Fusing multi-season UAS images with convolutional neural networks to map tree species in Amazonian forests.

dc.contributorHUDSON 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.creatorVERAS, H. F. P.
dc.creatorFERREIRA, M. P.
dc.creatorCUNHA NETO, E. M. da
dc.creatorFIGUEIREDO, E. O.
dc.creatorDALLA CORTE, A. P.
dc.creatorSANQUETTA, C. R.
dc.date2022-12-21T14:02:03Z
dc.date2022-12-21T14:02:03Z
dc.date2022-12-21
dc.date2022
dc.date.accessioned2023-09-05T02:04:00Z
dc.date.available2023-09-05T02:04:00Z
dc.identifierEcological Informatics, v. 71, 101815, 2022.
dc.identifier1574-9541
dc.identifierhttp://www.alice.cnptia.embrapa.br/alice/handle/doc/1150165
dc.identifierhttps://doi.org/10.1016/j.ecoinf.2022.101815
dc.identifier.urihttps://repositorioslatinoamericanos.uchile.cl/handle/2250/8634131
dc.descriptionRemote 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.
dc.languageIngles
dc.languageen
dc.rightsopenAccess
dc.subjectAmazônia Ocidental
dc.subjectAmazonia Occidental
dc.subjectFusão de imagens
dc.subjectImagem RGB
dc.subjectModelo CNN
dc.subjectMapeamento de espécies
dc.subjectImagem multitemporada
dc.subjectTeledetección
dc.subjectBosques tropicales
dc.subjectIdentificación de especies
dc.subjectBosques experimentales
dc.subjectEmbrapa Acre
dc.subjectRio Branco (AC)
dc.subjectAcre
dc.subjectWestern Amazon
dc.subjectSensoriamento Remoto
dc.subjectFenologia
dc.subjectCampo Experimental
dc.subjectEspécie Nativa
dc.subjectFloresta Tropical
dc.subjectIdentificação
dc.subjectRemote sensing
dc.subjectExperimental forests
dc.subjectTropical forests
dc.subjectSpecies identification
dc.subjectPhenology
dc.titleFusing multi-season UAS images with convolutional neural networks to map tree species in Amazonian forests.
dc.typeArtigo de periódico


Este ítem pertenece a la siguiente institución