| |
|
|
 | Acesso ao texto completo restrito à biblioteca da Embrapa Agricultura Digital. Para informações adicionais entre em contato com cnptia.biblioteca@embrapa.br. |
|
Registro Completo |
|
Biblioteca(s): |
Embrapa Agricultura Digital. |
|
Data corrente: |
22/06/2026 |
|
Data da última atualização: |
22/06/2026 |
|
Tipo da produção científica: |
Artigo em Periódico Indexado |
|
Autoria: |
BETTOLLI, M. L.; ROCHA, R. P. da; MILOVAC, J.; FERNANDEZ, J.; BALMACEDA-HUARTE, R.; BAÑO-MEDINA, J.; BLÁZQUEZ, J.; RODRIGUES, D. C.; CHOU, S. C.; COPPOLA, E.; SILVA, M. L. da; DOYLE, M.; LLORENTE, J. M. G.; OLMO, M.; PREIN, A. F.; RAFFAELE, F.; SOLMAN, S.; CUADRA, S. V. |
|
Afiliação: |
MARIA LAURA BETTOLLI, INSTITUTO FRANCO-ARGENTINO DE ESTUDIOS SOBRE EL CLIMA Y SUS IMPACTOS; R. P. DA ROCHA, UNIVERSIDADE DE SÃO PAULO; JOLIPA MILOVAC, CSIC-UNIVERSIDAD DE CANTABRIA; J. FERNANDEZ, CSIC-UNIVERSIDAD DE CANTABRIA; R. BALMACEDA-HUARTE, INSTITUTO FRANCO-ARGENTINO DE ESTUDIOS SOBRE EL CLIMA Y SUS IMPACTOS; J. BAÑO-MEDINA, CSIC-UNIVERSIDAD DE CANTABRIA, UNIVERSITY OF CALIFORNIA; J. BLÁZQUEZ, UNIVERSIDAD NACIONAL DE LA PLATA; D. CARNEIRO RODRIGUES, INSTITUTO NACIONAL DE PESQUISAS ESPACIAIS; S. C. CHOU, INSTITUTO NACIONAL DE PESQUISAS ESPACIAIS; E. COPPOLA, THE ABDUS SALAM INTERNATIONAL CENTRE FOR THEORETICAL PHYSICS; M. L. DA SILVA, THE ABDUS SALAM INTERNATIONAL CENTRE FOR THEORETICAL PHYSICS; M. DOYLE, INSTITUTO FRANCO-ARGENTINO DE ESTUDIOS SOBRE EL CLIMA Y SUS IMPACTOS; J. M. GUTIÉRREZ LLORENTE, CSIC-UNIVERSIDAD DE CANTABRIA; M. OLMO, BARCELONA SUPERCOMPUTING CENTER; A. F. PREIN, BARCELONA SUPERCOMPUTING CENTER, NSF NATIONAL CENTER FOR ATMOSPHERIC RESEARCH; F. RAFFAELE, ISTITUTO NAZIONALE DI OCEANOGRAFIA E DI GEOFISICA SPERIMENTALE; S. SOLMAN, INSTITUTO FRANCO-ARGENTINO DE ESTUDIOS SOBRE EL CLIMA Y SUS IMPACTOS; SANTIAGO VIANNA CUADRA, CNPTIA. |
|
Título: |
High-resolution deep-learning and dynamical climate downscaling for impact modeling in Southeast South America. |
|
Ano de publicação: |
2026 |
|
Fonte/Imprenta: |
Earth Systems and Environment, v. 10, n. 2, p. 1167-1189, Apr. 2026. |
|
ISSN: |
2509-9426 |
|
DOI: |
https://doi.org/10.1007/s41748-025-00661-8 |
|
Idioma: |
Inglês |
|
Conteúdo: |
This work introduces the experimental design and main results of a coordinated modeling study within the framework of a Flagship Pilot Study endorsed by the Coordinated Regional Climate Downscaling Experiment (CORDEX). The objective is to apply high-resolution climate downscaling for hydrological and agricultural modeling in Southeastern South America (SESA). To this end, targeted simulations using convection-permitting regional climate models (CPRCM at 4 km resolution) and deep learning-based empirical statistical downscaling were performed covering 3 consecutive years from June 2018 to May 2021. These simulations were used to drive the Variable Infiltration Capacity hydrologic model to simulate the streamflow of the Uruguay river and the Agricultural Crop Simulator to reproduce crop yields over Southern Brazil. An ensemble of six CPRCMs and a variety of statistical downscaling models based on convolutional neural networks (CNNs) contributed to this project. Overall, CPRCMs and CNNs show skill in reproducing daily precipitation over SESA, with different abilities in simulating the different aspects of precipitation extremes (dry and wet), although within the range of observational uncertainty. The intra-seasonal and inter-annual variability of extreme events and their frequency over the different sub-regions of SESA are very well captured by the simulations with most correlations between 0.63 and 0.88. This aspect also translates into the Uruguay River streamflow simulations (with time correlations above 0.42) whose response appears to be highly sensitive to precipitation intensity and location. The largest impacts on soybean yield simulation are related to low precipitation intensity and spatial variability, reaching to mean spatial biases up to -20%. MenosThis work introduces the experimental design and main results of a coordinated modeling study within the framework of a Flagship Pilot Study endorsed by the Coordinated Regional Climate Downscaling Experiment (CORDEX). The objective is to apply high-resolution climate downscaling for hydrological and agricultural modeling in Southeastern South America (SESA). To this end, targeted simulations using convection-permitting regional climate models (CPRCM at 4 km resolution) and deep learning-based empirical statistical downscaling were performed covering 3 consecutive years from June 2018 to May 2021. These simulations were used to drive the Variable Infiltration Capacity hydrologic model to simulate the streamflow of the Uruguay river and the Agricultural Crop Simulator to reproduce crop yields over Southern Brazil. An ensemble of six CPRCMs and a variety of statistical downscaling models based on convolutional neural networks (CNNs) contributed to this project. Overall, CPRCMs and CNNs show skill in reproducing daily precipitation over SESA, with different abilities in simulating the different aspects of precipitation extremes (dry and wet), although within the range of observational uncertainty. The intra-seasonal and inter-annual variability of extreme events and their frequency over the different sub-regions of SESA are very well captured by the simulations with most correlations between 0.63 and 0.88. This aspect also translates into the Uruguay River streamflow simulation... Mostrar Tudo |
|
Palavras-Chave: |
Agricultural modeling; Aprendizado profundo; Deep learning; Dynamical downscaling; Hydrological modeling; Modelagem agrícola; Modelagem hidrológica; Modelos climáticos; Precipitação; Precipitation extremes. |
|
Thesagro: |
Modelo de Simulação. |
|
Categoria do assunto: |
X Pesquisa, Tecnologia e Engenharia |
|
Marc: |
LEADER 03213naa a2200481 a 4500
001 2187730
005 2026-06-22
008 2026 bl uuuu u00u1 u #d
022 $a2509-9426
024 7 $ahttps://doi.org/10.1007/s41748-025-00661-8$2DOI
100 1 $aBETTOLLI, M. L.
245 $aHigh-resolution deep-learning and dynamical climate downscaling for impact modeling in Southeast South America.$h[electronic resource]
260 $c2026
520 $aThis work introduces the experimental design and main results of a coordinated modeling study within the framework of a Flagship Pilot Study endorsed by the Coordinated Regional Climate Downscaling Experiment (CORDEX). The objective is to apply high-resolution climate downscaling for hydrological and agricultural modeling in Southeastern South America (SESA). To this end, targeted simulations using convection-permitting regional climate models (CPRCM at 4 km resolution) and deep learning-based empirical statistical downscaling were performed covering 3 consecutive years from June 2018 to May 2021. These simulations were used to drive the Variable Infiltration Capacity hydrologic model to simulate the streamflow of the Uruguay river and the Agricultural Crop Simulator to reproduce crop yields over Southern Brazil. An ensemble of six CPRCMs and a variety of statistical downscaling models based on convolutional neural networks (CNNs) contributed to this project. Overall, CPRCMs and CNNs show skill in reproducing daily precipitation over SESA, with different abilities in simulating the different aspects of precipitation extremes (dry and wet), although within the range of observational uncertainty. The intra-seasonal and inter-annual variability of extreme events and their frequency over the different sub-regions of SESA are very well captured by the simulations with most correlations between 0.63 and 0.88. This aspect also translates into the Uruguay River streamflow simulations (with time correlations above 0.42) whose response appears to be highly sensitive to precipitation intensity and location. The largest impacts on soybean yield simulation are related to low precipitation intensity and spatial variability, reaching to mean spatial biases up to -20%.
650 $aModelo de Simulação
653 $aAgricultural modeling
653 $aAprendizado profundo
653 $aDeep learning
653 $aDynamical downscaling
653 $aHydrological modeling
653 $aModelagem agrícola
653 $aModelagem hidrológica
653 $aModelos climáticos
653 $aPrecipitação
653 $aPrecipitation extremes
700 1 $aROCHA, R. P. da
700 1 $aMILOVAC, J.
700 1 $aFERNANDEZ, J.
700 1 $aBALMACEDA-HUARTE, R.
700 1 $aBAÑO-MEDINA, J.
700 1 $aBLÁZQUEZ, J.
700 1 $aRODRIGUES, D. C.
700 1 $aCHOU, S. C.
700 1 $aCOPPOLA, E.
700 1 $aSILVA, M. L. da
700 1 $aDOYLE, M.
700 1 $aLLORENTE, J. M. G.
700 1 $aOLMO, M.
700 1 $aPREIN, A. F.
700 1 $aRAFFAELE, F.
700 1 $aSOLMAN, S.
700 1 $aCUADRA, S. V.
773 $tEarth Systems and Environment$gv. 10, n. 2, p. 1167-1189, Apr. 2026.
Download
Esconder MarcMostrar Marc Completo |
|
Registro original: |
Embrapa Agricultura Digital (CNPTIA) |
|
|
Biblioteca |
ID |
Origem |
Tipo/Formato |
Classificação |
Cutter |
Registro |
Volume |
Status |
URL |
Voltar
|
|
|
| Registros recuperados : 1 | |
| 1. |  | LUCHIARI JÚNIOR, A.; SHANAHAN, J.; SCHEPERS, J.; FRANCIS, D.; SCHLEMMER, M.; SCHEPERS, A.; INAMASO, R.; FRANCA, G.; MANTOVANI, E.; GOMIDE, R. Crop and soil based approaches for site specific nutrient management. In: CONGRESSO NACIONAL DE MILHO E SORGO, 24., 2002, Florianópolis, SC. Meio ambiente e a nova agenda para o agronegócio de milho e sorgo: [palestras]. Sete Lagoas: ABMS: Embrapa Milho e Sorgo; Florianópolis: Epagri, 2002.| Biblioteca(s): Embrapa Milho e Sorgo. |
|    |
| Registros recuperados : 1 | |
|
| Expressão de busca inválida. Verifique!!! |
|
|
