| |
|
|
 | Acesso ao texto completo restrito à biblioteca da Embrapa Gado de Corte. Para informações adicionais entre em contato com cnpgc.biblioteca@embrapa.br. |
|
Registro Completo |
|
Biblioteca(s): |
Embrapa Gado de Corte. |
|
Data corrente: |
12/12/2023 |
|
Data da última atualização: |
12/12/2023 |
|
Tipo da produção científica: |
Artigo em Periódico Indexado |
|
Autoria: |
BRETAS, I. L.; VALENTE, D. S. M.; OLIVEIRA, T. F. DE; MONTAGNER, D. B.; EUCLIDES, V. P. B.; CHIZZOTTI, F. H. M. |
|
Afiliação: |
IGOR LIMA BRETAS, UNIVERSIDADE FEDERAL DE VIÇOSA; DOMINGOS SARVIO MAGALHÃES VALENTE, UNIVERSIDADE FEDERAL DE VIÇOSA; THIAGO FURTADO DE OLIVEIRA, UNIVERSIDADE FEDERAL DE VIÇOSA; DENISE BAPTAGLIN MONTAGNER, CNPGC; VALERIA PACHECO BATISTA EUCLIDES, CNPGC; FERNANDA HELENA MARTINS CHIZZOTTI, UNIVERSIDADE FEDERAL DE VIÇOSA. |
|
Título: |
Canopy height and biomass prediction in Mombaça guinea grass pastures using satellite imagery and machine learning. |
|
Ano de publicação: |
2023 |
|
Fonte/Imprenta: |
Precision Agriculture, v. 24, n. 4, p. 1638–1662, 2023. |
|
DOI: |
https://doi.org/10.1007/s11119-023-10013-z |
|
Idioma: |
Inglês |
|
Notas: |
Published online: 17 April 2023. |
|
Conteúdo: |
ABSTRACT - Remote sensing can serve as a promising solution for monitoring spatio-temporal variability in grasslands, providing timely information about diferent biophysical parameters. We aimed to develop models for canopy height classifcation and aboveground biomass estimation in pastures of Megathyrsus maximus cv. Mombaça using machine learning techniques and images obtained from the Sentinel-2 satellite. We used diferent spectral bands from the Sentinel-2, which were obtained and processed entirely in the cloud computing space. Three canopy height classes were defned according to grazing management recommendations: Class 0 (<0.45 m), Class 1 (0.45–0.80 m) and Class 2 (>0.80 m). For modeling, the original database was divided into training data (85%) and test data (15%). To avoid dependency between our training and test datasets and ensure greater generalization capacity, we used a spatial grouping evaluation structure. The random forest algorithm was used to predict canopy height and aboveground biomass by using height and biomass feld reference data obtained from 54 paddocks in Brazil between 2016 and 2018. Our results demonstrated precision, recall, and accuracy values of up to 73%, 73%, and 72%, respectively, for canopy height classifcation. In addition, the models showed reasonable predictive performance for aboveground fresh biomass (AFB) and dry matter concentration (DMC; R2=0.61 and 0.69, respectively). We conclude that the combined use of satellite imagery and machine learning techniques has potential to predict canopy height and aboveground biomass of Megathyrsus maximus cv. Mombaça. However, further studies should be conducted to improve the proposed models and develop software to implement the tool under feld conditions. MenosABSTRACT - Remote sensing can serve as a promising solution for monitoring spatio-temporal variability in grasslands, providing timely information about diferent biophysical parameters. We aimed to develop models for canopy height classifcation and aboveground biomass estimation in pastures of Megathyrsus maximus cv. Mombaça using machine learning techniques and images obtained from the Sentinel-2 satellite. We used diferent spectral bands from the Sentinel-2, which were obtained and processed entirely in the cloud computing space. Three canopy height classes were defned according to grazing management recommendations: Class 0 (<0.45 m), Class 1 (0.45–0.80 m) and Class 2 (>0.80 m). For modeling, the original database was divided into training data (85%) and test data (15%). To avoid dependency between our training and test datasets and ensure greater generalization capacity, we used a spatial grouping evaluation structure. The random forest algorithm was used to predict canopy height and aboveground biomass by using height and biomass feld reference data obtained from 54 paddocks in Brazil between 2016 and 2018. Our results demonstrated precision, recall, and accuracy values of up to 73%, 73%, and 72%, respectively, for canopy height classifcation. In addition, the models showed reasonable predictive performance for aboveground fresh biomass (AFB) and dry matter concentration (DMC; R2=0.61 and 0.69, respectively). We conclude that the combined use of satellite imagery and ma... Mostrar Tudo |
|
Palavras-Chave: |
Pecuária de precisão. |
|
Thesagro: |
Biomassa; Pastagem; Sensoriamento Remoto; Tecnologia. |
|
Thesaurus Nal: |
Biomass; Pasture management; Remote sensing; Tropical grasslands. |
|
Categoria do assunto: |
-- |
|
Marc: |
LEADER 02758naa a2200313 a 4500
001 2159571
005 2023-12-12
008 2023 bl uuuu u00u1 u #d
024 7 $ahttps://doi.org/10.1007/s11119-023-10013-z$2DOI
100 1 $aBRETAS, I. L.
245 $aCanopy height and biomass prediction in Mombaça guinea grass pastures using satellite imagery and machine learning.$h[electronic resource]
260 $c2023
500 $aPublished online: 17 April 2023.
520 $aABSTRACT - Remote sensing can serve as a promising solution for monitoring spatio-temporal variability in grasslands, providing timely information about diferent biophysical parameters. We aimed to develop models for canopy height classifcation and aboveground biomass estimation in pastures of Megathyrsus maximus cv. Mombaça using machine learning techniques and images obtained from the Sentinel-2 satellite. We used diferent spectral bands from the Sentinel-2, which were obtained and processed entirely in the cloud computing space. Three canopy height classes were defned according to grazing management recommendations: Class 0 (<0.45 m), Class 1 (0.45–0.80 m) and Class 2 (>0.80 m). For modeling, the original database was divided into training data (85%) and test data (15%). To avoid dependency between our training and test datasets and ensure greater generalization capacity, we used a spatial grouping evaluation structure. The random forest algorithm was used to predict canopy height and aboveground biomass by using height and biomass feld reference data obtained from 54 paddocks in Brazil between 2016 and 2018. Our results demonstrated precision, recall, and accuracy values of up to 73%, 73%, and 72%, respectively, for canopy height classifcation. In addition, the models showed reasonable predictive performance for aboveground fresh biomass (AFB) and dry matter concentration (DMC; R2=0.61 and 0.69, respectively). We conclude that the combined use of satellite imagery and machine learning techniques has potential to predict canopy height and aboveground biomass of Megathyrsus maximus cv. Mombaça. However, further studies should be conducted to improve the proposed models and develop software to implement the tool under feld conditions.
650 $aBiomass
650 $aPasture management
650 $aRemote sensing
650 $aTropical grasslands
650 $aBiomassa
650 $aPastagem
650 $aSensoriamento Remoto
650 $aTecnologia
653 $aPecuária de precisão
700 1 $aVALENTE, D. S. M.
700 1 $aOLIVEIRA, T. F. DE
700 1 $aMONTAGNER, D. B.
700 1 $aEUCLIDES, V. P. B.
700 1 $aCHIZZOTTI, F. H. M.
773 $tPrecision Agriculture$gv. 24, n. 4, p. 1638–1662, 2023.
Download
Esconder MarcMostrar Marc Completo |
|
Registro original: |
Embrapa Gado de Corte (CNPGC) |
|
|
Biblioteca |
ID |
Origem |
Tipo/Formato |
Classificação |
Cutter |
Registro |
Volume |
Status |
URL |
Voltar
|
|
|
| Registros recuperados : 1 | |
| Registros recuperados : 1 | |
|
| Expressão de busca inválida. Verifique!!! |
|
|
