| |
|
|
 | Acesso ao texto completo restrito à biblioteca da Embrapa Meio Ambiente. Para informações adicionais entre em contato com cnpma.biblioteca@embrapa.br. |
|
Registro Completo |
|
Biblioteca(s): |
Embrapa Meio Ambiente. |
|
Data corrente: |
28/01/2025 |
|
Data da última atualização: |
28/01/2025 |
|
Tipo da produção científica: |
Artigo em Periódico Indexado |
|
Autoria: |
SANTOS, R. A. dos; MANTOVANI, E. C.; BUFON, V. B.; FERNANDES-FILHO, E. F. |
|
Afiliação: |
ROBSON ARGOLO DOS SANTOS, UNIVERSIDADE FEDERAL DE VIÇOSA; EVERARDO CHARTUNI MANTOVANI, UNIVERSIDADE FEDERAL DE VIÇOSA; VINICIUS BOF BUFON, CNPMA; ELPÍDIO INÁCIO FERNANDES FILHO, UNIVERSIDADE FEDERAL DE VIÇOSA. |
|
Título: |
Improving actual evapotranspiration estimates through an integrated remote sensing and cutting-edge machine learning approach. |
|
Ano de publicação: |
2024 |
|
Fonte/Imprenta: |
Computers and Electronics in Agriculture, v. 225, article 109258, 2024. |
|
ISSN: |
0168-1699 |
|
DOI: |
https://doi.org/10.1016/j.compag.2024.109258 |
|
Idioma: |
Inglês |
|
Conteúdo: |
Abstract: Recent technological advances have allowed the production of many studies on evapotranspiration, resulting in improvements in reference evapotranspiration estimates and crop coefficients with remote sensing data. However, these two areas of research often work independently, producing valuable studies, but without an effective integration to predict actual evapotranspiration directly, without the need for weather stations. Thus, this study aimed to model actual evapotranspiration in sugarcane crop using machine learning techniques, independently of weather stations and thermal sensor data. To achieve this goal, data from the OLI (Operational Land Imager) and TIRS (Thermal Infrared Sensor) sensors aboard the Landsat-8 and 9 satellites were used to produce the variable observed from the METRIC model, and data from the Sentinel-2A and 2B satellites, NASA POWER, WorldClim and astronomical variables, latitude, elevation, day of the year and month were used to generate the explanatory variables and feed 13 machine learning models for three different biomes: Atlantic Forest, Caatinga and Cerrado. The results indicated that the brnn (Bayesian regularized neural networks) model with R2 and RMSE of 0.73 and 1.10, respectively, and the XgbLinear (extreme gradient boosting – linear method) model, which obtained values of 0.74 and 1.25 for these metrics, in that order, showed the best overall performance. Specific analyses indicated that brnn was superior for cultivated areas in the Atlantic Forest and Caatinga biomes, while XgbLinear was superior in the Cerrado biome. These results show that machine learning algorithms are able to predict actual evapotranspiration without the need for using weather stations and thermal data. MenosAbstract: Recent technological advances have allowed the production of many studies on evapotranspiration, resulting in improvements in reference evapotranspiration estimates and crop coefficients with remote sensing data. However, these two areas of research often work independently, producing valuable studies, but without an effective integration to predict actual evapotranspiration directly, without the need for weather stations. Thus, this study aimed to model actual evapotranspiration in sugarcane crop using machine learning techniques, independently of weather stations and thermal sensor data. To achieve this goal, data from the OLI (Operational Land Imager) and TIRS (Thermal Infrared Sensor) sensors aboard the Landsat-8 and 9 satellites were used to produce the variable observed from the METRIC model, and data from the Sentinel-2A and 2B satellites, NASA POWER, WorldClim and astronomical variables, latitude, elevation, day of the year and month were used to generate the explanatory variables and feed 13 machine learning models for three different biomes: Atlantic Forest, Caatinga and Cerrado. The results indicated that the brnn (Bayesian regularized neural networks) model with R2 and RMSE of 0.73 and 1.10, respectively, and the XgbLinear (extreme gradient boosting – linear method) model, which obtained values of 0.74 and 1.25 for these metrics, in that order, showed the best overall performance. Specific analyses indicated that brnn was superior for cultivated areas i... Mostrar Tudo |
|
Thesagro: |
Cana de Açúcar; Evapotranspiração; Irrigação; Sensoriamento Remoto. |
|
Thesaurus Nal: |
Artificial intelligence; Environmental sustainability; Evapotranspiration; Prediction; Remote sensing; Sugarcane. |
|
Categoria do assunto: |
X Pesquisa, Tecnologia e Engenharia |
|
Marc: |
LEADER 02733naa a2200301 a 4500
001 2172026
005 2025-01-28
008 2024 bl uuuu u00u1 u #d
022 $a0168-1699
024 7 $ahttps://doi.org/10.1016/j.compag.2024.109258$2DOI
100 1 $aSANTOS, R. A. dos
245 $aImproving actual evapotranspiration estimates through an integrated remote sensing and cutting-edge machine learning approach.$h[electronic resource]
260 $c2024
520 $aAbstract: Recent technological advances have allowed the production of many studies on evapotranspiration, resulting in improvements in reference evapotranspiration estimates and crop coefficients with remote sensing data. However, these two areas of research often work independently, producing valuable studies, but without an effective integration to predict actual evapotranspiration directly, without the need for weather stations. Thus, this study aimed to model actual evapotranspiration in sugarcane crop using machine learning techniques, independently of weather stations and thermal sensor data. To achieve this goal, data from the OLI (Operational Land Imager) and TIRS (Thermal Infrared Sensor) sensors aboard the Landsat-8 and 9 satellites were used to produce the variable observed from the METRIC model, and data from the Sentinel-2A and 2B satellites, NASA POWER, WorldClim and astronomical variables, latitude, elevation, day of the year and month were used to generate the explanatory variables and feed 13 machine learning models for three different biomes: Atlantic Forest, Caatinga and Cerrado. The results indicated that the brnn (Bayesian regularized neural networks) model with R2 and RMSE of 0.73 and 1.10, respectively, and the XgbLinear (extreme gradient boosting – linear method) model, which obtained values of 0.74 and 1.25 for these metrics, in that order, showed the best overall performance. Specific analyses indicated that brnn was superior for cultivated areas in the Atlantic Forest and Caatinga biomes, while XgbLinear was superior in the Cerrado biome. These results show that machine learning algorithms are able to predict actual evapotranspiration without the need for using weather stations and thermal data.
650 $aArtificial intelligence
650 $aEnvironmental sustainability
650 $aEvapotranspiration
650 $aPrediction
650 $aRemote sensing
650 $aSugarcane
650 $aCana de Açúcar
650 $aEvapotranspiração
650 $aIrrigação
650 $aSensoriamento Remoto
700 1 $aMANTOVANI, E. C.
700 1 $aBUFON, V. B.
700 1 $aFERNANDES-FILHO, E. F.
773 $tComputers and Electronics in Agriculture$gv. 225, article 109258, 2024.
Download
Esconder MarcMostrar Marc Completo |
|
Registro original: |
Embrapa Meio Ambiente (CNPMA) |
|
|
Biblioteca |
ID |
Origem |
Tipo/Formato |
Classificação |
Cutter |
Registro |
Volume |
Status |
URL |
Voltar
|
|
|
| Registros recuperados : 5 | |
| 1. |  | MELO, P. S. L.; WARTHA, E. R. S. de A.; MARINS, M. L. da C. L.; LIMA, P. B. N.; SILVA, D. G. da; CARVALHO, J. L. V. de. Caracterização química de batata-doce biofortificada (Ipomea batatas L.) in natura e cozida. In: CONGRESSO BRASILEIRO DE CIÊNCIA E TECNOLOGIA DE ALIMENTOS, 24.; CONGRESSO DO INSTITUTO NACIONAL DE CIÊNCIA E TECNOLOGIA DE FRUTOS TROPICAIS, 4., 2014, Aracaju. Inovação e sustentabilidade em ciência e tecnologia de alimentos: resumos. [Campinas]: SBCTA, 2014. p. 17| Tipo: Resumo em Anais de Congresso |
| Biblioteca(s): Embrapa Agroindústria de Alimentos. |
|    |
| 2. | | LIMA, P. N. B.; WARTHA, E. R. S. de A.; MARINS, M. L. da C. L.; MELO, P. S. L.; MENDES NETTO, R. S.; CARVALHO, J. L. V. de. Composição centesimal e conteúdo de minerais de macaxeira (Manihot esculenta Crantz) biofortificada. In: CONGRESSO BRASILEIRO DE CIÊNCIA E TECNOLOGIA DE ALIMENTOS, 24.; CONGRESSO DO INSTITUTO NACIONAL DE CIÊNCIA E TECNOLOGIA DE FRUTOS TROPICAIS, 4., 2014, Aracaju. Inovação e sustentabilidade em ciência e tecnologia de alimentos: resumos. [Campinas]: SBCTA, 2014.| Tipo: Resumo em Anais de Congresso |
| Biblioteca(s): Embrapa Agroindústria de Alimentos. |
| |
| 3. | | WARTHA, E. R. S. de A.; MARTINS, M. L.; LIMA, P. N. B.; MELO, P. S. L.; COSTA, D.; CARVALHO, J. L. V. de; NUNES, M. U. C.; CARVALHO, H. W. L. de; SILVA, D. G. da; MENDES NETTO, R. S. Características química, tecnológica, nutricional e sensorial de batata-doce biofortificada. In: REUNIÃO DE BIOFORTIFICAÇÃO NO BRASIL, 5., 2015, São Paulo. Anais... Brasília, DF : Embrapa, 2015. p. 117-120.| Tipo: Artigo em Anais de Congresso |
| Biblioteca(s): Embrapa Tabuleiros Costeiros. |
| |
| 4. | | WARTHA, E. R. S. DE A.; MARINS, M. L.; LIMA, P. N. B.; MELI, P. S. L.; COSTA, D. DA; CARVALHO, J. L. V. de; NUNES, M. U. C.; CARVALHO, H. W. L. de; SILVA, D. G. DA; MENDES NETTO, R. S. Características química, tecnológica, nutricional e sensorial de mandioca biofortificada. In: REUNIÃO DE BIOFORTIFICAÇÃO NO BRASIL, 5., 2015, São Paulo. Anais... Brasília, DF : Embrapa, 2015. T309. p. 121-124| Tipo: Artigo em Anais de Congresso |
| Biblioteca(s): Embrapa Agroindústria de Alimentos. |
| |
| 5. | | WARTHA, E. R. S. de a.; MARTINS, M. L.; LIMA, P. N. B.; MELO, P. S. L.; COSTA, D. da; CARVALHO, J. L. V. de; NUNES, M. U. C.; CARVALHO, H. W. L. de; SILVA, D. G. da; MENDES NETTO, R. S. Características química, tecnológica, nutricional e sensorial de mandioca biofortificada. In: REUNIÃO DE BIOFORTIFICAÇÃO NO BRASIL, 5., 2015, São Paulo. Anais... Brasília, DF : Embrapa, 2015. p. 121-124| Tipo: Artigo em Anais de Congresso |
| Biblioteca(s): Embrapa Tabuleiros Costeiros. |
| |
| Registros recuperados : 5 | |
|
| Expressão de busca inválida. Verifique!!! |
|
|
