Shorebird nesting habitat at the Virginia Coast Reserve

Chapter 3 — how barrier island change shapes American Oystercatcher nesting habitat

At a glance

Question
How do barrier island morphology, vegetation, and human disturbance shape where American Oystercatchers nest, and how will geomorphic change alter that habitat over time?
Where
The barrier islands of the Virginia Coast Reserve Long Term Ecological Research (VCR LTER) site, on the Atlantic side of Virginia's Eastern Shore
Approach
Machine learning models of nesting habitat built from LiDAR topography, satellite imagery, and long-term nest monitoring
Data
LiDAR-derived topography, satellite imagery, long-term avian monitoring data, and field surveys
Collaborators
Virginia Coast Reserve LTER, Dr. Sarah Karpanty (Virginia Tech), The Nature Conservancy
Status
Getting started: shorebird habitat and geomorphic surveys on the reserve in 2025 (avian point counts, sediment cores, microclimate monitoring); results to come
Aerial imagery of the Virginia Coast Reserve barrier islands, labelled from Assawoman Island in the north to Fishermans Island in the south
(a) The barrier islands of the Virginia Coast Reserve, from Assawoman Island in the north to Fishermans Island at the mouth of the Chesapeake Bay. (b) The reserve (teal box) on the Mid-Atlantic coast. (c) American Oystercatchers, the focus of this chapter. Imagery: Esri World Imagery; island locations: © OpenStreetMap contributors.

This chapter will explore how barrier island morphology, vegetation, and human disturbance shape nesting habitat for the American Oystercatcher (Haematopus palliatus), a species of conservation concern along the Atlantic coast. I plan to develop a machine learning model to predict suitable nesting habitat across the Virginia Coast Reserve by integrating geospatial datasets, field surveys, and remotely sensed imagery.

Approach

The approach combines spatial analysis with predictive modeling to identify how geomorphic features (e.g., elevation, slope, island width), vegetation patterns (e.g., NDVI, habitat type), and proximity to anthropogenic features influence nest site selection, drawing on LiDAR-derived topography, satellite imagery, and long-term avian monitoring data, and comparing algorithms such as random forest and gradient boosting.

This work will contribute to the growing need for data-driven conservation tools that support habitat protection and adaptive management for coastal wildlife in the face of sea-level rise and landscape change.