geociências http://creativecommons.org/licenses/by/4.0 |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
Universidade Federal do Rio de Janeiro |
publisher.none.fl_str_mv |
Universidade Federal do Rio de Janeiro |
dc.source.none.fl_str_mv |
Anuário do Instituto de Geociências; Vol 39, No 1 (2016); 23-31 Anuário do Instituto de Geociências; Vol 39, No 1 (2016); 23-31 1982-3908 0101-9759 reponame:Anuário do Instituto de Geociências (Online) instname:Universidade Federal do Rio de Janeiro (UFRJ) instacron:UFRJ |
instname_str |
Universidade Federal do Rio de Janeiro (UFRJ) |
instacron_str |
UFRJ |
institution |
UFRJ |
reponame_str |
Anuário do Instituto de Geociências (Online) |
collection |
Anuário do Instituto de Geociências (Online) |
repository.name.fl_str_mv |
Anuário do Instituto de Geociências (Online) - Universidade Federal do Rio de Janeiro (UFRJ) |
repository.mail.fl_str_mv |
anuario@igeo.ufrj.br|| |
_version_ |
1797053541702959104 |