|
|
| 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 Solos. |
Data corrente: |
12/01/2009 |
Data da última atualização: |
01/09/2020 |
Tipo da produção científica: |
Artigo em Anais de Congresso |
Autoria: |
ARVOR, D.; JONATHAN, M.; MEIRELLES, M. S. P.; DUBREUIL, V.; LECERF, R. |
Afiliação: |
Damien Arvor, Université Rennes; Milton Jonathan, Embrapa Solos; MARGARETH GONCALVES SIMOES, CNPS; Vincent Dubreuil, Université Rennes; Rémi Lecerf, Université Rennes. |
Título: |
Comparison of multitemporal MODIS-EVI smoothing algorithms and its contribution to crop monitoring. |
Ano de publicação: |
2008 |
Fonte/Imprenta: |
In: IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, 2008, Boston. Proceedings... Danvers, MA: IEEE, 2008. v. 2, p. 958-961. |
DOI: |
https://doi.org/10.1109/IGARSS.2008.4779155 |
Idioma: |
Inglês |
Conteúdo: |
Crop monitoring and more generally land use change detection are of primary importance in order to analyze spatio-temporal dynamics and its impacts on environment. This aspect is especially true in such a region as the State of Mato Grosso (south of the Brazilian Amazon Basin) which hosts an intensive pioneer front. Deforestation in this region as often been explained by soybean expansion in the last three decades. Remote sensing techniques may now represent an efficient and objective manner to quantify how crops expansion really represents a factor of deforestation through crop mapping studies. Due to the special characteristics of the soybean productions' farms in Mato Grosso (area varying between 1000 hectares and 40000 hectares and individual fields often bigger than 100 hectares), the Moderate Resolution Imaging Spectroradiometer (MODIS) data with a near daily temporal resolution and 250 m spatial resolution can be considered as adequate resources to crop mapping. Especially, multitemporal vegetation indices (VI) studies have been currently used to realize this task [1] [2]. In this study, 16-days compositions of EVI (MODQ13 product) data are used. However, although these data are already processed, multitemporal VI profiles still remain noisy due to cloudiness (which is extremely frequent in a tropical region such as south Amazon Basin), sensor problems, errors in atmospheric corrections or BRDF effect. Thus, many works tried to develop algorithms that could smooth the multitemporal VI profiles in order to improve further classification. The goal of this study is to compare and test different smoothing algorithms in order to select the one which satisfies better to the demand which is classifying crop classes. Those classes correspond to 6 different agricultural managements observed in Mato Grosso through an intensive field work which resulted in mapping more than 1000 individual fields. The agricultural managements above mentioned are based on combination of soy, cotton, corn, millet and sorghum crops sowed in single or double crop systems. Due to the difficulty in separating certain classes because of too similar agricultural calendars, the classification will be reduced to 3 classes : Cotton (single crop), Soy and cotton (double crop), soy (single or double crop with corn, millet or sorghum). The classification will use training data obtained in the 2005-2006 harvest and then be tested on the 2006-2007 harvest. In a first step, four smoothing techniques are presented and criticized. Those techniques are Best Index Slope Extraction (BISE) [3], Mean Value Iteration (MVI) [4], Weighted Least Squares (WLS) [5] and Savitzky-Golay Filter (SG) [6] [7]. These techniques are then implemented and visually compared on a few individual pixels so that it allows doing a first selection between the five studied techniques. The WLS and SG techniques are selected according to criteria proposed by [8]. Those criteria are: ability in eliminating frequent noises, conserving the upper values of the VI profiles and keeping the temporality of the profiles. Those selected algorithms are then programmed and applied to the MODIS/TERRA EVI data (16-days composition periods). Tests of separability are realized based on the Jeffries-Matusita distance in order to see if the algorithms managed in improving the potential of differentiation between the classes. Those tests are realized on the overall profile (comprising 23 MODIS images) as well as on each MODIS sub-period of the profile [1]. This last test is a double interest process because it allows comparing the smoothing techniques and also enables to select a set of images which carries more information on the separability between the classes. Those selected dates can then be used to realize a supervised classification. Here three different classifiers are tested to evaluate if the smoothing techniques as a particular effect on the classification depending on the classifiers used. Those classifiers are Maximum Likelihood classifier, Spectral Angle Mapper (SAM) classifier and CHAID Improved Decision tree. It appears through the separability tests on the overall process that the smoothed profiles don't improve efficiently the potential of discrimination between classes when compared with the original data. However, the same tests realized on the MODIS sub-periods show better results obtained with the smoothed algorithms. The results of the classification confirm this first analyze. The Kappa coefficients are always better with the smoothing techniques and the results obtained with the WLS and SG smoothed profiles are nearly equal. However, the results are different depending on the classifier used. The impact of the smoothing algorithms is much better while using the decision tree model. Indeed, it allows a gain of 0.1 in the Kappa coefficient. While using the Maximum Likelihood end SAM models, the gain remains positive but is much lower (Kappa improved of 0.02 only). Thus, this work's aim is to prove the utility in smoothing the VI profiles in order to improve the final results. However, the choice of the smoothing algorithm has to be made considering the original data used and the classifier models used. In that case the Savitzky-Golay filter gave the better results. MenosCrop monitoring and more generally land use change detection are of primary importance in order to analyze spatio-temporal dynamics and its impacts on environment. This aspect is especially true in such a region as the State of Mato Grosso (south of the Brazilian Amazon Basin) which hosts an intensive pioneer front. Deforestation in this region as often been explained by soybean expansion in the last three decades. Remote sensing techniques may now represent an efficient and objective manner to quantify how crops expansion really represents a factor of deforestation through crop mapping studies. Due to the special characteristics of the soybean productions' farms in Mato Grosso (area varying between 1000 hectares and 40000 hectares and individual fields often bigger than 100 hectares), the Moderate Resolution Imaging Spectroradiometer (MODIS) data with a near daily temporal resolution and 250 m spatial resolution can be considered as adequate resources to crop mapping. Especially, multitemporal vegetation indices (VI) studies have been currently used to realize this task [1] [2]. In this study, 16-days compositions of EVI (MODQ13 product) data are used. However, although these data are already processed, multitemporal VI profiles still remain noisy due to cloudiness (which is extremely frequent in a tropical region such as south Amazon Basin), sensor problems, errors in atmospheric corrections or BRDF effect. Thus, many works tried to develop algorithms that could smooth the... Mostrar Tudo |
Palavras-Chave: |
Algoritmo; Classes de culturas. |
Categoria do assunto: |
P Recursos Naturais, Ciências Ambientais e da Terra |
Marc: |
LEADER 06008nam a2200193 a 4500 001 1334899 005 2020-09-01 008 2008 bl uuuu u00u1 u #d 024 7 $ahttps://doi.org/10.1109/IGARSS.2008.4779155$2DOI 100 1 $aARVOR, D. 245 $aComparison of multitemporal MODIS-EVI smoothing algorithms and its contribution to crop monitoring.$h[electronic resource] 260 $aIn: IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, 2008, Boston. Proceedings... Danvers, MA: IEEE, 2008. v. 2, p. 958-961.$c2008 520 $aCrop monitoring and more generally land use change detection are of primary importance in order to analyze spatio-temporal dynamics and its impacts on environment. This aspect is especially true in such a region as the State of Mato Grosso (south of the Brazilian Amazon Basin) which hosts an intensive pioneer front. Deforestation in this region as often been explained by soybean expansion in the last three decades. Remote sensing techniques may now represent an efficient and objective manner to quantify how crops expansion really represents a factor of deforestation through crop mapping studies. Due to the special characteristics of the soybean productions' farms in Mato Grosso (area varying between 1000 hectares and 40000 hectares and individual fields often bigger than 100 hectares), the Moderate Resolution Imaging Spectroradiometer (MODIS) data with a near daily temporal resolution and 250 m spatial resolution can be considered as adequate resources to crop mapping. Especially, multitemporal vegetation indices (VI) studies have been currently used to realize this task [1] [2]. In this study, 16-days compositions of EVI (MODQ13 product) data are used. However, although these data are already processed, multitemporal VI profiles still remain noisy due to cloudiness (which is extremely frequent in a tropical region such as south Amazon Basin), sensor problems, errors in atmospheric corrections or BRDF effect. Thus, many works tried to develop algorithms that could smooth the multitemporal VI profiles in order to improve further classification. The goal of this study is to compare and test different smoothing algorithms in order to select the one which satisfies better to the demand which is classifying crop classes. Those classes correspond to 6 different agricultural managements observed in Mato Grosso through an intensive field work which resulted in mapping more than 1000 individual fields. The agricultural managements above mentioned are based on combination of soy, cotton, corn, millet and sorghum crops sowed in single or double crop systems. Due to the difficulty in separating certain classes because of too similar agricultural calendars, the classification will be reduced to 3 classes : Cotton (single crop), Soy and cotton (double crop), soy (single or double crop with corn, millet or sorghum). The classification will use training data obtained in the 2005-2006 harvest and then be tested on the 2006-2007 harvest. In a first step, four smoothing techniques are presented and criticized. Those techniques are Best Index Slope Extraction (BISE) [3], Mean Value Iteration (MVI) [4], Weighted Least Squares (WLS) [5] and Savitzky-Golay Filter (SG) [6] [7]. These techniques are then implemented and visually compared on a few individual pixels so that it allows doing a first selection between the five studied techniques. The WLS and SG techniques are selected according to criteria proposed by [8]. Those criteria are: ability in eliminating frequent noises, conserving the upper values of the VI profiles and keeping the temporality of the profiles. Those selected algorithms are then programmed and applied to the MODIS/TERRA EVI data (16-days composition periods). Tests of separability are realized based on the Jeffries-Matusita distance in order to see if the algorithms managed in improving the potential of differentiation between the classes. Those tests are realized on the overall profile (comprising 23 MODIS images) as well as on each MODIS sub-period of the profile [1]. This last test is a double interest process because it allows comparing the smoothing techniques and also enables to select a set of images which carries more information on the separability between the classes. Those selected dates can then be used to realize a supervised classification. Here three different classifiers are tested to evaluate if the smoothing techniques as a particular effect on the classification depending on the classifiers used. Those classifiers are Maximum Likelihood classifier, Spectral Angle Mapper (SAM) classifier and CHAID Improved Decision tree. It appears through the separability tests on the overall process that the smoothed profiles don't improve efficiently the potential of discrimination between classes when compared with the original data. However, the same tests realized on the MODIS sub-periods show better results obtained with the smoothed algorithms. The results of the classification confirm this first analyze. The Kappa coefficients are always better with the smoothing techniques and the results obtained with the WLS and SG smoothed profiles are nearly equal. However, the results are different depending on the classifier used. The impact of the smoothing algorithms is much better while using the decision tree model. Indeed, it allows a gain of 0.1 in the Kappa coefficient. While using the Maximum Likelihood end SAM models, the gain remains positive but is much lower (Kappa improved of 0.02 only). Thus, this work's aim is to prove the utility in smoothing the VI profiles in order to improve the final results. However, the choice of the smoothing algorithm has to be made considering the original data used and the classifier models used. In that case the Savitzky-Golay filter gave the better results. 653 $aAlgoritmo 653 $aClasses de culturas 700 1 $aJONATHAN, M. 700 1 $aMEIRELLES, M. S. P. 700 1 $aDUBREUIL, V. 700 1 $aLECERF, R.
Download
Esconder MarcMostrar Marc Completo |
Registro original: |
Embrapa Solos (CNPS) |
|
Biblioteca |
ID |
Origem |
Tipo/Formato |
Classificação |
Cutter |
Registro |
Volume |
Status |
URL |
Voltar
|
|
Registros recuperados : 124 | |
61. | | CORRÊA-FERREIRA, B.S.; CASTRO, L. C.; ROGGIA, S.; CESCONETTO, N.; COSTA, J. M.; OLIVEIRA, M. C. N. de. MIP-soja: uma tecnologia eficiente e sustentável no manejo dos percevejos no atual sistema produtivo da soja. In: CONGRESSO BRASILEIRO DE SOJA, 6., 2012, Cuiabá. Soja: integração nacional e desenvolvimento sustentável: anais. Brasília, DF: Embrapa, 2012. 5 p. 1 CD-ROM.Tipo: Artigo em Anais de Congresso |
Biblioteca(s): Embrapa Soja. |
| |
62. | | ANDRADE, V. M. S.; COSTA, J. M. N.; SILVA, M. A. V.; FERREIRA, W. P. M.; SANS, L. M. A. Partição da energia na fase reprodutiva da cultura de milho. In: CONGRESSO NACIONAL DE MILHO E SORGO, 27.; SIMPOSIO BRASILEIRO SOBRE A LAGARTA-DO-CARTUCHO, SPODOPTERA FRUGIPERDA, 3.; WORKSHOP SOBRE MANEJO E ETIOLOGIA DA MANCHA BRANCA DO MILHO, 2008, Londrina. Agroenergia, produção de alimentos e mudanças climáticas: desafios para milho e sorgo: trabalhos e palestras. [Londrina]: IAPAR; [Sete Lagoas]: Embrapa Milho e Sorgo, 2008. 1 CD-ROM.Tipo: Artigo em Anais de Congresso / Nota Técnica |
Biblioteca(s): Embrapa Milho e Sorgo. |
| |
63. | | SILVEIRA, J. M.; COSTA, J. M.; CARRARO, I. M.; WOBETO, C.; MOREIRA FILHO, P.; CASTIGLIONI, V. B. R. The potential of winter/spring sowings of sunflower as oil seed crop in southern Brazil. In: INTERNATIONAL SUNFLOWER CONFERENCE, 13., 1992, Pisa. Proceedings... Paris: International Sunflower Association, 1992. p. 416-421.Tipo: Artigo em Anais de Congresso |
Biblioteca(s): Embrapa Soja. |
| |
65. | | GAUDENCIO, C. de A.; COSTA, J. M.; LANTMANN, A. F.; MACHADO, C. C.; VOLL, E.; GAZZIERO, D. L. P. Rotacao soja-milho sucedida por trigo, adubacao verde e cobertura morta do solo, no sistema alternado de preparo do solo e semeadura direta, em Campo Mourao, PR. In: EMBRAPA. Centro Nacional de Pesquisa de Soja (Londrina, PR). Resultados de pesquisa de soja 1988/89. Londrina, 1989. p.261-271. (EMBRAPA-CNPSo. Documentos, 43).Biblioteca(s): Embrapa Soja. |
| |
68. | | CARVALHO, M. G. de; COSTA, J. M. C. da; SOUZA, V. A. B. de; MAIA, G. A.; SANTOS, S. M. L. dos. Composição nutricional de amêndoas de chichá (Sterculia striata ST. Hill. et Naud), sapucaia (Lecithys pisonis Camb.) e castanha do gurguéia (Dipteryx spp.). In: CONGRESSO LATINO AMERICANO DE ANALISTAS DE ALIMENTOS, 15., 2007, Fortaleza. Anais... Fortaleza: SBAAL, 2007. 3 p. 1 CD-ROM.Tipo: Artigo em Anais de Congresso / Nota Técnica |
Biblioteca(s): Embrapa Meio-Norte. |
| |
69. | | SILVA, M. A. V.; ANDRADE, V. M. S. de; COSTA, J. M. N. da; FERREIRA, W. P. M.; BEZERRA, A. R. G.; MOSCONS, E. S. Influência da soma térmica no crescimento e desenvolvimento do milho BR 106 cultivado sob plantio direto. In: CONGRESSO BRASILEIRO DE BIOMETEOROLOGIA, 5., 2011, Piracicaba. Mudanças climáticas: impactos e conseguêcias nos seres vivos: anais. Piracicaba: ESALQ, 2011. 6 p.Tipo: Artigo em Anais de Congresso |
Biblioteca(s): Embrapa Milho e Sorgo. |
| |
70. | | SILVA, M. A. V. da; ANDRADE, V. M. S. de; FERREIRA, W. P. M.; OLIVEIRA, E. C. de; COSTA, J. M. N. da; GONÇALVES, P. H. L. Influência da temperatura do ar e da radiação fotossinteticamente ativa no crescimento e desenvolvimento do milho BR 106 cultivado sob plantio direto. In: CONGRESSO BRASILEIRO DE METEOROLOGIA, 16., 2010, Belém. A Amazônia e o clima global: anais. Belém: SBMET, 2010.Tipo: Artigo em Anais de Congresso |
Biblioteca(s): Embrapa Milho e Sorgo. |
| |
71. | | SOUZA, J. H. P. de; AFONSO, M. R. A.; COSTA, J. M. C. da; WURLITZER, N. J.; RYBKA, A. C. P.; COSTA, J. de P. da. Influência do tempo de liofilização nas características da manga cv. Kent em pó. In: CONGRESSO BRASILEIRO DE CIÊNCIA E TECNOLOGIA DE ALIMENTOS, 26., 2018, Belém, PA. O uso consciente da biodiversidade: perspectivas para o avanço da ciência e tecnologia de alimentos. Belém, PA: SBCTA:UFPA, 2018.Tipo: Artigo em Anais de Congresso |
Biblioteca(s): Embrapa Semiárido. |
| |
73. | | MENDES, L. G.; MENDES, F. R. S.; RIBEIRO, L. C.; DA COSTA, J. M. C.; NASCIMENTO, M. A.; FURTADO, R. F.; MOREIRA, R. A. Influência de parâmetros do spray-dryer no processo de microencapsulação do óleo essencial de alecrim. In: CONGRESSO BRASILEIRO DE CIÊNCIA E TECNOLOGIA DE ALIMENTOS, 25., 2016, Gramado. Anais... Gramado: SBCTA-RS, 2016.Tipo: Artigo em Anais de Congresso |
Biblioteca(s): Embrapa Agroindústria Tropical. |
| |
74. | | MACEDO, R. T. de; ZOTARELLI, L.; COSTA, J. M. da; TORRES, E.; URQUIAGA, S.; BODDEY R. M.; ALVES, B. J. R. Influencia do preparo do solo sobre a contribuicao da FBN para a cultura da soja. In: CONGRESSO BRASILEIRO DE CIENCIA DO SOLO, 28., 2001, Londrina. Ciencia do solo: fator de produtividade e competitividade com sustentabilidade. Londrina: Sociedade Brasileira de Ciencia do Solo, 2001. p.91.Biblioteca(s): Embrapa Soja. |
| |
75. | | VOLL, E.; DOMIT, L. A.; GAZZIERO, D. L. P.; RODRIGUES, B. N.; ADEGAS, F. S.; COSTA, J. M. da; WOBETO, C.; VICENTE, D. Levantamento de banco de sementes e de flora daninha emergente no manejo integrado de plantas daninhas, em lavouras de soja no Parana - 95/96. Londrina: EMBRAPA-CNPSo, 1997. 6p. (EMBRAPA-CNPSo. Pesquisa em Andamento, 18).Biblioteca(s): Embrapa Soja. |
| |
76. | | COSTA, J. M. da S.; MENEZES, D. R.; ZOCCHE, F.; NEVES, A. L. A.; FERNANDES, F. S.; SOUZA, J. B. de. Caracterização de sistemas de produção de vacas de leite no Submédio São Francisco: resultados parciais. In: REUNIÃO ANUAL DA SOCIEDADE BRASILEIRA DE ZOOTECNIA, 47., 2010, Salvador. Empreendedorismo e progresso científico na zootecnia brasileira: anais. Viçosa, MG: Sociedade Brasileira de Zootecnia, 2010.Tipo: Artigo em Anais de Congresso |
Biblioteca(s): Embrapa Gado de Leite; Embrapa Semiárido. |
| |
77. | | SANTOS, M. A. M.; GRADELA, A.; MORAES, E. A.; SOUZA, W. L.; ALVES, N. G.; COSTA, J. M. S.; MATOS, W. C. G. Características de sêmen a fresco e descongelado de garanhões da raça nordestina. Pesquisa Veterinária Brasileira, Brasília, DF, v. 35, n. 11, p. 925-932, nov. 2015.Biblioteca(s): Embrapa Unidades Centrais. |
| |
78. | | RIBEIRO, F. W. M.; LAURENTINO, L. da S.; ALVES, C. R.; BASTOS, M. do S. R.; COSTA, J. M. C da; CANUTO, K. M.; FURTADO, R. F. Chemical modification of gum arabic and its application in the encapsulation of Cymbopogon citratus essential oil. Journal of Applied Polymer Science, v. 132, n. 8, 2015. Projeto: 02.12.01.029.00.03Tipo: Artigo em Periódico Indexado | Circulação/Nível: A - 1 |
Biblioteca(s): Embrapa Agroindústria Tropical. |
| |
80. | | FRANCHINI, J. C.; TORRES, E.; GARBELINI, L. G.; MIYAZAWA, M.; FONTOURA, S.; COSTA, J. M. da; RODRIGUES, J. C. P.; PAULETTI, V. Correção da acidez subsuperficial no plantio direto pela aplicação de calcário na superfície e uso de plantas de cobertura e adubação verde. In: SARAIVA, O. F.; LEITE, R. M. V. B. de C. (Ed.). Resultados de pesquisa da Embrapa Soja 2006. Londrina: Embrapa Soja, 2008. p. 125-132. (Embrapa Soja. Documentos, 308).Tipo: Capítulo em Livro Técnico-Científico |
Biblioteca(s): Embrapa Soja. |
| |
Registros recuperados : 124 | |
|
Nenhum registro encontrado para a expressão de busca informada. |
|
|