|
|
| Acesso ao texto completo restrito à biblioteca da Embrapa Agricultura Digital. Para informações adicionais entre em contato com cnptia.biblioteca@embrapa.br. |
Registro Completo |
Biblioteca(s): |
Embrapa Agricultura Digital. |
Data corrente: |
14/12/2021 |
Data da última atualização: |
14/12/2021 |
Tipo da produção científica: |
Artigo em Anais de Congresso |
Autoria: |
ALMEIDA, H. S. L.; REIS, A. A. dos; WERNER, J. P. S.; ANTUNES, J. F. G.; ZHONG, L.; FIGUEIREDO, G. K. D. A.; ESQUERDO, J. C. D. M.; COUTINHO, A. C.; LAMPARELLI, R. A. C.; MAGALHÃES, P. S. G. |
Afiliação: |
HENRIQUE S. L. ALMEIDA, UNICAMP; ALINY APARECIDA DOS REIS, UNICAMP; JOÃO PAULO SAMPAIO WERNER, UNICAMP; JOAO FRANCISCO GONCALVES ANTUNES, CNPTIA; LIHENG ZHONG, Ant Group, World Financial Center, Beijing; GLEYCE KELLY DANTAS ARAÚJO FIGUEIREDO, UNICAMP; JULIO CESAR DALLA MORA ESQUERDO, CNPTIA; ALEXANDRE CAMARGO COUTINHO, CNPTIA; RUBENS AUGUSTO CAMARGO LAMPARELLI, UNICAMP; PAULO S. G. MAGALHÃES, UNICAMP. |
Título: |
Deep neural networks for mapping integrated crop-livestock systems using PlanetScope time series. |
Ano de publicação: |
2021 |
Fonte/Imprenta: |
IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, 2021, Brussels. Proceedings [...]. [S. l.]: IEEE, 2021. |
Páginas: |
p. 4224-4227. |
ISBN: |
978-1-6654-0369-6 |
DOI: |
10.1109/IGARSS47720.2021.9554500 |
Idioma: |
Inglês |
Notas: |
IGARSS 2021. Paper WE2.MM-8.3. |
Conteúdo: |
Abstract: Mapping highly dynamic cropping systems using satellite image time series is still challenging even when robust approaches are used. We assessed the potential of using high spatial and temporal resolution PlanetScope time series and deep neural networks (Convolutional Neural Networks (CNN) in one dimension - Conv1D, Long Short-Term Memory (LSTM), and Multi-Layer Perceptron (MLP)) for mapping integrated crop-livestock systems (ICLS) and different land covers in the western region of São Paulo State, Brazil. We used 10-day and 15-day composite EVI and NDVI time series (both individually and combined) as input data in the neural network classifiers. Conv1D using both EVI and NDVI 10 day-composite time series outperformed the other classifiers evaluated in this study (LSTM and MLP), allowing improved discrimination of land parcels with ICLS in our study area. |
Palavras-Chave: |
Aprendizado profundo; Convolutional Neural Networks; Deep learning; EVI; Nano-Satellites; Nanossatélites; NDVI; Redes neurais; Redes neurais convolucionais; Redes neurais profundas; Séries temporais; Sistemas de integração lavoura-pecuária. |
Thesaurus Nal: |
Neural networks; Time series analysis. |
Categoria do assunto: |
-- |
Marc: |
LEADER 02288nam a2200433 a 4500 001 2137800 005 2021-12-14 008 2021 bl uuuu u00u1 u #d 020 $a978-1-6654-0369-6 024 7 $a10.1109/IGARSS47720.2021.9554500$2DOI 100 1 $aALMEIDA, H. S. L. 245 $aDeep neural networks for mapping integrated crop-livestock systems using PlanetScope time series.$h[electronic resource] 260 $aIEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, 2021, Brussels. Proceedings [...]. [S. l.]: IEEE$c2021 300 $ap. 4224-4227. 500 $aIGARSS 2021. Paper WE2.MM-8.3. 520 $aAbstract: Mapping highly dynamic cropping systems using satellite image time series is still challenging even when robust approaches are used. We assessed the potential of using high spatial and temporal resolution PlanetScope time series and deep neural networks (Convolutional Neural Networks (CNN) in one dimension - Conv1D, Long Short-Term Memory (LSTM), and Multi-Layer Perceptron (MLP)) for mapping integrated crop-livestock systems (ICLS) and different land covers in the western region of São Paulo State, Brazil. We used 10-day and 15-day composite EVI and NDVI time series (both individually and combined) as input data in the neural network classifiers. Conv1D using both EVI and NDVI 10 day-composite time series outperformed the other classifiers evaluated in this study (LSTM and MLP), allowing improved discrimination of land parcels with ICLS in our study area. 650 $aNeural networks 650 $aTime series analysis 653 $aAprendizado profundo 653 $aConvolutional Neural Networks 653 $aDeep learning 653 $aEVI 653 $aNano-Satellites 653 $aNanossatélites 653 $aNDVI 653 $aRedes neurais 653 $aRedes neurais convolucionais 653 $aRedes neurais profundas 653 $aSéries temporais 653 $aSistemas de integração lavoura-pecuária 700 1 $aREIS, A. A. dos 700 1 $aWERNER, J. P. S. 700 1 $aANTUNES, J. F. G. 700 1 $aZHONG, L. 700 1 $aFIGUEIREDO, G. K. D. A. 700 1 $aESQUERDO, J. C. D. M. 700 1 $aCOUTINHO, A. C. 700 1 $aLAMPARELLI, R. A. C. 700 1 $aMAGALHÃES, P. S. G.
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 : 163 | |
Registros recuperados : 163 | |
|
Nenhum registro encontrado para a expressão de busca informada. |
|
|