Search

Abstract Measuring forest biodiversity using terrestrial surveys is expensive and can only capture common species abundance in large heterogeneous landscapes. In contrast, combining airborne imagery with computer vision can generate individual tree data at the scales of hundreds of thousands of trees. To train computer vision models, ground‐based species labels are combined with airborne reflectance data. Due to the difficulty of finding rare species in a large landscape, many classification models only include the most abundant species, leading to biased predictions at broad scales. For example, if only common species are used to train the model, this assumes that these samples are representative across the entire landscape. Extending classification models to include rare species requires targeted data collection and algorithmic improvements to overcome large data imbalances between dominant and rare taxa. We use a targeted sampling workflow to the Ordway Swisher Biological Station within the US National Ecological Observatory Network (NEON), where traditional forestry plots had identified six canopy tree species with more than 10 individuals at the site. Combining iterative model development with rare species sampling, we extend a training dataset to include 14 species. Using a multi‐temporal hierarchical model, we demonstrate the ability to include species predicted at

Supervised methods for object delineation in remote sensing require labeled ground-truth data. Gathering sufficient high quality ground-truth data is difficult, especially when targets are of irregular shape or difficult to distinguish from background or neighboring objects. Tree crown delineation provides key information from remote sensing images for forestry, ecology, and management. However, tree crowns in remote sensing imagery are often difficult to label and annotate due to irregular shape, overlapping canopies, shadowing, and indistinct edges. There are also multiple approaches to annotation in this field (e.g., rectangular boxes vs. convex polygons) that further contribute to annotation imprecision. However, current evaluation methods do not account for this uncertainty in annotations, and quantitative metrics for evaluation can vary across multiple annotators. In this article, we address these limitations by developing an adaptation of the Rand index (RI) for weakly labeled crown delineation that we call RandCrowns (RC). Our new RC evaluation metric provides a method to appropriately evaluate delineated tree crowns while taking into account imprecision in the ground-truth delineations. The RC metric reformulates the RI by adjusting the areas over which each term of the index is computed to account for uncertain and imprecise object delineation labels. Quantitative comparisons to the commonly used intersection over union method show a decrease in the variance generated by differences among multiple annotators. Combined with qualitative examples, our results suggest that the RC metric is more robust for scoring target delineations in the presence of uncertainty and imprecision in annotations that are inherent to tree crown delineation.

Abstract Background Matching animal movement with the behaviors that shape life history requires a rigorous connection between the observed patterns of space use and inferred behavioral states. As animal-borne dataloggers capture a greater diversity and frequency of three dimensional movements, we can increase the complexity of movement models describing animal behavior. One challenge in combining data streams is the different spatial and temporal frequency of observations. Nested movement models provide a flexible framework for gleaning data from long-duration, but temporally sparse, data sources. Results Using a two-layer nested model, we combined geographic and vertical movement to infer traveling, foraging and resting behaviors of Humpback whales off the West Antarctic Peninsula. This approach refined previous work using only geographic data to delineate coarser behavioral states. Our results showed increased intensity in foraging activity in late season animals as the whales prepared to migrate north to tropical calving grounds. Our model also suggests strong diel variation in movement states, likely linked to daily changes in prey distribution. Conclusions Using a combination of two-dimensional and three-dimensional movement data, we highlight the connection between whale movement and krill availability, as well as the complex spatial pattern of whale foraging in productive polar waters.

Remote sensing can transform the speed, scale, and cost of biodiversity and forestry surveys. Data acquisition currently outpaces the ability to identify individual organisms in high resolution imagery. We outline an approach for identifying tree-crowns in RGB imagery while using a semi-supervised deep learning detection network. Individual crown delineation has been a long-standing challenge in remote sensing and available algorithms produce mixed results. We show that deep learning models can leverage existing Light Detection and Ranging (LIDAR)-based unsupervised delineation to generate trees that are used for training an initial RGB crown detection model. Despite limitations in the original unsupervised detection approach, this noisy training data may contain information from which the neural network can learn initial tree features. We then refine the initial model using a small number of higher-quality hand-annotated RGB images. We validate our proposed approach while using an open-canopy site in the National Ecological Observation Network. Our results show that a model using 434,551 self-generated trees with the addition of 2848 hand-annotated trees yields accurate predictions in natural landscapes. Using an intersection-over-union threshold of 0.5, the full model had an average tree crown recall of 0.69, with a precision of 0.61 for the visually-annotated data. The model had an average tree detection rate of 0.82 for the field collected stems. The addition of a small number of hand-annotated trees improved the performance over the initial self-supervised model. This semi-supervised deep learning approach demonstrates that remote sensing can overcome a lack of labeled training data by generating noisy data for initial training using unsupervised methods and retraining the resulting models with high quality labeled data.

Forests provide biodiversity, ecosystem, and economic services. Information on individual trees is important for understanding forest ecosystems but obtaining individual-level data at broad scales is challenging due to the costs and logistics of data collection. While advances in remote sensing techniques allow surveys of individual trees at unprecedented extents, there remain technical challenges in turning sensor data into tangible information. Using deep learning methods, we produced an open-source data set of individual-level crown estimates for 100 million trees at 37 sites across the United States surveyed by the National Ecological Observatory Network’s Airborne Observation Platform. Each canopy tree crown is represented by a rectangular bounding box and includes information on the height, crown area, and spatial location of the tree. These data have the potential to drive significant expansion of individual-level research on trees by facilitating both regional analyses and cross-region comparisons encompassing forest types from most of the United States.

The composition of ecological assemblages depends on a variety of factors including environmental filtering, biotic interactions and dispersal limitation. By evaluating the phylogenetic pattern of assemblages, we gain insight into the relative contribution of these mechanisms to generating observed assemblages. We address some limitations in the field of community phylogenetics by using simulations, biologically relevant null models, and cost distance analysis to evaluate simultaneous mechanisms leading to observed patterns of co-occurrence. Building from past studies of phylogenetic community structure, we applied our approach to hummingbird assemblages in the Northern Andes. We compared the relationship between relatedness and co-occurrence among predicted assemblages, based on estimates of suitable habitat and dispersal limitation, and observed assemblages. Hummingbird co-occurrence peaked at intermediate relatedness and decreased when a closely-related species was present. This result was most similar to simulations that included simultaneous effects of phylogenetic conservatism and repulsion. In addition, we found older sister taxa were only weakly more separated by geographic barriers, suggesting that time since dispersal is unlikely to be the sole factor influencing co-occurrence of closely related species. Our analysis highlights the role of multiple mechanisms acting simultaneously, and provides a hypothesis for the potential importance of competition at regional scales.

The ecology of forest ecosystems depends on the composition of trees. Capturing fine-grained information on individual trees at broad scales provides a unique perspective on forest ecosystems, forest restoration, and responses to disturbance. Individual tree data at wide extents promises to increase the scale of forest analysis, biogeographic research, and ecosystem monitoring without losing details on individual species composition and abundance. Computer vision using deep neural networks can convert raw sensor data into predictions of individual canopy tree species through labeled data collected by field researchers. Using over 40,000 individual tree stems as training data, we create landscape-level species predictions for over 100 million individual trees across 24 sites in the National Ecological Observatory Network (NEON). Using hierarchical multi-temporal models fine-tuned for each geographic area, we produce open-source data available as 1 km2 shapefiles with individual tree species prediction, as well as crown location, crown area, and height of 81 canopy tree species. Site-specific models had an average performance of 79% accuracy covering an average of 6 species per site, ranging from 3 to 15 species per site. All predictions are openly archived and have been uploaded to Google Earth Engine to benefit the ecology community and overlay with other remote sensing assets. We outline the potential utility and limitations of these data in ecology and computer vision research, as well as strategies for improving predictions using targeted data sampling.

Broad scale remote sensing promises to build forest inventories at unprecedented scales. A crucial step in this process is to associate sensor data into individual crowns. While dozens of crown detection algorithms have been proposed, their performance is typically not compared based on standard data or evaluation metrics. There is a need for a benchmark dataset to minimize differences in reported results as well as support evaluation of algorithms across a broad range of forest types. Combining RGB, LiDAR and hyperspectral sensor data from the USA National Ecological Observatory Network's Airborne Observation Platform with multiple types of evaluation data, we created a benchmark dataset to assess crown detection and delineation methods for canopy trees covering dominant forest types in the United States. This benchmark dataset includes an R package to standardize evaluation metrics and simplify comparisons between methods. The benchmark dataset contains over 6,000 image-annotated crowns, 400 field-annotated crowns, and 3,000 canopy stem points from a wide range of forest types. In addition, we include over 10,000 training crowns for optional use. We discuss the different evaluation data sources and assess the accuracy of the image-annotated crowns by comparing annotations among multiple annotators as well as overlapping field-annotated crowns. We provide an example submission and score for an open-source algorithm that can serve as a baseline for future methods.