Search for: All records

Wildlife population monitoring over large geographic areas is increasingly feasible due to developments in aerial survey methods coupled with the use of computer vision models for identifying and classifying individual organisms. However, aerial surveys still occur infrequently, and there are often long delays between the acquisition of airborne imagery and its conversion into population monitoring data. Near real‐time monitoring is increasingly important for active management decisions and ecological forecasting. Accomplishing this over large scales requires a combination of airborne imagery, computer vision models to process imagery into information on individual organisms, and automated workflows to ensure that imagery is quickly processed into data following acquisition. Here we present our end‐to‐end workflow for conducting near real‐time monitoring of wading birds in the Everglades, Florida, USA. Imagery is acquired as frequently as weekly using uncrewed aircraft systems (aka drones), processed into orthomosaics (using Agisoft metashape), converted into individual‐level species data using a Retinanet‐50 object detector, post‐processed, archived, and presented on a web‐based visualization platform (using Shiny). The main components of the workflow are automated using Snakemake. The underlying computer vision model provides accurate object detection, species classification, and both total and species‐level counts for five out of six target species (White Ibis, Great Egret, Great Blue Heron, Wood Stork, and Roseate Spoonbill). The model performed poorly for Snowy Egrets due to the small number of labels and difficulty distinguishing them from White Ibis (the most abundant species). By automating the post‐survey processing, data on the populations of these species is available in near real‐time (<1 week from the date of the survey) providing information at the time scales needed for ecological forecasting and active management. 

A substantial increase in predictive capacity is needed to anticipate and mitigate the widespread change in ecosystems and their services in the face of climate and biodiversity crises. In this era of accelerating change, we cannot rely on historical patterns or focus primarily on long-term projections that extend decades into the future. In this Perspective, we discuss the potential of near-term (daily to decadal) iterative ecological forecasting to improve decision-making on actionable time frames. We summarize the current status of ecological forecasting and focus on how to scale up, build on lessons from weather forecasting, and take advantage of recent technological advances. We also highlight the need to focus on equity, workforce development, and broad cross-disciplinary and non-academic partnerships. 

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 km²shapefiles 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. 

Ecological Dynamics and Forecasting' is a semester-long course to introduce students to the fundamentals of ecological dynamics and forecasting. This course implements paper-based discussion to introduce students to concepts and ideas and R-based tutorials for hands-on application and training. The course material includes a reading list with prompting questions for discussions, teachers notes for guiding discussions, lecture notes for live coding demonstrations, and video presentations of all R tutorials. This course material can be used either as self-directed learning or as all or part of a college or university course. Individual learners have access to all of the necessary material - including discussion questions and instructor notes - on the website. The course focuses on papers with an open-access or free-to-read version where possible, though some materials still rely on access to closed-access papers. The course is structured around two sessions per week, with most weeks consisting of a one hour paper discussion session and a 1-2 hour session focused on applications in R. R tutorials use publicly available ecological datasets to provide realistic applications. Because the material is organized around content themes, instructors can modify and remix materials based on their course goals and student levels of background knowledge. These course materials have been taught for several years at the authors’ university and have also generated significant online engagement with course videos tens of thousands of times. 

Data on individual tree crowns from remote sensing have the potential to advance forest ecology by providing information about forest composition and structure with a continuous spatial coverage over large spatial extents. Classifying individual trees to their taxonomic species over large regions from remote sensing data is challenging. Methods to classify individual species are often accurate for common species, but perform poorly for less common species and when applied to new sites. We ran a data science competition to help identify effective methods for the task of classification of individual crowns to species identity. The competition included data from three sites to assess each methods’ ability to generalize patterns across two sites simultaneously and apply methods to an untrained site. Three different metrics were used to assess and compare model performance. Six teams participated, representing four countries and nine individuals. The highest performing method from a previous competition in 2017 was applied and used as a baseline to understand advancements and changes in successful methods. The best species classification method was based on a two-stage fully connected neural network that significantly outperformed the baseline random forest and gradient boosting ensemble methods. All methods generalized well by showing relatively strong performance on the trained sites (accuracy = 0.46–0.55, macro F1 = 0.09–0.32, cross entropy loss = 2.4–9.2), but generally failed to transfer effectively to the untrained site (accuracy = 0.07–0.32, macro F1 = 0.02–0.18, cross entropy loss = 2.8–16.3). Classification performance was influenced by the number of samples with species labels available for training, with most methods predicting common species at the training sites well (maximum F1 score of 0.86) relative to the uncommon species where none were predicted. Classification errors were most common between species in the same genus and different species that occur in the same habitat. Most methods performed better than the baseline in detecting if a species was not in the training data by predicting an untrained mixed-species class, especially in the untrained site. This work has highlighted that data science competitions can encourage advancement of methods, particularly by bringing in new people from outside the focal discipline, and by providing an open dataset and evaluation criteria from which participants can learn. 

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.