A general deep learning model for bird detection in high-resolution airborne imagery.

Advances in artificial intelligence for computer vision hold great promise for increasing the scales at which ecological systems can be studied. The distribution and behavior of individuals is central to ecology, and computer vision using deep neural networks can learn to detect individual objects in imagery. However, developing supervised models for ecological monitoring is challenging because it requires large amounts of human-labeled training data, requires advanced technical expertise and computational infrastructure, and is prone to overfitting. This limits application across space and time. One solution is developing generalized models that can be applied across species and ecosystems. Using over 250,000 annotations from 13 projects from around the world, we develop a general bird detection model that achieves over 65% recall and 50% precision on novel aerial data without any local training despite differences in species, habitat, and imaging methodology. Fine-tuning this model with only 1000 local annotations increases these values to an average of 84% recall and 69% precision by building on the general features learned from other data sources. Retraining from the general model improves local predictions even when moderately large annotation sets are available and makes model training faster and more stable. Our results demonstrate that general models for detecting broad classes of organisms using airborne imagery are achievable. These models can reduce the effort, expertise, and computational resources necessary for automating the detection of individual organisms across large scales, helping to transform the scale of data collection in ecology and the questions that can be addressed.

A benchmark dataset for canopy crown detection and delineation in co-registered airborne RGB, LiDAR and hyperspectral imagery from the National Ecological Observation Network.

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.

A remote sensing derived data set of 100 million individual tree crowns for the National Ecological Observatory Network.

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.

Estimating individual-level plant traits at scale.

Functional ecology has increasingly focused on describing ecological communities based on their traits (measurable features affecting individuals' fitness and performance). Analyzing trait distributions within and among forests could significantly improve understanding of community composition and ecosystem function. Historically, data on trait distributions are generated by (1) collecting a small number of leaves from a small number of trees, which suffers from limited sampling but produces information at the fundamental ecological unit (the individual), or (2) using remote-sensing images to infer traits, producing information continuously across large regions, but as plots (containing multiple trees of different species) or pixels, not individuals. Remote-sensing methods that identify individual trees and estimate their traits would provide the benefits of both approaches, producing continuous large-scale data linked to biological individuals. We used data from the National Ecological Observatory Network (NEON) to develop a method to scale up functional traits from 160 trees to the millions of trees within the spatial extent of two NEON sites. The pipeline consists of three stages: (1) image segmentation, to identify individual trees and estimate structural traits; (2) an ensemble of models to infer leaf mass area (LMA), nitrogen, carbon, and phosphorus content using hyperspectral signatures, and DBH from allometry; and (3) predictions for segmented crowns for the full remote-sensing footprint at the NEON sites. The R2 values on held-out test data ranged from 0.41 to 0.75 on held-out test data. The ensemble approach performed better than single partial least-squares models. Carbon performed poorly compared to other traits (R2 of 0.41). The crown segmentation step contributed the most uncertainty in the pipeline, due to over-segmentation. The pipeline produced good estimates of DBH (R2 of 0.62 on held-out data). Trait predictions for crowns performed significantly better than comparable predictions on pixels, resulting in improvement of R2 on test data of between 0.07 and 0.26. We used the pipeline to produce individual-level trait data for ~5 million individual crowns, covering a total extent of ~360 km2 . This large data set allows testing ecological questions on landscape scales, revealing that foliar traits are correlated with structural traits and environmental conditions.

Capturing foraging and resting behavior using nested multivariate Markov models in an air-breathing marine vertebrate.

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.

Towards a predictive model of species interaction beta diversity.

Species interactions are fundamental to community dynamics and ecosystem processes. Despite significant progress in describing species interactions, we lack the ability to predict changes in interactions across space and time. We outline a Bayesian approach to separate the probability of species co-occurrence, interaction and detectability in influencing interaction betadiversity. We use a multi-year hummingbird-plant time series, divided into training and testing data, to show that including models of detectability and occurrence improves forecasts of mutualistic interactions. We then extend our model to explore interaction betadiversity across two distinct seasons. Despite differences in the observed interactions among seasons, there was no significant change in hummingbird occurrence or interaction frequency between hummingbirds and plants. These results highlight the challenge of inferring the causes of interaction betadiversity when interaction detectability is low. Finally, we highlight potential applications of our model for integrating observations of local interactions with biogeographic and evolutionary histories of co-occurring species. These advances will provide new insight into the mechanisms that drive variation in patterns of biodiversity.

A computer vision for animal ecology.

A central goal of animal ecology is to observe species in the natural world. The cost and challenge of data collection often limit the breadth and scope of ecological study. Ecologists often use image capture to bolster data collection in time and space. However, the ability to process these images remains a bottleneck. Computer vision can greatly increase the efficiency, repeatability and accuracy of image review. Computer vision uses image features, such as colour, shape and texture to infer image content. I provide a brief primer on ecological computer vision to outline its goals, tools and applications to animal ecology. I reviewed 187 existing applications of computer vision and divided articles into ecological description, counting and identity tasks. I discuss recommendations for enhancing the collaboration between ecologists and computer scientists and highlight areas for future growth of automated image analysis.

The role of environment, dispersal and competition in explaining reduced co-occurrence among related species.

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.

Dynamic foraging of a top predator in a seasonal polar marine environment.

The seasonal movement of animals at broad spatial scales provides insight into life-history, ecology and conservation. By combining high-resolution satellite-tagged data with hierarchical Bayesian movement models, we can associate spatial patterns of movement with marine animal behavior. We used a multi-state mixture model to describe humpback whale traveling and area-restricted search states as they forage along the West Antarctic Peninsula. We estimated the change in the geography, composition and characteristics of these behavioral states through time. We show that whales later in the austral fall spent more time in movements associated with foraging, traveled at lower speeds between foraging areas, and shifted their distribution northward and inshore. Seasonal changes in movement are likely due to a combination of sea ice advance and regional shifts in the primary prey source. Our study is a step towards dynamic movement models in the marine environment at broad scales.

Persistent bill and corolla matching despite shifting temporal resources in tropical hummingbird-plant interactions.

By specialising on specific resources, species evolve advantageous morphologies to increase the efficiency of nutrient acquisition. However, many specialists face variation in resource availability and composition. Whether specialists respond to these changes depends on the composition of the resource pulses, the cost of foraging on poorly matched resources, and the strength of interspecific competition. We studied hummingbird bill and plant corolla matching during seasonal variation in flower availability and morphology. Using a hierarchical Bayesian model, we accounted for the detectability and spatial overlap of hummingbird-plant interactions. We found that despite seasonal pulses of flowers with short-corollas, hummingbirds consistently foraged on well-matched flowers, leading to low niche overlap. This behaviour suggests that the costs of searching for rare and more specialised resources are lower than the benefit of switching to super-abundant resources. Our results highlight the trade-off between foraging efficiency and interspecific competition, and underline niche partitioning in maintaining tropical diversity.

Evaluating broad scale patterns among related species using resource experiments in tropical hummingbirds.

A challenge in community ecology is connecting biogeographic patterns with local scale observations. In Neotropical hummingbirds, closely related species often co-occur less frequently than expected (overdispersion) when compared to a regional species pool. While this pattern has been attributed to interspecific competition, it is important to connect these findings with local scale mechanisms of coexistence. We measured the importance of the presence of competitors and the availability of resources on selectivity at experimental feeders for Andean hummingbirds along a wide elevation gradient. Selectivity was measured as the time a bird fed at a feeder with a high sucrose concentration when presented with feeders of both low and high sucrose concentrations. Resource selection was measured using time-lapse cameras to identity which floral resources were used by each hummingbird species. We found that the increased abundance of preferred resources surrounding the feeder best explained increased species selectivity, and that related hummingbirds with similar morphology chose similar floral resources. We did not find strong support for direct agonism based on differences in body size or phylogenetic relatedness in predicting selectivity. These results suggest closely related hummingbird species have overlapping resource niches, and that the intensity of interspecific competition is related to the abundance of those preferred resources. If these competitive interactions have negative demographic effects, our results could help explain the pattern of phylogenetic overdispersion observed at regional scales.

Small unmanned aerial vehicles (micro-UAVs, drones) in plant ecology.

PREMISE OF THE STUDY: Low-elevation surveys with small aerial drones (micro-unmanned aerial vehicles [UAVs]) may be used for a wide variety of applications in plant ecology, including mapping vegetation over small- to medium-sized regions. We provide an overview of methods and procedures for conducting surveys and illustrate some of these applications. METHODS: Aerial images were obtained by flying a small drone along transects over the area of interest. Images were used to create a composite image (orthomosaic) and a digital surface model (DSM). Vegetation classification was conducted manually and using an automated routine. Coverage of an individual species was estimated from aerial images. RESULTS: We created a vegetation map for the entire region from the orthomosaic and DSM, and mapped the density of one species. Comparison of our manual and automated habitat classification confirmed that our mapping methods were accurate. A species with high contrast to the background matrix allowed adequate estimate of its coverage. DISCUSSION: The example surveys demonstrate that small aerial drones are capable of gathering large amounts of information on the distribution of vegetation and individual species with minimal impact to sensitive habitats. Low-elevation aerial surveys have potential for a wide range of applications in plant ecology.

Global mammal beta diversity shows parallel assemblage structure in similar but isolated environments.

The taxonomic, phylogenetic and trait dimensions of beta diversity each provide us unique insights into the importance of historical isolation and environmental conditions in shaping global diversity. These three dimensions should, in general, be positively correlated. However, if similar environmental conditions filter species with similar trait values, then assemblages located in similar environmental conditions, but separated by large dispersal barriers, may show high taxonomic, high phylogenetic, but low trait beta diversity. Conversely, we expect lower phylogenetic diversity, but higher trait biodiversity among assemblages that are connected but are in differing environmental conditions. We calculated all pairwise comparisons of approximately 110 × 110 km grid cells across the globe for more than 5000 mammal species (approx. 70 million comparisons). We considered realms as units representing geographical distance and historical isolation and biomes as units with similar environmental conditions. While beta diversity dimensions were generally correlated, we highlight geographical regions of decoupling among beta diversity dimensions. Our analysis shows that assemblages from tropical forests in different realms had low trait dissimilarity while phylogenetic beta diversity was significantly higher than expected, suggesting potential convergent evolution. Low trait beta diversity was surprisingly not found between isolated deserts, despite harsh environmental conditions. Overall, our results provide evidence for parallel assemblage structure of mammal assemblages driven by environmental conditions at a global scale.

Process-Based Species Pools Reveal the Hidden Signature of Biotic Interactions Amid the Influence of Temperature Filtering.

A persistent challenge in ecology is to tease apart the influence of multiple processes acting simultaneously and interacting in complex ways to shape the structure of species assemblages. We implement a heuristic approach that relies on explicitly defining species pools and permits assessment of the relative influence of the main processes thought to shape assemblage structure: environmental filtering, dispersal limitations, and biotic interactions. We illustrate our approach using data on the assemblage composition and geographic distribution of hummingbirds, a comprehensive phylogeny and morphological traits. The implementation of several process-based species pool definitions in null models suggests that temperature-but not precipitation or dispersal limitation-acts as the main regional filter of assemblage structure. Incorporating this environmental filter directly into the definition of assemblage-specific species pools revealed an otherwise hidden pattern of phylogenetic evenness, indicating that biotic interactions might further influence hummingbird assemblage structure. Such hidden patterns of assemblage structure call for a reexamination of a multitude of phylogenetic- and trait-based studies that did not explicitly consider potentially important processes in their definition of the species pool. Our heuristic approach provides a transparent way to explore patterns and refine interpretations of the underlying causes of assemblage structure.

Taxonomic, phylogenetic, and trait Beta diversity in South American hummingbirds.

Comparison of the taxonomic, phylogenetic, and trait dimensions of beta diversity may uncover the mechanisms that generate and maintain biodiversity, such as geographic isolation, environmental filtering, and convergent adaptation. We developed an approach to predict the relationship between environmental and geographic distance and the dimensions of beta diversity. We tested these predictions using hummingbird assemblages in the northern Andes. We expected taxonomic beta diversity to result from recent geographic barriers limiting dispersal, and we found that cost distance, which includes barriers, was a better predictor than Euclidean distance. We expected phylogenetic beta diversity to result from historical connectivity and found that differences in elevation were the best predictors of phylogenetic beta diversity. We expected high trait beta diversity to result from local adaptation to differing environments and found that differences in elevation were correlated with trait beta diversity. When combining beta diversity dimensions, we observe that high beta diversity in all dimensions results from adaption to different environments between isolated assemblages. Comparisons with high taxonomic, low phylogenetic, and low trait beta diversity occurred among lowland assemblages separated by the Andes, suggesting that geographic barriers have recently isolated lineages in similar environments. We provide insight into mechanisms governing hummingbird biodiversity patterns and provide a framework that is broadly applicable to other taxonomic groups.