|
|
Registro Completo |
Biblioteca(s): |
Embrapa Agricultura Digital; Embrapa Cerrados; Embrapa Meio Ambiente. |
Data corrente: |
05/08/2022 |
Data da última atualização: |
05/08/2022 |
Tipo da produção científica: |
Artigo em Periódico Indexado |
Autoria: |
PARREIRAS, T. C.; BOLFE, E. L.; CHAVES, M. E. D.; DEL'ARCO SANCHES, I.; SANO, E. E.; VICTORIA, D. de C.; BETTIOL, G. M.; VICENTE, L. E. |
Afiliação: |
TAYA CRISTO PARREIRAS, IG/UNICAMP; EDSON LUIS BOLFE, CNPTIA, IG/UNICAMP; MICHEL EUSTÁQUIO DANTAS CHAVES, INPE; IARA DEL´ARCO SANCHES, INPE; EDSON EYJI SANO, CPAC; DANIEL DE CASTRO VICTORIA, CNPTIA; GIOVANA MARANHAO BETTIOL, CPAC; LUIZ EDUARDO VICENTE, CNPMA. |
Título: |
Hierarchical classification of soybean in the Brazilian Savanna based on Harmonized Landsat Sentinel data. |
Ano de publicação: |
2022 |
Fonte/Imprenta: |
Remote Sensing, v. 14, n. 15, 3736, Aug. 2022. |
DOI: |
https://doi.org/10.3390/rs14153736 |
Idioma: |
Inglês |
Conteúdo: |
Abstract. The Brazilian Savanna presents a complex agricultural dynamic and cloud cover issues; therefore, there is a need for new strategies for more detailed agricultural monitoring. Using a hierarchical classification system, we explored the Harmonized Landsat Sentinel-2 (HLS) dataset to detect soybean in western Bahia, Brazil. Multispectral bands (MS) and vegetation indices (VIs) from October 2021 to March 2022 were used as variables to feed Random Forest models, and the performances of the complete HLS time-series, HLSS30 (harmonized Sentinel), HLSL30 (harmonized Landsat), and Landsat 8 OLI (L8) were compared. At Level 1 (agricultural areas × native vegetation), HLS, HLSS30, and L8 produced identical models using MS + VIs, with 0.959 overall accuracies (OA) and Kappa of 0.917. At Level 2 (annual crops × perennial crops × pasturelands), HLS and L8 achieved an OA of 0.935 and Kappa > 0.89 using only VIs. At Level 3 (soybean × other annual crops), the HLS MS + VIs model achieved the best performance, with OA of 0.913 and Kappa of 0.808. Our results demonstrated the potential of the new HLS dataset for medium-resolution mapping initiatives at the crop level, which can impact decision-making processes involving large-scale soybean production and agricultural sustainability. |
Palavras-Chave: |
Agriculture monitoring; Harmonized Landsat Sentinel-2; HLS; Monitoramento agrícola; Multisensor. |
Thesagro: |
Cerrado; Glycine Max; Sensoriamento Remoto; Soja. |
Thesaurus Nal: |
Agriculture; Remote sensing; Soybeans. |
Categoria do assunto: |
-- X Pesquisa, Tecnologia e Engenharia |
URL: |
https://ainfo.cnptia.embrapa.br/digital/bitstream/doc/1145300/1/AP-Hierarchical-classification-soybean-2022.pdf
|
Marc: |
LEADER 02349naa a2200361 a 4500 001 2145300 005 2022-08-05 008 2022 bl uuuu u00u1 u #d 024 7 $ahttps://doi.org/10.3390/rs14153736$2DOI 100 1 $aPARREIRAS, T. C. 245 $aHierarchical classification of soybean in the Brazilian Savanna based on Harmonized Landsat Sentinel data.$h[electronic resource] 260 $c2022 520 $aAbstract. The Brazilian Savanna presents a complex agricultural dynamic and cloud cover issues; therefore, there is a need for new strategies for more detailed agricultural monitoring. Using a hierarchical classification system, we explored the Harmonized Landsat Sentinel-2 (HLS) dataset to detect soybean in western Bahia, Brazil. Multispectral bands (MS) and vegetation indices (VIs) from October 2021 to March 2022 were used as variables to feed Random Forest models, and the performances of the complete HLS time-series, HLSS30 (harmonized Sentinel), HLSL30 (harmonized Landsat), and Landsat 8 OLI (L8) were compared. At Level 1 (agricultural areas × native vegetation), HLS, HLSS30, and L8 produced identical models using MS + VIs, with 0.959 overall accuracies (OA) and Kappa of 0.917. At Level 2 (annual crops × perennial crops × pasturelands), HLS and L8 achieved an OA of 0.935 and Kappa > 0.89 using only VIs. At Level 3 (soybean × other annual crops), the HLS MS + VIs model achieved the best performance, with OA of 0.913 and Kappa of 0.808. Our results demonstrated the potential of the new HLS dataset for medium-resolution mapping initiatives at the crop level, which can impact decision-making processes involving large-scale soybean production and agricultural sustainability. 650 $aAgriculture 650 $aRemote sensing 650 $aSoybeans 650 $aCerrado 650 $aGlycine Max 650 $aSensoriamento Remoto 650 $aSoja 653 $aAgriculture monitoring 653 $aHarmonized Landsat Sentinel-2 653 $aHLS 653 $aMonitoramento agrícola 653 $aMultisensor 700 1 $aBOLFE, E. L. 700 1 $aCHAVES, M. E. D. 700 1 $aDEL'ARCO SANCHES, I. 700 1 $aSANO, E. E. 700 1 $aVICTORIA, D. de C. 700 1 $aBETTIOL, G. M. 700 1 $aVICENTE, L. E. 773 $tRemote Sensing$gv. 14, n. 15, 3736, Aug. 2022.
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. | | PARREIRAS, T. C.; BOLFE, E. L.; CHAVES, M. E. D.; DEL'ARCO SANCHES, I.; SANO, E. E.; VICTORIA, D. de C.; BETTIOL, G. M.; VICENTE, L. E. Hierarchical classification of soybean in the Brazilian Savanna based on Harmonized Landsat Sentinel data. Remote Sensing, v. 14, n. 15, 3736, Aug. 2022.Tipo: Artigo em Periódico Indexado | Circulação/Nível: A - 1 |
Biblioteca(s): Embrapa Agricultura Digital; Embrapa Cerrados; Embrapa Meio Ambiente. |
| |
Registros recuperados : 1 | |
|
Nenhum registro encontrado para a expressão de busca informada. |
|
|