@Article{SilvaWaEmStGaOmAr:2022:CaPaCo,
author = "Silva, Ricardo Dalagnol da and Wagner, Fabien Hubert and Emilio,
Thaise and Streher, Annia Susin and Galv{\~a}o, L{\^e}nio Soares
and Ometto, Jean Pierre Henry Balbaud and Arag{\~a}o, Luiz
Eduardo Oliveira e Cruz de",
affiliation = "{Instituto Nacional de Pesquisas Espaciais (INPE)} and {Instituto
Nacional de Pesquisas Espaciais (INPE)} and {Universidade Estadual
de Campinas (UNICAMP)} and {Instituto Nacional de Pesquisas
Espaciais (INPE)} and {Instituto Nacional de Pesquisas Espaciais
(INPE)} and {Instituto Nacional de Pesquisas Espaciais (INPE)} and
{Instituto Nacional de Pesquisas Espaciais (INPE)}",
title = "Canopy palm cover across the Brazilian Amazon forests mapped with
airborne LiDAR data and deep learning",
journal = "Remote Sensing in Ecology and Conservation",
year = "2022",
volume = "8",
number = "5",
pages = "601--614",
month = "Oct.",
keywords = "Airborne LiDAR, Amazon, biodiversity, deep learning, palm cover.",
abstract = "The Amazon region in Brazil contains c. 5% 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
(Par{\'a} 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.",
doi = "10.1002/rse2.264",
url = "http://dx.doi.org/10.1002/rse2.264",
issn = "2056-3485",
language = "en",
targetfile = "Remote Sens Ecol Conserv - 2022 - Dalagnol - Canopy palm cover
across the Brazilian Amazon forests mapped with airborne.pdf",
urlaccessdate = "2024, May 02"
}