Authors: Jacob Lehner*, University of Windsor, Phillipe Wernette, University of Windsor, Chris Houser, University of Windsor
Topics: Quantitative Methods, Coastal and Marine, Geomorphology
Keywords: Geomorphology, Machine Learning, Coastal
Session Type: Poster
Start / End Time: 1:20 PM / 3:00 PM
Room: Napoleon Foyer/Common St. Corridor, Sheraton, 3rd Floor
Presentation File: No File Uploaded
The resiliency of a barrier island, its ability to return to form and ecological function after storms, is of key scientific importance with future climate change and sea level rise. Foredune elevation, width, and extent are important factors that determine the response of a barrier island, though the underlying controls of these alongshore variations are not fully understood. Topographic complexity of barrier islands provides an insight to the complex nature of processes and sediment supply and is critical for assessing how barrier islands recover and evolve through time. The purpose of this research is to generate a model to predict foredune crest elevation through quantifying relationships between dune morphometrics, offshore bathymetry, and subsurface geology. The method presented is an evolutionary neural network for a subsection of Padre Island National Seashore. Dune morphometrics are extracted using an automated relative relief approach and used alongside bathymetric and subsurface data to train the model using a portion of the study site, the remainder of the site is used to test the model. Results demonstrate that this methodology is feasible and useful for predicting dune crest elevation from different coastal variables, and nonlinearities between these input variables can be used to explain alongshore variation in dune crest elevation. Accurately predicting dune crest elevation while providing a clear connection to the controlling variables, requires additional inputs to generate a more simplistic and more accurate model. Machine learning has the potential to advance our understanding of barrier island geomorphology and resiliency.