Fusing multi-season UAS images with convolutional neural networks to map tree species in Amazonian forests.
Autor(a) principal: | |
---|---|
Data de Publicação: | 2022 |
Outros Autores: | , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da EMBRAPA (Repository Open Access to Scientific Information from EMBRAPA - Alice) |
Texto Completo: | http://www.alice.cnptia.embrapa.br/alice/handle/doc/1150165 https://doi.org/10.1016/j.ecoinf.2022.101815 |
Resumo: | Remote sensing images obtained by unoccupied aircraft systems (UAS) across different seasons enabled capturing of species-specific phenological patterns of tropical trees. The application of UAS multi-season images to classify tropical tree species is still poorly understood. In this study, we used RGB images from different seasons obtained by a low-cost UAS and convolutional neural networks (CNNs) to map tree species in an Amazonian forest. Individual tree crowns (ITC) were outlined in the UAS images and identified to the species level using forest inventory data. The CNN model was trained with images obtained in February, May, August, and November. The classification accuracy in the rainy season (November and February) was higher than in the dry season (May and August). Fusing images from multiple seasons improved the average accuracy of tree species classification by up to 21.1 percentage points, reaching 90.5%. The CNN model can learn species-specific phenological characteristics that impact the classification accuracy, such as leaf fall in the dry season, which highlights its potential to discriminate species in various conditions. We produced high-quality individual tree crown maps of the species using a post-processing procedure. The combination of multi-season UAS images and CNNs has the potential to map tree species in the Amazon, providing valuable insights for forest management and conservation initiatives. |
id |
EMBR_6f70783fa56812b83328a0fb0d4caa3e |
---|---|
oai_identifier_str |
oai:www.alice.cnptia.embrapa.br:doc/1150165 |
network_acronym_str |
EMBR |
network_name_str |
Repositório Institucional da EMBRAPA (Repository Open Access to Scientific Information from EMBRAPA - Alice) |
repository_id_str |
2154 |
spelling |
Fusing multi-season UAS images with convolutional neural networks to map tree species in Amazonian forests.Amazônia OcidentalAmazonia OccidentalFusão de imagensImagem RGBModelo CNNMapeamento de espéciesImagem multitemporadaTeledetecciónBosques tropicalesIdentificación de especiesBosques experimentalesEmbrapa AcreRio Branco (AC)AcreWestern AmazonSensoriamento RemotoFenologiaCampo ExperimentalEspécie NativaFloresta TropicalIdentificaçãoRemote sensingExperimental forestsTropical forestsSpecies identificationPhenologyRemote sensing images obtained by unoccupied aircraft systems (UAS) across different seasons enabled capturing of species-specific phenological patterns of tropical trees. The application of UAS multi-season images to classify tropical tree species is still poorly understood. In this study, we used RGB images from different seasons obtained by a low-cost UAS and convolutional neural networks (CNNs) to map tree species in an Amazonian forest. Individual tree crowns (ITC) were outlined in the UAS images and identified to the species level using forest inventory data. The CNN model was trained with images obtained in February, May, August, and November. The classification accuracy in the rainy season (November and February) was higher than in the dry season (May and August). Fusing images from multiple seasons improved the average accuracy of tree species classification by up to 21.1 percentage points, reaching 90.5%. The CNN model can learn species-specific phenological characteristics that impact the classification accuracy, such as leaf fall in the dry season, which highlights its potential to discriminate species in various conditions. We produced high-quality individual tree crown maps of the species using a post-processing procedure. The combination of multi-season UAS images and CNNs has the potential to map tree species in the Amazon, providing valuable insights for forest management and conservation initiatives.HUDSON FRANKLIN PESSOA VERAS, UNIVERSIDADE FEDERAL DO PARANÁ; MATHEUS PINHEIRO FERREIRA, INSTITUTO MILITAR DE ENGENHARIA; ERNANDES MACEDO DA CUNHA NETO, UNIVERSIDADE FEDERAL DO PARANÁ; EVANDRO ORFANO FIGUEIREDO, CPAF-AC; ANA PAULA DALLA CORTE, UNIVERSIDADE FEDERAL DO PARANÁ; CARLOS ROBERTO SANQUETTA, UNIVERSIDADE FEDERAL DO PARANÁ.VERAS, H. F. P.FERREIRA, M. P.CUNHA NETO, E. M. daFIGUEIREDO, E. O.DALLA CORTE, A. P.SANQUETTA, C. R.2022-12-21T14:02:03Z2022-12-21T14:02:03Z2022-12-212022info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleEcological Informatics, v. 71, 101815, 2022.1574-9541http://www.alice.cnptia.embrapa.br/alice/handle/doc/1150165https://doi.org/10.1016/j.ecoinf.2022.101815enginfo:eu-repo/semantics/openAccessreponame:Repositório Institucional da EMBRAPA (Repository Open Access to Scientific Information from EMBRAPA - Alice)instname:Empresa Brasileira de Pesquisa Agropecuária (Embrapa)instacron:EMBRAPA2022-12-21T14:02:03Zoai:www.alice.cnptia.embrapa.br:doc/1150165Repositório InstitucionalPUBhttps://www.alice.cnptia.embrapa.br/oai/requestopendoar:21542022-12-21T14:02:03falseRepositório InstitucionalPUBhttps://www.alice.cnptia.embrapa.br/oai/requestcg-riaa@embrapa.bropendoar:21542022-12-21T14:02:03Repositório Institucional da EMBRAPA (Repository Open Access to Scientific Information from EMBRAPA - Alice) - Empresa Brasileira de Pesquisa Agropecuária (Embrapa)false |
dc.title.none.fl_str_mv |
Fusing multi-season UAS images with convolutional neural networks to map tree species in Amazonian forests. |
title |
Fusing multi-season UAS images with convolutional neural networks to map tree species in Amazonian forests. |
spellingShingle |
Fusing multi-season UAS images with convolutional neural networks to map tree species in Amazonian forests. VERAS, H. F. P. Amazônia Ocidental Amazonia Occidental Fusão de imagens Imagem RGB Modelo CNN Mapeamento de espécies Imagem multitemporada Teledetección Bosques tropicales Identificación de especies Bosques experimentales Embrapa Acre Rio Branco (AC) Acre Western Amazon Sensoriamento Remoto Fenologia Campo Experimental Espécie Nativa Floresta Tropical Identificação Remote sensing Experimental forests Tropical forests Species identification Phenology |
title_short |
Fusing multi-season UAS images with convolutional neural networks to map tree species in Amazonian forests. |
title_full |
Fusing multi-season UAS images with convolutional neural networks to map tree species in Amazonian forests. |
title_fullStr |
Fusing multi-season UAS images with convolutional neural networks to map tree species in Amazonian forests. |
title_full_unstemmed |
Fusing multi-season UAS images with convolutional neural networks to map tree species in Amazonian forests. |
title_sort |
Fusing multi-season UAS images with convolutional neural networks to map tree species in Amazonian forests. |
author |
VERAS, H. F. P. |
author_facet |
VERAS, H. F. P. FERREIRA, M. P. CUNHA NETO, E. M. da FIGUEIREDO, E. O. DALLA CORTE, A. P. SANQUETTA, C. R. |
author_role |
author |
author2 |
FERREIRA, M. P. CUNHA NETO, E. M. da FIGUEIREDO, E. O. DALLA CORTE, A. P. SANQUETTA, C. R. |
author2_role |
author author author author author |
dc.contributor.none.fl_str_mv |
HUDSON FRANKLIN PESSOA VERAS, UNIVERSIDADE FEDERAL DO PARANÁ; MATHEUS PINHEIRO FERREIRA, INSTITUTO MILITAR DE ENGENHARIA; ERNANDES MACEDO DA CUNHA NETO, UNIVERSIDADE FEDERAL DO PARANÁ; EVANDRO ORFANO FIGUEIREDO, CPAF-AC; ANA PAULA DALLA CORTE, UNIVERSIDADE FEDERAL DO PARANÁ; CARLOS ROBERTO SANQUETTA, UNIVERSIDADE FEDERAL DO PARANÁ. |
dc.contributor.author.fl_str_mv |
VERAS, H. F. P. FERREIRA, M. P. CUNHA NETO, E. M. da FIGUEIREDO, E. O. DALLA CORTE, A. P. SANQUETTA, C. R. |
dc.subject.por.fl_str_mv |
Amazônia Ocidental Amazonia Occidental Fusão de imagens Imagem RGB Modelo CNN Mapeamento de espécies Imagem multitemporada Teledetección Bosques tropicales Identificación de especies Bosques experimentales Embrapa Acre Rio Branco (AC) Acre Western Amazon Sensoriamento Remoto Fenologia Campo Experimental Espécie Nativa Floresta Tropical Identificação Remote sensing Experimental forests Tropical forests Species identification Phenology |
topic |
Amazônia Ocidental Amazonia Occidental Fusão de imagens Imagem RGB Modelo CNN Mapeamento de espécies Imagem multitemporada Teledetección Bosques tropicales Identificación de especies Bosques experimentales Embrapa Acre Rio Branco (AC) Acre Western Amazon Sensoriamento Remoto Fenologia Campo Experimental Espécie Nativa Floresta Tropical Identificação Remote sensing Experimental forests Tropical forests Species identification Phenology |
description |
Remote sensing images obtained by unoccupied aircraft systems (UAS) across different seasons enabled capturing of species-specific phenological patterns of tropical trees. The application of UAS multi-season images to classify tropical tree species is still poorly understood. In this study, we used RGB images from different seasons obtained by a low-cost UAS and convolutional neural networks (CNNs) to map tree species in an Amazonian forest. Individual tree crowns (ITC) were outlined in the UAS images and identified to the species level using forest inventory data. The CNN model was trained with images obtained in February, May, August, and November. The classification accuracy in the rainy season (November and February) was higher than in the dry season (May and August). Fusing images from multiple seasons improved the average accuracy of tree species classification by up to 21.1 percentage points, reaching 90.5%. The CNN model can learn species-specific phenological characteristics that impact the classification accuracy, such as leaf fall in the dry season, which highlights its potential to discriminate species in various conditions. We produced high-quality individual tree crown maps of the species using a post-processing procedure. The combination of multi-season UAS images and CNNs has the potential to map tree species in the Amazon, providing valuable insights for forest management and conservation initiatives. |
publishDate |
2022 |
dc.date.none.fl_str_mv |
2022-12-21T14:02:03Z 2022-12-21T14:02:03Z 2022-12-21 2022 |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/publishedVersion info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
Ecological Informatics, v. 71, 101815, 2022. 1574-9541 http://www.alice.cnptia.embrapa.br/alice/handle/doc/1150165 https://doi.org/10.1016/j.ecoinf.2022.101815 |
identifier_str_mv |
Ecological Informatics, v. 71, 101815, 2022. 1574-9541 |
url |
http://www.alice.cnptia.embrapa.br/alice/handle/doc/1150165 https://doi.org/10.1016/j.ecoinf.2022.101815 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.source.none.fl_str_mv |
reponame:Repositório Institucional da EMBRAPA (Repository Open Access to Scientific Information from EMBRAPA - Alice) instname:Empresa Brasileira de Pesquisa Agropecuária (Embrapa) instacron:EMBRAPA |
instname_str |
Empresa Brasileira de Pesquisa Agropecuária (Embrapa) |
instacron_str |
EMBRAPA |
institution |
EMBRAPA |
reponame_str |
Repositório Institucional da EMBRAPA (Repository Open Access to Scientific Information from EMBRAPA - Alice) |
collection |
Repositório Institucional da EMBRAPA (Repository Open Access to Scientific Information from EMBRAPA - Alice) |
repository.name.fl_str_mv |
Repositório Institucional da EMBRAPA (Repository Open Access to Scientific Information from EMBRAPA - Alice) - Empresa Brasileira de Pesquisa Agropecuária (Embrapa) |
repository.mail.fl_str_mv |
cg-riaa@embrapa.br |
_version_ |
1794503536435789824 |