Canopy palm cover across the Brazilian Amazon forests mapped with airborne LiDAR data and deep learning

Autor(es)

Dalagnol, Ricardo ; Wagner, Fabien H. ; Emilio, Thaise ; Streher, Annia S. ; Galvao, Lenio S. ; Ometto, Jean P. H. B. ; Aragao, Luiz E. O. C.

• Tipo de documento: Artigo Científico
• Fonte: REMOTE SENSING IN ECOLOGY AND CONSERVATION; v. 8, n. 5, p. 14-pg., 2022-07-22.

Resumo

The Amazon region in Brazil contains c. 30% of the palm species of the world. However, palm cover at macroecological scales has not yet been quantified in this biome. Here, we used high spatial resolution LiDAR data, acquired from 610 flightlines over the Brazilian Amazon, to map canopy palm cover for the first time using a deep learning approach. The image segmentation model from U-Net deep learning was selected for mapping palm segments using the LiDAR canopy height model (CHM) at 0.5-m spatial resolution. To train and validate the model, we manually delineated 6971 canopy palm segments over 931.43 ha of forests on four training sites by inspecting their unique star-shaped crown architecture in the CHM. The results indicated an accuracy of 80% to automatically map canopy palm area. The approach detected >1.1 million palm segments over the 480 000 ha sampled by LiDAR and roughly estimated 1.05 billion palm segments for the Brazilian Amazon. Palm cover was not evenly distributed over the Amazon, revealing undocumented hotspots of high cover (>5%) in eastern Amazon (Para state), and confirming documented hotspots in southwest (Acre state) and north of the region (Roraima state). Palm segment height was strongly and positively correlated with forest height, where palm segments showed overall lower height. A higher canopy palm cover was observed over shorter forests, while the opposite was found over taller forests, where palms may not be visible from the canopy. Palm segments occurred more frequently at valleys but they were also observed in other landscapes, depending on site location and forest height. Our findings highlight the disproportional occurrence of palm cover in some Amazonian canopies. This fact should be taken into account to improve regional carbon cycle representation and promote initiatives of biodiversity conservation and bioeconomic use of these forests. (AU)

• Processo FAPESP: 18/15001-6 - ARBOLES: um entendimento da biodiversidade e resiliência das florestas LATAM baseado em características funcionais
• Beneficiário: Luiz Eduardo Oliveira e Cruz de Aragão
• Modalidade de apoio: Auxílio à Pesquisa - Regular
• Processo FAPESP: 19/09248-1 - Usando rede convolucional de aprendizado profundo para estimar atributos do dossel a partir de imagens de alta resolução
• Beneficiário: Annia Susin Streher
• Modalidade de apoio: Bolsas no Brasil - Programa Capacitação - Treinamento Técnico
• Processo FAPESP: 18/24017-3 - Desenvolvimento de novas ferramentas para o compartilhamento e reúso de dados através de pesquisa transnacional sobre o impacto socioeconômico das áreas protegidas (PARSEC)
• Beneficiário: Pedro Luiz Pizzigatti Corrêa
• Modalidade de apoio: Auxílio à Pesquisa - Regular
• Processo FAPESP: 19/21662-8 - Quantificando mortalidade de árvores com lasers: usando uma abordagem de fusão de dados e modelagem de última geração para estimar a perda de biomassa em florestas tropicais
• Beneficiário: Ricardo Dal'Agnol da Silva
• Modalidade de apoio: Bolsas no Brasil - Pós-Doutorado
• Processo FAPESP: 16/17652-9 - Diversidade funcional dos biomas Amazônia, Mata Atlântica e Cerrado nos ambientes intactos e em regeneração por meio de imagens hiperspectrais
• Beneficiário: Fabien Hubert Wagner
• Modalidade de apoio: Bolsas no Brasil - Jovens Pesquisadores