Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher.
Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?
Some links on this page may take you to non-federal websites. Their policies may differ from this site.
-
Amazon forests are characterized by rich structural diversity. However, the influence of factors such as topography, soil attributes, and external disturbances on structural variability is not always well characterized, and traditional structural metrics may be inadequate to capture this type of complexity. While LiDAR offers expanded structural insights, traditional parameters used in LiDAR analysis, such as mean or maximum canopy height, are not always well directly linked to environmental variables like topography. Emerging approaches merge LiDAR with machine learning to uncover deeper structural complexities. However, work to date may fail to fully utilize the potential of fine-scale LiDAR information. Here we introduce a novel approach, leveraging 2D point cloud images derived from a profiling canopy LiDAR (PCL). The technique targets intricate details within LiDAR point clouds by using deep learning algorithms. With a dataset from the Central Amazon comprising 18 multitemporal transects of 450 m in length, our objective was to detect structural "fingerprints" of varied topographical types along a hillslope, comprising: Riparian, White-sand, and Plateau, and to detect any gradient of structural shifts based on terrain variations here represented by the height above the nearest drainage (HAND). The dataset was trained and tested using a leave-one-group-out approach (LOGO) in which, for each iteration, a complete 450 m multitemporal transect was excluded from training and tested after each iteration. The fast.ai platform and a ResNet-34 architecture, coupled with transfer learning, were used to perform a classification to distinguish between three topographical types. Furthermore, a hybrid model combining a Convolutional Autoencoder, and Partial Least Square (PLS) regression was designed to detect forest structural gradient correlations with HAND variation. Cross-validation achieved a promising high weighted F1 score of 0.83 to classify forests based on the topographical types. Additionally, a combined Convolutional Autoencoder and PLS regression revealed a strong correlation (R2 = 0.76) between actual and predicted HAND. Innovatively combining deep learning with ground-based PCL LiDAR, our study revealed unique Amazon Forest structures connected to topographic variation. Our findings underscore the transformative potential of such integrative approaches for investigating forest dynamics and promise a powerful new tool for understanding climate-related forest structure change.more » « lessFree, publicly-accessible full text available July 1, 2025
-
Free, publicly-accessible full text available June 19, 2025
-
Abstract. In humid tropical regions, irregular illumination and cloud shadows can complicate near-surface optical remote sensing. This could lead to costly and repetitive surveys to maintain geographical and spectral consistency. This could have a significant impact on the regular monitoring of forest ecosystems. A novel correction method using deep learning is presented here to address the issue in high-resolution canopy images. Our method involves training a deep learning model on one or a few well-illuminated/homogeneous reference images augmented with artificially generated cloud shadows. This training enables the model to predict illumination and cloud shadow patterns in any image and ultimately mitigate these effects. Using images captured by multispectral and RGB cameras, we evaluated the method across multiple sensors and conditions. These included nadir-view images from two sensors mounted on a drone and tower-mounted RGB Phenocams. The technique effectively corrects uneven illumination in near-infrared and true-color RGB images, including non-forested areas. This improvement was also evident in more consistent normalized difference vegetation index (NDVI) patterns in areas affected by uneven illumination. By comparing corrected RGB images to the original in a binary classification task, we evaluated the method's accuracy and Kappa values. Our goal was to detect non-photosynthetic vegetation (NPV) in a mosaic. The overall accuracy and Kappa were both significantly improved in corrected images, with a 2.5% and 1.1% increase, respectively. Moreover, the method can be generalized across sensors and conditions. Further work should focus on refining the technique and exploring its applicability to satellite imagery and beyond.
-
Abstract Predictions of the magnitude and timing of leaf phenology in Amazonian forests remain highly controversial. Here, we use terrestrial LiDAR surveys every two weeks spanning wet and dry seasons in Central Amazonia to show that plant phenology varies strongly across vertical strata in old-growth forests, but is sensitive to disturbances arising from forest fragmentation. In combination with continuous microclimate measurements, we find that when maximum daily temperatures reached 35 °C in the latter part of the dry season, the upper canopy of large trees in undisturbed forests lost plant material. In contrast, the understory greened up with increased light availability driven by the upper canopy loss, alongside increases in solar radiation, even during periods of drier soil and atmospheric conditions. However, persistently high temperatures in forest edges exacerbated the upper canopy losses of large trees throughout the dry season, whereas the understory in these light-rich environments was less dependent on the altered upper canopy structure. Our findings reveal a strong influence of edge effects on phenological controls in wet forests of Central Amazonia.more » « less
-
With deforestation and associated fires ongoing at high rates, and amidst urgent need to preserve Amazonia, improving the understanding of biomass burning emissions drivers is essential. The use of orbital remote sensing data enables the estimate of both biomass burning emissions and deforestation. In this study, we have estimated emissions of particulate matter with diameter less than 2.5 µm (PM2.5) associated with biomass burning, a primary human health risk, using the Brazilian Biomass Burning emission model with Fire Radiative Power (3BEM_FRP), and estimated deforestation based on the MapBiomas dataset. Using these estimates, we have assessed for the first time how deforestation drove biomass burning emissions in Amazonia over the last two decades at three scales of analysis: Amazonia-wide, country/state and pixel. Amazonia accounted for 48% of PM2.5 emitted from biomass burning in South America and current deforestation rates have reached values on par with those of the early 21st Century. Emissions and deforestation were concentrated in the Eastern and Central-Southern portions of Amazonia. Amazonia-wide deforestation and emissions were linked through time (R = 0.65). Countries/states with the widest spread agriculture were less likely to be correlated at this scale, likely because of the importance of biomass burning in agricultural practices. Concentrated in regions of ongoing deforestation, in 18% of Amazonia grid cells PM2.5 emissions associated with biomass burning and deforestation were significantly positively correlated. Deforestation is an important driver of emissions in Amazonia but does not explain biomass burning alone. Therefore, future work must link climate and other non-deforestation drivers to completely understand biomass burning emissions in Amazonia. The advance of anthropogenic activities over forested areas, which ultimately leads to more fires and deforestation, is expected to continue, worsening a crisis of dangerous emissions.more » « less