| |
|
|
| Registros recuperados : 311 | |
| Registros recuperados : 311 | |
|
|
|
 | Acesso ao texto completo restrito à biblioteca da Embrapa Cerrados. Para informações adicionais entre em contato com cpac.biblioteca@embrapa.br. |
Registro Completo
|
Biblioteca(s): |
Embrapa Cerrados. |
|
Data corrente: |
17/08/2021 |
|
Data da última atualização: |
17/08/2021 |
|
Tipo da produção científica: |
Artigo em Periódico Indexado |
|
Circulação/Nível: |
A - 1 |
|
Autoria: |
ALTHOFF, D.; RODRIGUES, L. N.; SILVA, D. D. da. |
|
Afiliação: |
DANIEL ALTHOFF; LINEU NEIVA RODRIGUES, CPAC; DEMETRIUS DAVID DA SILVA. |
|
Título: |
Addressing hydrological modeling in watersheds under land cover change with deep learning. |
|
Ano de publicação: |
2021 |
|
Fonte/Imprenta: |
Advances in Water Resources, v. 154, 2021. |
|
Páginas: |
12 p. |
|
DOI: |
https://doi.org/10.1016/j.advwatres.2021.103965 |
|
Idioma: |
Inglês |
|
Conteúdo: |
The impacts of land cover change have traditionally been assessed in hydrological modeling with a priori knowl- edge, e.g., using methods based on the curve number, or by calibrating hydrological models over different time periods. However, how hydrological processes respond to such changes is extremely context-dependent. Thus, there is an opportunity for the development of hydrological models that can learn from large hydrological data sets under the context of severe environmental changes. In this study, a single regional hydrological model is developed based on long short-term memory (LSTM) neural networks using different input configurations. One model considers only meteorological forcings as inputs (I1), another model considers meteorological forcings and static catchment attributes (I2), and a third model also considers meteorological forcings and catchment attributes but where the land cover characteristics are dynamic (I3). The models are trained using information from 411 catchments in the Brazilian Cerrado biome. The data set includes, for each catchment, the daily stream- flow observations (target), daily precipitation and reference evapotranspiration (meteorological forcings), and 21 catchment attributes including topography, climate indices, soil characteristics, and land cover characteristics. Considering catchment attributes increases the performance of the LSTM model (I2 and I3 median KGE : 0.69). Considering the land use cover characteristics as dynamic improves the predictions under low-flow conditions (I3 median rNSE : 0.62) when compared to the model considering such characteristics as static (I2 median rNSE : 0.53). This study also uses the deep network with the integrated gradients technique to explore the contribution of the catchment characteristics to streamflow and the number of time steps of influence for the deep network in different regions. MenosThe impacts of land cover change have traditionally been assessed in hydrological modeling with a priori knowl- edge, e.g., using methods based on the curve number, or by calibrating hydrological models over different time periods. However, how hydrological processes respond to such changes is extremely context-dependent. Thus, there is an opportunity for the development of hydrological models that can learn from large hydrological data sets under the context of severe environmental changes. In this study, a single regional hydrological model is developed based on long short-term memory (LSTM) neural networks using different input configurations. One model considers only meteorological forcings as inputs (I1), another model considers meteorological forcings and static catchment attributes (I2), and a third model also considers meteorological forcings and catchment attributes but where the land cover characteristics are dynamic (I3). The models are trained using information from 411 catchments in the Brazilian Cerrado biome. The data set includes, for each catchment, the daily stream- flow observations (target), daily precipitation and reference evapotranspiration (meteorological forcings), and 21 catchment attributes including topography, climate indices, soil characteristics, and land cover characteristics. Considering catchment attributes increases the performance of the LSTM model (I2 and I3 median KGE : 0.69). Considering the land use cover characteristics as dynamic imp... Mostrar Tudo |
|
Palavras-Chave: |
Inteligência artificial; Modelo hidrológico. |
|
Thesagro: |
Bacia Hidrográfica; Cerrado; Hidrologia. |
|
Categoria do assunto: |
P Recursos Naturais, Ciências Ambientais e da Terra |
|
Marc: |
LEADER 02600naa a2200229 a 4500
001 2133627
005 2021-08-17
008 2021 bl uuuu u00u1 u #d
024 7 $ahttps://doi.org/10.1016/j.advwatres.2021.103965$2DOI
100 1 $aALTHOFF, D.
245 $aAddressing hydrological modeling in watersheds under land cover change with deep learning.$h[electronic resource]
260 $c2021
300 $a12 p.
520 $aThe impacts of land cover change have traditionally been assessed in hydrological modeling with a priori knowl- edge, e.g., using methods based on the curve number, or by calibrating hydrological models over different time periods. However, how hydrological processes respond to such changes is extremely context-dependent. Thus, there is an opportunity for the development of hydrological models that can learn from large hydrological data sets under the context of severe environmental changes. In this study, a single regional hydrological model is developed based on long short-term memory (LSTM) neural networks using different input configurations. One model considers only meteorological forcings as inputs (I1), another model considers meteorological forcings and static catchment attributes (I2), and a third model also considers meteorological forcings and catchment attributes but where the land cover characteristics are dynamic (I3). The models are trained using information from 411 catchments in the Brazilian Cerrado biome. The data set includes, for each catchment, the daily stream- flow observations (target), daily precipitation and reference evapotranspiration (meteorological forcings), and 21 catchment attributes including topography, climate indices, soil characteristics, and land cover characteristics. Considering catchment attributes increases the performance of the LSTM model (I2 and I3 median KGE : 0.69). Considering the land use cover characteristics as dynamic improves the predictions under low-flow conditions (I3 median rNSE : 0.62) when compared to the model considering such characteristics as static (I2 median rNSE : 0.53). This study also uses the deep network with the integrated gradients technique to explore the contribution of the catchment characteristics to streamflow and the number of time steps of influence for the deep network in different regions.
650 $aBacia Hidrográfica
650 $aCerrado
650 $aHidrologia
653 $aInteligência artificial
653 $aModelo hidrológico
700 1 $aRODRIGUES, L. N.
700 1 $aSILVA, D. D. da
773 $tAdvances in Water Resources$gv. 154, 2021.
Download
Esconder MarcMostrar Marc Completo |
|
Registro original: |
Embrapa Cerrados (CPAC) |
|
|
Biblioteca |
ID |
Origem |
Tipo/Formato |
Classificação |
Cutter |
Registro |
Volume |
Status |
Fechar
|
| Nenhum registro encontrado para a expressão de busca informada. |
|
|
