| |
|
|
 | Acesso ao texto completo restrito à biblioteca da Embrapa Solos. Para informações adicionais entre em contato com cnps.biblioteca@embrapa.br. |
|
Registro Completo |
|
Biblioteca(s): |
Embrapa Pesca e Aquicultura; Embrapa Solos. |
|
Data corrente: |
21/03/2018 |
|
Data da última atualização: |
03/06/2019 |
|
Tipo da produção científica: |
Artigo em Periódico Indexado |
|
Autoria: |
BELLÓN, B.; BÉGUÉ, A.; LO SEEN, D.; LEBOURGEOIS, V.; EVANGELISTA, B. A.; SIMÕES, M.; FERRAZ, R. P. D. |
|
Afiliação: |
BEATRIZ BELLÓN, CIRAD; AGNES BEGUE, CIRAD; DANNY LO SEEN, CIRAD; VALENTINE LEBOURGEOIS, CIRAD; BALBINO ANTONIO EVANGELISTA, CNPASA; MARGARETH GONCALVES SIMOES, CNPS; RODRIGO PEÇANHA DEMONTE FERRAZ, UERJ. |
|
Título: |
Improved regional-scale Brazilian cropping systems' mapping based on a semi-automatic object-based clustering approach. |
|
Ano de publicação: |
2018 |
|
Fonte/Imprenta: |
International Journal of Applied Earth Observation and Geoinformation, V. 68, p. 127-138, Jun. 2018. |
|
ISSN: |
0303-2434 |
|
DOI: |
10.1016/j.jag.2018.01.019 |
|
Idioma: |
Inglês |
|
Conteúdo: |
Cropping systems' maps at fine scale over large areas provide key information for further agricultural production and environmental impact assessments, and thus represent a valuable tool for effective land-use planning. There is, therefore, a growing interest in mapping cropping systems in an operational manner over large areas, and remote sensing approaches based on vegetation index time series analysis have proven to be an efficient tool. However, supervised pixel-based approaches are commonly adopted, requiring resource consuming field campaigns to gather training data. In this paper, we present a new object-based unsupervised classification approach tested on an annual MODIS 16-day composite Normalized Difference Vegetation Index time series and a Landsat 8 mosaic of the State of Tocantins, Brazil, for the 2014-2015 growing season. Two variants of the approach are compared: an hyperclustering approach, and a landscape-clustering approach involving a previous stratification of the study area into landscape units on which the clustering is then performed. The main cropping systems of Tocantins, characterized by the crop types and cropping patterns, were efficiently mapped with the landscape clustering approach. Results show that stratification prior to clustering significantly improves the classification accuracies for underrepresented and sparsely distributed cropping systems. This study illustrates the potential of unsupervised classification for large area cropping systems' mapping and contributes to the development of generic tools for supporting large-scale agricultural monitoring across regions. MenosCropping systems' maps at fine scale over large areas provide key information for further agricultural production and environmental impact assessments, and thus represent a valuable tool for effective land-use planning. There is, therefore, a growing interest in mapping cropping systems in an operational manner over large areas, and remote sensing approaches based on vegetation index time series analysis have proven to be an efficient tool. However, supervised pixel-based approaches are commonly adopted, requiring resource consuming field campaigns to gather training data. In this paper, we present a new object-based unsupervised classification approach tested on an annual MODIS 16-day composite Normalized Difference Vegetation Index time series and a Landsat 8 mosaic of the State of Tocantins, Brazil, for the 2014-2015 growing season. Two variants of the approach are compared: an hyperclustering approach, and a landscape-clustering approach involving a previous stratification of the study area into landscape units on which the clustering is then performed. The main cropping systems of Tocantins, characterized by the crop types and cropping patterns, were efficiently mapped with the landscape clustering approach. Results show that stratification prior to clustering significantly improves the classification accuracies for underrepresented and sparsely distributed cropping systems. This study illustrates the potential of unsupervised classification for large area cropping syst... Mostrar Tudo |
|
Palavras-Chave: |
Geographic object-based image analysis. |
|
Thesagro: |
Mapa; Sensoriamento remoto; Sistema de cultivo. |
|
Thesaurus Nal: |
Cluster analysis; Cropping systems; Landsat; Moderate resolution imaging spectroradiometer; Spectroradiometers. |
|
Categoria do assunto: |
P Recursos Naturais, Ciências Ambientais e da Terra |
|
Marc: |
LEADER 02686naa a2200325 a 4500
001 2089570
005 2019-06-03
008 2018 bl uuuu u00u1 u #d
022 $a0303-2434
024 7 $a10.1016/j.jag.2018.01.019$2DOI
100 1 $aBELLÓN, B.
245 $aImproved regional-scale Brazilian cropping systems' mapping based on a semi-automatic object-based clustering approach.$h[electronic resource]
260 $c2018
520 $aCropping systems' maps at fine scale over large areas provide key information for further agricultural production and environmental impact assessments, and thus represent a valuable tool for effective land-use planning. There is, therefore, a growing interest in mapping cropping systems in an operational manner over large areas, and remote sensing approaches based on vegetation index time series analysis have proven to be an efficient tool. However, supervised pixel-based approaches are commonly adopted, requiring resource consuming field campaigns to gather training data. In this paper, we present a new object-based unsupervised classification approach tested on an annual MODIS 16-day composite Normalized Difference Vegetation Index time series and a Landsat 8 mosaic of the State of Tocantins, Brazil, for the 2014-2015 growing season. Two variants of the approach are compared: an hyperclustering approach, and a landscape-clustering approach involving a previous stratification of the study area into landscape units on which the clustering is then performed. The main cropping systems of Tocantins, characterized by the crop types and cropping patterns, were efficiently mapped with the landscape clustering approach. Results show that stratification prior to clustering significantly improves the classification accuracies for underrepresented and sparsely distributed cropping systems. This study illustrates the potential of unsupervised classification for large area cropping systems' mapping and contributes to the development of generic tools for supporting large-scale agricultural monitoring across regions.
650 $aCluster analysis
650 $aCropping systems
650 $aLandsat
650 $aModerate resolution imaging spectroradiometer
650 $aSpectroradiometers
650 $aMapa
650 $aSensoriamento remoto
650 $aSistema de cultivo
653 $aGeographic object-based image analysis
700 1 $aBÉGUÉ, A.
700 1 $aLO SEEN, D.
700 1 $aLEBOURGEOIS, V.
700 1 $aEVANGELISTA, B. A.
700 1 $aSIMÕES, M.
700 1 $aFERRAZ, R. P. D.
773 $tInternational Journal of Applied Earth Observation and Geoinformation, V. 68, p. 127-138, Jun. 2018.
Download
Esconder MarcMostrar Marc Completo |
|
Registro original: |
Embrapa Pesca e Aquicultura (CNPASA) |
|
|
Biblioteca |
ID |
Origem |
Tipo/Formato |
Classificação |
Cutter |
Registro |
Volume |
Status |
URL |
Voltar
|
|
|
| Registros recuperados : 1 | |
| 1. |  | VASQUEZ, D. D. N.; PINHEIRO, D. H.; TEIXEIRA, L. A.; MOREIRA-PINTO, C. E.; MACEDO, L. L. P. de; SALLES-FILHO, A. L. O.; SILVA, M. C. M. da; LOURENCO, I. T.; MORGANTE, C. V.; SILVA, L. P. da; SA, M. F. G. de. Simultaneous silencing of juvenile hormone metabolism genes through RNAi interrupts metamorphosis in the cotton boll weevil. Frontiers in Molecular Biosciences, v. 10, 2023. Na publicação: Leonardo L. P. Macedo; Maria C. M. Silva; Isabela T. Lourenço-Tessutti; Luciano P. Silva; Maria F. Grossi-de-Sa.| Tipo: Artigo em Periódico Indexado | Circulação/Nível: A - 2 |
| Biblioteca(s): Embrapa Recursos Genéticos e Biotecnologia; Embrapa Semiárido. |
|    |
| Registros recuperados : 1 | |
|
| Nenhum registro encontrado para a expressão de busca informada. |
|
|
