Search

California forests have recently experienced record breaking wildfires and tree mortality from droughts, However, there is inadequate monitoring, and limited data to inform policies and management strategies across the state. Although forest surveys and satellite observations of forest cover changes exist at medium to coarse resolutions (30-500 m) annually, they remain less effective in mapping small disturbances of forest patches (<5m) occurring multiple times a year. We introduce a novel method of tracking California forest cover using a supervised U-Net deep learning architecture and PlanetScope's Visual dataset which provides 3-band RGB (Red, Green, and Blue) mosaicked imagery. We created labels of forest and non-forest to train the U-Net model to map tree cover based on a semi-unsupervised classification method. We then detected changes of tree cover and disturbance with the U-Net model, achieving an overall accuracy of 98.97% over training data set, and 95.5% over an independent validation dataset, obtaining a precision of 82%, and a recall of 74%. With the predicted tree cover mask, we created wall to wall monthly tree cover maps over California at 4.77 m resolution for 2020, 2021, and 2022. These maps were then aggregated in a postprocessing step to develop annual maps of disturbance, while accounting for the time of disturbance and other confounding factors such as topography, phenological and snow cover variability. We compared our high-resolution disturbance maps with wildfire GIS survey data from CALFIRE, and satellitebased forest cover changes and achieved an F-1 score of 54% and 88% respectively. The results suggest that high-resolution maps capture variability of forest disturbance and fire that wildfire surveys and medium resolution satellite products cannot. From 2020 to 2021, California maintained 30,923.5 sq km of forest while 5,994.9 sq km were disturbed. The highest observed forest loss rate was located at the Sierra Nevada mountains at 21.4% of the forested area being disturbed between 2020 and 2021. Our findings highlight the strong potential of deep learning and high-resolution RGB optical imagery for mapping complex forest ecosystems and their changes across California, as well as the application of these techniques on a national to global scale. [ABSTRACT FROM AUTHOR]

The Amazon, the world's largest rainforest, faces a severe historic drought. The Rio Negro River, one of the major Amazon River tributaries, reached its lowest level in a century in October 2023. Here, we used a U-net deep learning model to map water surfaces in the Rio Negro River basin every 12 days in 2022 and 2023 using 10 m spatial resolution Sentinel-1 satellite radar images. The accuracy of the water surface model was high, with an F1-score of 0.93. A 12-day mosaic time series of the water surface was generated from the Sentinel-1 prediction. The water surface mask demonstrated relatively consistent agreement with the global surface water (GSW) product from the Joint Research Centre (F1-score: 0.708) and with the Brazilian MapBiomas Water initiative (F1-score: 0.686). The main errors of the map were omission errors in flooded woodland, in flooded shrub, and because of clouds. Rio Negro water surfaces reached their lowest level around the 25th of November 2023 and were reduced to 68.1% (9559.9 km2) of the maximum water surfaces observed in the period 2022–2023 (14,036.3 km2). Synthetic aperture radar (SAR) data, in conjunction with deep learning techniques, can significantly improve near-real-time mapping of water surfaces in tropical regions. [ABSTRACT FROM AUTHOR]

Natural disturbances like hurricanes can cause extensive disorder in forest structure, composition, and succession. Consequently, ecological, social, and economic alterations may occur. Terrestrial laser scanning (TLS) and deep learning have been used for estimating forest attributes with high accuracy, but to date, no study has combined both TLS and deep learning for assessing the impact of hurricane disturbance at the individual tree level. Here, we aim to assess the capability of TLS and convolutional neural networks (CNNs) combined for classifying post-Hurricane Michael damage severity at the individual tree level in a pine-dominated forest ecosystem in the Florida Panhandle, Southern U.S. We assessed the combined impact of using either binary-color or multicolored-by-height TLS-derived 2D images along with six CNN architectures (Densenet201, EfficientNet_b7, Inception_v3, Res-net152v2, VGG16, and a simple CNN). The confusion matrices used for assessing the overall accuracy were symmetric in all six CNNs and 2D image variants tested with overall accuracy ranging from 73% to 92%. We found higher F-1 scores when classifying trees with damage severity varying from extremely leaning, trunk snapped, stem breakage, and uprooted compared to trees that were undamaged or slightly leaning (<45°). Moreover, we found higher accuracies when using VGG16 combined with multicolored-by-height TLS-derived 2D images compared with other methods. Our findings demonstrate the high capability of combining TLS with CNNs for classifying post-hurricane damage severity at the individual tree level in pine forest ecosystems. As part of this work, we developed a new open-source R package (rTLsDeep) and implemented all methods tested herein. We hope that the promising results and the rTLsDeep R package developed in this study for classifying post-hurricane damage severity at the individual tree level will stimulate further research and applications not just in pine forests but in other forest types in hurricane-prone regions. [ABSTRACT FROM AUTHOR]

Monitoring changes in tree cover for assessment of deforestation is a premise for policies to reduce carbon emission in the tropics. Here, a U-net deep learning model was used to map monthly tropical tree cover in the Brazilian state of Mato Grosso between 2015 and 2021 using 5 m spatial resolution Planet NICFI satellite images. The accuracy of the tree cover model was extremely high, with an F1-score >0.98, further confirmed by an independent LiDAR validation showing that 95% of tree cover pixels had a height >5 m while 98% of non-tree cover pixels had a height <5 m. The biannual map of deforestation was then built from the monthly tree cover map. The deforestation map showed relatively consistent agreement with the official deforestation map from Brazil (67.2%) but deviated significantly from Global Forest Change (GFC)'s year of forest loss, showing that our product is closest to the product made by visual interpretation. Finally, we estimated that 14.8% of Mato Grosso's total area had undergone clear-cut logging between 2015 and 2021, and that deforestation was increasing, with December 2021, the last date, being the highest. High-resolution imagery from Planet NICFI in conjunction with deep learning techniques can significantly improve the mapping of deforestation extent in tropical regions. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

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. • Our study employs deep learning on LiDAR-derived 2D point cloud images, presenting a novel application in forest ecology. • We identified unique forest structural 'fingerprints' along a topographical gradient in the Central Amazon. • We showcase machine learning's effectiveness in extracting "hidden" forest structural information from complex LiDAR data. [ABSTRACT FROM AUTHOR]

Tropical rainforests from the Brazilian Amazon are frequently degraded by logging, fire, edge effects and minor unpaved roads. However, mapping the extent of degradation remains challenging because of the lack of frequent high-spatial resolution satellite observations, occlusion of understory disturbances, quick recovery of leafy vegetation, and limitations of conventional reflectance-based remote sensing techniques. Here, we introduce a new approach to map forest degradation caused by logging, fire, and road construction based on deep learning (DL), henceforth called DL-DEGRAD, using very high spatial (4.77 m) and bi-annual to monthly temporal resolution of the Planet NICFI imagery. We applied DL-DEGRAD model over forests of the state of Mato Grosso in Brazil to map forest degradation with attributions from 2016 to 2021 at six-month intervals. A total of 73,744 images (256 × 256 pixels in size) were visually interpreted and manually labeled with three semantic classes (logging, fire, and roads) to train/validate a U-Net model. We predicted the three classes over the study area for all dates, producing accumulated degradation maps biannually. Estimates of accuracy and areas of degradation were performed using a probability design-based stratified random sampling approach (n = 2678 samples) and compared it with existing operational data products at the state level. DL-DEGRAD performed significantly better than all other data products in mapping logging activities (F 1 -score = 68.9) and forest fire (F 1 -score = 75.6) when compared with the Brazil's national maps (SIMEX, DETER, MapBiomas Fire) and global products (UMD-GFC, TMF, FireCCI, FireGFL, GABAM, MCD64). Pixel-based spatial comparison of degradation areas showed the highest agreement with DETER and SIMEX as Brazil official data products derived from visual interpretation of Landsat imagery. The U-Net model applied to NICFI data performed as closely to a trained human delineation of logged and burned forests, suggesting the methodology can readily scale up the mapping and monitoring of degraded forests at national to regional scales. Over the state of Mato Grosso, the combined effects of logging and fire are degrading the remaining intact forests at an average rate of 8443 km2 year−1 from 2017 to 2021. In 2020, a record degradation area of 13,294 km2 was estimated from DL-DEGRAD, which was two times the areas of deforestation. • Mapping forest degradation is a major gap for carbon emissions in tropical forests. • Here we train a deep learning model using Planet NICFI data to map degradation. • The U-Net model segments degraded forests due to logging, fire, and roads. • Our maps show the highest overlap with official Brazilian data from DETER and SIMEX. • This novel approach provides mapping and attribution of tropical forest degradation. [ABSTRACT FROM AUTHOR]

Mapping plant species at the regional scale to provide information for ecologists and forest managers is a challenge for the remote sensing community. Here, we use a deep learning algorithm called U-net and very high-resolution multispectral images (0.5 m) from GeoEye satellite to identify, segment and map canopy palms over ∼3000 km 2 of Amazonian forest. The map was used to analyse the spatial distribution of canopy palm trees and its relation to human disturbance and edaphic conditions. The overall accuracy of the map was 95.5% and the F1-score was 0.7. Canopy palm trees covered 6.4% of the forest canopy and were distributed in more than two million patches that can represent one or more individuals. The density of canopy palms is affected by human disturbance. The post-disturbance density in secondary forests seems to be related to the type of disturbance, being higher in abandoned pasture areas and lower in forests that have been cut once and abandoned. Additionally, analysis of palm trees' distribution shows that their abundance is controlled naturally by local soil water content, avoiding both flooded and waterlogged areas near rivers and dry areas on the top of the hills. They show two preferential habitats, in the low elevation above the large rivers, and in the slope directly below the hill tops. Overall, their distribution over the region indicates a relatively pristine landscape, albeit within a forest that is critically endangered because of its location between two deforestation fronts and because of illegal cutting. New tree species distribution data, such as the map of all adult canopy palms produced in this work, are urgently needed to support Amazon species inventory and to understand their distribution and diversity. [ABSTRACT FROM AUTHOR]

Tropical forests concentrate the largest diversity of species on the planet and play a key role in maintaining environmental processes. Due to the importance of those forests, there is growing interest in mapping their components and getting information at an individual tree level to conduct reliable satellite-based forest inventory for biomass and species distribution qualification. Individual tree crown information could be manually gathered from high resolution satellite images; however, to achieve this task at large-scale, an algorithm to identify and delineate each tree crown individually, with high accuracy, is a prerequisite. In this study, we propose the application of a convolutional neural network—Mask R-CNN algorithm—to perform the tree crown detection and delineation. The algorithm uses very high-resolution satellite images from tropical forests. The results obtained are promising—the R e c a l l , P r e c i s i o n , and F 1 score values obtained were were 0.81 , 0.91 , and 0.86 , respectively. In the study site, the total of tree crowns delineated was 59,062 . These results suggest that this algorithm can be used to assist the planning and conduction of forest inventories. As the algorithm is based on a Deep Learning approach, it can be systematically trained and used for other regions. [ABSTRACT FROM AUTHOR]