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 (Pará 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.