Biology subjects

Frederick, P.

Publications and source records attributed to Frederick, P..

5 recordsLinked to original sources

bioRxiv2025

Using time-series remote sensing to identify and track individual bird nests at large scales

The challenges of monitoring wildlife often limits the scales and intensity of the data that can be collected. New technologies - such as remote sensing using unoccupied aircraft systems (UAS) - can collect information more quickly, over larger areas, and more frequently than is feasible using ground-based methods. While airborne imaging is increasingly used to produce data on the location and counts of individuals, its ability to produce individual-based demographic information is less explored. Repeat airborne imagery to generate an imagery time-series provides the potential to track individuals over time to collect information beyond one-off counts, but doing so necessitates automated approaches to handle the resulting high-frequency large-spatial scale imagery. We develop an automated time-series remote sensing approach to identifying wading bird nests in the Everglades ecosystem of Florida, USA to explore the feasibility and challenges of conducting time-series based remote sensing on mobile animals at large spatial scales. We combine a computer vision model for detecting birds in weekly UAS imagery of colonies with biology-informed algorithmic rules to generate an automated approach that identifies likely nests. Comparing the performance of these automated approaches to human assessment of the same imagery shows that our primary approach identifies nests with comparable performance to human photo assessment, and that a secondary approach designed to find quick-fail nests resulted in high false positive rates. We also assessed the ability of both human photo assessment and our primary algorithm to find ground-verified nests in UAS imagery and again found comparable performance, with the exception of nests that fail quickly. Our results show that automating nest detection, a key first step towards estimating nest success, is possible in complex environments like the Everglades and we discuss a number of challenges and possible uses for these types of approaches.

ecology↗

bioRxiv2024

Near real-time monitoring of long legged wading birds using uncrewed aircraft systems and computer vision

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.

ecology↗

bioRxiv2021

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 needs 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 increase 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.

ecology↗

bioRxiv2019

Partial migration in a subtropical wading bird in the Southeastern U.S.

The function of migration is to allow exploitation of resources whose availability is heterogeneous in space and time. Much effort has been historically directed to studying migration as a response to seasonal, predictable fluctuations in resource availability in temperate species. A deeper understanding of how different migration patterns emerge in response to different patterns of resource variation requires focusing on species inhabiting less predictable environments, especially in tropical and subtropical areas. We provide the first individual-based, quantitative description of migratory patterns in a subtropical wading bird in the Southeastern U.S., the wood stork (Mycteria americana). Using GPS tracking data for 64 individuals tracked between 2004 and 2017, we classified migratory behavior at the individual-year level using information theory-based model selection on non-linear models of net squared displacement. We found that the wood stork population is partially migratory, with 59% of individuals seasonally commuting between winter ranges in Florida and summer ranges elsewhere in the population range (migrants), and 28% remaining in a single area in Florida year-round (residents). Additionally, 13% of storks act as facultative migrants, migrating in some years but not in others. Comparing the distribution of residents and migrants suggests that different migratory strategies might be associated with the use of different or differently distributed resources, possibly including food supplementation from human activities. The existence of facultative migrants shows the potential for plastic change of migratory patterns. Partial migration in wood storks may be an adaptation to high heterogeneity and unpredictability of food resources. We suggest that future research should focus on wading birds as model species for the study of partial migration as an adaptation to heterogeneous and unpredictable environments, by comparing populations of the same species across different wetland systems and sympatric populations of species that differ in their resource acquisition mechanisms.

ecology↗

bioRxiv2019

EFFECT OF PARENTAL CARE ON REPRODUCTIVE SUCCESS IN WOOD STORKS (MYCTERIA AMERICANA)

In many species of birds, parental care is provided by both parents to maximize offspring survival, and there may be important trade-offs between maximizing food gathering and nest protection during the nesting period. The role of parental care in determining reproductive success was investigated in Wood Storks (Mycteria americana), and specifically how the trade-off between frequency and duration of foraging trips, and nest protection has contributed to the nesting outcome. Parental behavior of 85 pairs of Wood Storks was monitored throughout the nesting season in two breeding colonies in Palm Beach County, Florida. Wood Storks have gradually increased the frequency, but not the duration, of foraging trips as chicks developed. The ratio of hatchlings to fledglings was positively associated with the frequency of foraging trips during late chick development. Intra-specific aggressions resulting in nest takeovers have affected 32 % of the nests under study. Occurrence of nest takeovers have been higher for later-breeding pairs, and was happened primarily in the first few weeks of incubation, but was not affected by the degree of joint nest attendance of both parents. These results establish a functional link between parental effort and reproductive outcome in Wood Storks, and highlight the importance of frequent foraging trips, but not nest attendance, by parents.Competing Interest StatementThe authors have declared no competing interest.View Full Text

zoology↗