| |
|
|
 | Acesso ao texto completo restrito à biblioteca da Embrapa Cerrados. Para informações adicionais entre em contato com biblioteca@embrapa.br. |
|
Registro Completo |
|
Biblioteca(s): |
Embrapa Cerrados. |
|
Data corrente: |
15/12/2023 |
|
Data da última atualização: |
15/12/2023 |
|
Tipo da produção científica: |
Artigo em Periódico Indexado |
|
Autoria: |
AIRES, U. R. V.; SILVA, D. D. da; FERNANDES FILHO, E. I.; RODRIGUES, L. N.; ULIANA, E. M.; AMORIM, R. S. S.; RIBEIRO, C. B. de M.; CAMPOS, J. A. |
|
Afiliação: |
UILSON RICARDO VENÂNCIO AIRES, UNIVERSIDADE FEDERAL DE VIÇOSA; DEMETRIUS DAVID DA SILVA, Universidade Federal de Viçosa; ELPÍDIO INÁCIO FERNANDES FILHO, Universidade Federal de Viçosa; LINEU NEIVA RODRIGUES, CPAC; EDUARDO MORGAN ULIANA, Universidade Federal de Mato Grosso; RICARDO SANTOS SILVA AMORIM, Universidade Federal de Viçosa; CELSO BANDEIRA DE MELO RIBEIRO, Universidade Federal de Juiz de Fora; JASMINE ALVES CAMPOS, Universidade Federal de Viçosa. |
|
Título: |
Machine learning-based modeling of surface sediment concentration in Doce river basin. |
|
Ano de publicação: |
2023 |
|
Fonte/Imprenta: |
Journal of Hydrology, v. 619, 2023. e129320. |
|
ISSN: |
0022-1694 |
|
Idioma: |
Inglês |
|
Conteúdo: |
As sediment measurements are laborious and costly, alternative techniques are required to provide such information from more easily measured variables. Thus, the objective of this study was to use machine learning-based models to predict the surface sediment concentration (SSC) in the Doce river basin. The cross-sectional averages of measurements from seven sediment monitoring stations of the Agˆencia Nacional de Aguas ́ e Saneamento Basico ́ located in the Doce riverbed were used as the SSC data. A total of 62 predictor variables were used, which were derived from data on the terrain slope, pedology, land use and cover, precipitation, river discharge and velocity, actual vapotranspiration, surface runoff, soil moisture, temperature, and normalized difference vegetation index. The Boruta and recursive feature elimination variable selection methods were employed to reduce the number of predictor variables. The random forest, Cubist, support vector machine, and eXtreme Gradient Boosting (XGBoost) algorithms as well as least absolute shrinkage and selection operator (LASSO) regression were applied to predict the SSC data. The machine learning algorithms provided superior results, particularly the Cubist and XGBoost models, which exhibited the lowest prediction error and highest efficiency metrics. According to the varImp function from Caret package, the most important predictor variables for the SSC modeling were the daily river discharge on the sediment collection date and time-lagged discharge. The cumulative daily mean precipitation was also important for the sediment modeling. Our findings demonstrate that machine learning models may be a very helpful tool for sediment monitoring and understanding sediment dynamics in the Doce river basin over time. MenosAs sediment measurements are laborious and costly, alternative techniques are required to provide such information from more easily measured variables. Thus, the objective of this study was to use machine learning-based models to predict the surface sediment concentration (SSC) in the Doce river basin. The cross-sectional averages of measurements from seven sediment monitoring stations of the Agˆencia Nacional de Aguas ́ e Saneamento Basico ́ located in the Doce riverbed were used as the SSC data. A total of 62 predictor variables were used, which were derived from data on the terrain slope, pedology, land use and cover, precipitation, river discharge and velocity, actual vapotranspiration, surface runoff, soil moisture, temperature, and normalized difference vegetation index. The Boruta and recursive feature elimination variable selection methods were employed to reduce the number of predictor variables. The random forest, Cubist, support vector machine, and eXtreme Gradient Boosting (XGBoost) algorithms as well as least absolute shrinkage and selection operator (LASSO) regression were applied to predict the SSC data. The machine learning algorithms provided superior results, particularly the Cubist and XGBoost models, which exhibited the lowest prediction error and highest efficiency metrics. According to the varImp function from Caret package, the most important predictor variables for the SSC modeling were the daily river discharge on the sediment collection date and tim... Mostrar Tudo |
|
Thesagro: |
Água Doce; Rio; Sedimento. |
|
Thesaurus Nal: |
Sediment contamination. |
|
Categoria do assunto: |
P Recursos Naturais, Ciências Ambientais e da Terra |
|
Marc: |
LEADER 02534naa a2200265 a 4500
001 2159802
005 2023-12-15
008 2023 bl uuuu u00u1 u #d
022 $a0022-1694
100 1 $aAIRES, U. R. V.
245 $aMachine learning-based modeling of surface sediment concentration in Doce river basin.$h[electronic resource]
260 $c2023
520 $aAs sediment measurements are laborious and costly, alternative techniques are required to provide such information from more easily measured variables. Thus, the objective of this study was to use machine learning-based models to predict the surface sediment concentration (SSC) in the Doce river basin. The cross-sectional averages of measurements from seven sediment monitoring stations of the Agˆencia Nacional de Aguas ́ e Saneamento Basico ́ located in the Doce riverbed were used as the SSC data. A total of 62 predictor variables were used, which were derived from data on the terrain slope, pedology, land use and cover, precipitation, river discharge and velocity, actual vapotranspiration, surface runoff, soil moisture, temperature, and normalized difference vegetation index. The Boruta and recursive feature elimination variable selection methods were employed to reduce the number of predictor variables. The random forest, Cubist, support vector machine, and eXtreme Gradient Boosting (XGBoost) algorithms as well as least absolute shrinkage and selection operator (LASSO) regression were applied to predict the SSC data. The machine learning algorithms provided superior results, particularly the Cubist and XGBoost models, which exhibited the lowest prediction error and highest efficiency metrics. According to the varImp function from Caret package, the most important predictor variables for the SSC modeling were the daily river discharge on the sediment collection date and time-lagged discharge. The cumulative daily mean precipitation was also important for the sediment modeling. Our findings demonstrate that machine learning models may be a very helpful tool for sediment monitoring and understanding sediment dynamics in the Doce river basin over time.
650 $aSediment contamination
650 $aÁgua Doce
650 $aRio
650 $aSedimento
700 1 $aSILVA, D. D. da
700 1 $aFERNANDES FILHO, E. I.
700 1 $aRODRIGUES, L. N.
700 1 $aULIANA, E. M.
700 1 $aAMORIM, R. S. S.
700 1 $aRIBEIRO, C. B. de M.
700 1 $aCAMPOS, J. A.
773 $tJournal of Hydrology$gv. 619, 2023. e129320.
Download
Esconder MarcMostrar Marc Completo |
|
Registro original: |
Embrapa Cerrados (CPAC) |
|
|
Biblioteca |
ID |
Origem |
Tipo/Formato |
Classificação |
Cutter |
Registro |
Volume |
Status |
URL |
Voltar
|
|
|
| Registros recuperados : 10 | |
| Registros recuperados : 10 | |
|
| Nenhum registro encontrado para a expressão de busca informada. |
|
|
