The Neuse River Estuary (NRE), NC has been impacted by a significant portion of the extreme storms that have swept coastal North Carolina in the past three decades. Shoreline classification maps are critical to understanding the context and magnitude of storm-induced erosion along the NRE shoreline. This study assessed the ability of an object-based ensemble analysis to map natural and engineered shoreline types observed within the NRE. Object-based ensemble analysis has emerged as a successful framework to improve image classification but has yet to be tested in classifying an estuarine shoreline environment. This approach used in-situ reference data, high-resolution aerial imagery, and LiDAR point data to train an ensemble of five machine learning algorithms (Random Forest, Support Vector Machine, LibLINEAR, Artificial Neural Network, and k-Nearest Neighbors). The object-based ensemble produced the highest overall classification accuracy at 76.4% (Kappa value = 0.66), 6.3% higher than the top performing pixel-based model, justifying its use to produce the final shoreline classification map. The results of the object-based ensemble analysis were then used to assess shoreline change and erosion vulnerability and produced comparable erosion rates to those observed in past studies. This demonstrates that an object-based ensemble approach is an effective way to map shoreline classifications in the NRE and should continue to be explored within other shoreline management applications.

Date: April 14, 2022
Time: 10:30 -11 am
Place: https://ecu.webex.com/ecu/j.php?MTID=m3a40a39d91d53d68a52b95a0f2ab7b87
Meeting number: 2620 747 3807
Password: XesqWcPQ222 (93779277 from phones)
Join by phone: +1-415-655-0003 US Toll; Access code: 2620 747 3807
Advisor: Dr. Hannah Sirianni
Committee: Drs. Thad Wasklewicz, Yong Wang and Burrell Montz