| |
|
|
 | Acesso ao texto completo restrito à biblioteca da Embrapa Recursos Genéticos e Biotecnologia. Para informações adicionais entre em contato com cenargen.biblioteca@embrapa.br. |
|
Registro Completo |
|
Biblioteca(s): |
Embrapa Instrumentação; Embrapa Recursos Genéticos e Biotecnologia. |
|
Data corrente: |
10/09/2021 |
|
Data da última atualização: |
03/10/2023 |
|
Tipo da produção científica: |
Artigo em Periódico Indexado |
|
Autoria: |
RAMOS, A. P. M.; GOMES, F. D. G.; PINHEIRO, M. M. F.; FURUYA, D. E. G.; GONÇALVEZ, W. N.; MARCATO JUNIOR, J.; MICHEREFF, M. F. F.; MORAES, M. C. B.; BORGES, M.; LAUMANN, R. A.; LIESENBERG, V.; JORGE, L. A. de C.; OSCO, L. P. |
|
Afiliação: |
ANA PAULA MARQUES RAMOS, UNOESTE; FELIPE DAVID GEORGES GOMES, UNOESTE; MAYARA MAEZANO FAITA PINHEIRO, UNOESTE; DANIELLE ELIS GARCIA FURUYA, UNOESTE; WESLEY NUNES GONÇALVEZ, UFMS; JOSÉ MARCATO JUNIOR, UFMS; MIRIAN FERNANDES FURTADO MICHEREFF; MARIA CAROLINA BLASSIOLI MORAES, Cenargen; MIGUEL BORGES, Cenargen; RAUL ALBERTO LAUMANN, Cenargen; VERALDO LIESENBERG, Udesc; LUCIO ANDRE DE CASTRO JORGE, CNPDIA; LUCAS PRADO OSCO, UNOESTE. |
|
Título: |
Detecting the attack of the fall armyworm (Spodoptera frugiperda) in cotton plants with machine learning and spectral measurements. |
|
Ano de publicação: |
2021 |
|
Fonte/Imprenta: |
Precision Agriculture, 2021. |
|
DOI: |
https://doi.org/10.1007/s11119-021-09845-4 |
|
Idioma: |
Inglês |
|
Notas: |
Na publicação: Maria Carolina Blassioli-Moraes; Raúl Alberto Alaumann. |
|
Conteúdo: |
ABSTRACT: The Spodoptera frugiperda (i.e., fall armyworm) causes irreversible damage in cotton cultivars, and its visual inspection on plants is a burdensome task for humans. A recent strategy to automatically do similar tasks is processing hyperspectral reflectance measurements with machine learning algorithms. Herein, its proposed a framework for modeling the spectral response of cotton plants under the fall armyworm attacks using machine learning algorithms, culminating in a theoretical model creation based on the band simulation process. A controlled experiment was conducted to collect hyperspectral radiance measurements from health and damage cotton plants over eight days. A hand-held spectroradiometer operating from 350 to 2500 nm was used. Several algorithms were evaluated, and a ranking approach was adopted to identify the most contributive wavelengths for detecting the damage. The Self-Organizing Map method was applied to organize the spectral wavelengths into groups, favoring the theoretical model creation for two sensors: OLI (Landsat-8) and MSI (Sentinel-2). It was found that the Random Forest algorithm produced the most suitable model, and the last day of analysis was better to separate healthy and damaged plants (F-measure: 0.912). The best spectral regions range from the red to near-infrared (650 to 1350 nm) and the shortwave infrared (1570 to 1640 nm). The theoretical model returned accurate results using both sensors (OLI, F-Measure?=?0.865, and MSI, F-Measure?=?0.886). In conclusion, the proposed framework contributes to accurately identifying cotton plants under the Spodoptera frugiperda attack for both hyperspectral and multispectral scales. MenosABSTRACT: The Spodoptera frugiperda (i.e., fall armyworm) causes irreversible damage in cotton cultivars, and its visual inspection on plants is a burdensome task for humans. A recent strategy to automatically do similar tasks is processing hyperspectral reflectance measurements with machine learning algorithms. Herein, its proposed a framework for modeling the spectral response of cotton plants under the fall armyworm attacks using machine learning algorithms, culminating in a theoretical model creation based on the band simulation process. A controlled experiment was conducted to collect hyperspectral radiance measurements from health and damage cotton plants over eight days. A hand-held spectroradiometer operating from 350 to 2500 nm was used. Several algorithms were evaluated, and a ranking approach was adopted to identify the most contributive wavelengths for detecting the damage. The Self-Organizing Map method was applied to organize the spectral wavelengths into groups, favoring the theoretical model creation for two sensors: OLI (Landsat-8) and MSI (Sentinel-2). It was found that the Random Forest algorithm produced the most suitable model, and the last day of analysis was better to separate healthy and damaged plants (F-measure: 0.912). The best spectral regions range from the red to near-infrared (650 to 1350 nm) and the shortwave infrared (1570 to 1640 nm). The theoretical model returned accurate results using both sensors (OLI, F-Measure?=?0.865, and MSI, F-Measu... Mostrar Tudo |
|
Palavras-Chave: |
Insect damage; Machine learning; Spectral data; Theoretical model. |
|
Categoria do assunto: |
-- |
|
Marc: |
LEADER 02768naa a2200337 a 4500
001 2138144
005 2023-10-03
008 2021 bl uuuu u00u1 u #d
024 7 $ahttps://doi.org/10.1007/s11119-021-09845-4$2DOI
100 1 $aRAMOS, A. P. M.
245 $aDetecting the attack of the fall armyworm (Spodoptera frugiperda) in cotton plants with machine learning and spectral measurements.$h[electronic resource]
260 $c2021
500 $aNa publicação: Maria Carolina Blassioli-Moraes; Raúl Alberto Alaumann.
520 $aABSTRACT: The Spodoptera frugiperda (i.e., fall armyworm) causes irreversible damage in cotton cultivars, and its visual inspection on plants is a burdensome task for humans. A recent strategy to automatically do similar tasks is processing hyperspectral reflectance measurements with machine learning algorithms. Herein, its proposed a framework for modeling the spectral response of cotton plants under the fall armyworm attacks using machine learning algorithms, culminating in a theoretical model creation based on the band simulation process. A controlled experiment was conducted to collect hyperspectral radiance measurements from health and damage cotton plants over eight days. A hand-held spectroradiometer operating from 350 to 2500 nm was used. Several algorithms were evaluated, and a ranking approach was adopted to identify the most contributive wavelengths for detecting the damage. The Self-Organizing Map method was applied to organize the spectral wavelengths into groups, favoring the theoretical model creation for two sensors: OLI (Landsat-8) and MSI (Sentinel-2). It was found that the Random Forest algorithm produced the most suitable model, and the last day of analysis was better to separate healthy and damaged plants (F-measure: 0.912). The best spectral regions range from the red to near-infrared (650 to 1350 nm) and the shortwave infrared (1570 to 1640 nm). The theoretical model returned accurate results using both sensors (OLI, F-Measure?=?0.865, and MSI, F-Measure?=?0.886). In conclusion, the proposed framework contributes to accurately identifying cotton plants under the Spodoptera frugiperda attack for both hyperspectral and multispectral scales.
653 $aInsect damage
653 $aMachine learning
653 $aSpectral data
653 $aTheoretical model
700 1 $aGOMES, F. D. G.
700 1 $aPINHEIRO, M. M. F.
700 1 $aFURUYA, D. E. G.
700 1 $aGONÇALVEZ, W. N.
700 1 $aMARCATO JUNIOR, J.
700 1 $aMICHEREFF, M. F. F.
700 1 $aMORAES, M. C. B.
700 1 $aBORGES, M.
700 1 $aLAUMANN, R. A.
700 1 $aLIESENBERG, V.
700 1 $aJORGE, L. A. de C.
700 1 $aOSCO, L. P.
773 $tPrecision Agriculture, 2021.
Download
Esconder MarcMostrar Marc Completo |
|
Registro original: |
Embrapa Instrumentação (CNPDIA) |
|
|
Biblioteca |
ID |
Origem |
Tipo/Formato |
Classificação |
Cutter |
Registro |
Volume |
Status |
URL |
Voltar
|
|
|
| Registros recuperados : 1 | |
| 1. |  | DÍAZ, S.; KATTGE, J.; CORNELISSEN, J. H. C.; WRIGHT, I. J.; LAVOREL, S.; DRAY, S.; REU, B.; KLEYER, M.; WIRTH, C.; PRENTICE, I. C.; GARNIER, E.; BÖNISCH, G.; WESTOBY, M.; POORTER, H.; REICH, P. B.; MOLES, A. T.; DICKIE, J.; ZANNE, A. E.; CHAVE, J.; WRIGHT, S. J.; SHEREMETIEV, S. N.; JACTEL, H.; BARALOTO, C.; CERABOLINI, B. E. L.; PIERCE, S.; SHIPLEY, B.; CASANOVES, F.; JOSWIG, J. S.; GÜNTHER, A.; FALCZUK, V.; RÜGER, N.; MAHECHA, M. D.; GORNÉ, L. D.; AMIAUD, B.; ATKIN, O. K.; BAHN, M.; BALDOCCHI, D.; BECKMANN, M.; BLONDER, B.; BOND, W.; BOND-LAMBERTY, B.; BROWN, K.; BURRASCANO, S.; BYUN, C.; CAMPETELLA, G.; CAVENDER-BARES, J.; CHAPIN, F. S.; CHOAT, B.; COOMES, D. A.; CORNWELL, W. K.; CRAINE, J.; CRAVEN, D.; DAINESE, M.; ARAUJO, A. C. de; VRIES, F. T. de; DOMINGUES, T. F.; ENQUIST, B. J.; FAGÚNDEZ, J.; FANG, J.; FERNÁNDEZ-MÉNDEZ, F.; FERNANDEZ-PIEDADE, M. T.; FORD, H.; FOREY, E.; FRESCHET, G. T.; GACHET, S.; GALLAGHER, R.; GREEN, W.; GUERIN, G. R.; GUTIÉRREZ, A. G.; HARRISON, S. P.; HATTINGH, W. N.; HE, T.; HICKLER, T.; HIGGINS, S. I.; HIGUCHI, P.; ILIC, J.; JACKSON, R. B.; JALILI, A.; JANSEN, S.; KOIKE, F.; KÖNIG, C.; KRAFT, N.; KRAMER, K.; KREFT, H.; KÜHN, I.; KUROKAWA, H.; LAMB, E. G.; LAUGHLIN, D. C.; LEISHMAN, M.; LEWIS, S.; LOUAULT, F.; MALHADO, A. C. M.; MANNING, P.; MEIR, P.; MENCUCCINI, M.; MESSIER, J.; MILLER, R.; MINDEN, V.; MOLOFSKY, J.; MONTGOMERY, R.; MONTSERRAT-MARTÍ, G.; MORETTI, M.; MÜLLER, S.; NIINEMETS, Ü.; OGAYA, R.; ÖLLERER, K.; ONIPCHENKO, V.; ONODA, Y.; OZINGA, W. A.; PAUSAS, J. G.; PECO, B.; PENUELAS, J.; PILLAR, V. D.; PLADEVALL, C.; RÖMERMANN, C.; SACK, L.; SALINAS, N.; SANDEL, B.; SARDANS, J.; SCHAMP, B.; SCHERER-LORENZEN, M.; SCHULZE, E.; SCHWEINGRUBER, F.; SHIODERA, S.; SOSINSKI JUNIOR, E. E.; SOUDZILOVSKAIA, N.; SPASOJEVIC, M. J.; SWAINE, E.; SWENSON, N.; TAUTENHAHN, S.; THOMPSON, K.; TOTTE, A.; URRUTIA-JALABERT, R.; VALLADARES, F.; BODEGOM, P. V.; VASSEUR, F.; VERHEYEN, K.; VILE, D.; VIOLLE, C.; HOLLE, B. V.; WEIGELT, P.; WEIHER, E.; WIEMANN, M. C.; WILLIAMS, M.; WRIGHT, J.; ZOTZ, G. The global spectrum of plant form and function: enhanced species-level trait dataset. Scientific Data, v. 9, n. 1, 755, 2022. 18 p.| Biblioteca(s): Embrapa Clima Temperado. |
|    |
| Registros recuperados : 1 | |
|
| Expressão de busca inválida. Verifique!!! |
|
|
