MACHINE LEARNING APPROACH TO COASTAL LANDFORM CLASSIFICATION

The resiliency of a barrier island, its ability to return to form and ecological function after storms, is important for our understanding of sea level rise and changes in storm activity. Topographic complexity provides insight to the complex nature of processes and sediment supply and is critical for assessing how barrier islands recover and evolve through time. Foredune, secondary dune, beach, and backbarrier entity identification is an important factor to determine the response of a barrier island, though the process for landform segmentation is difficult to quantify objectively. The purpose of this research is to generate a model to identify the position of foredune, secondary dune, beach, and backbarrier landforms using artificial neural networks. Sample data from Padre National Seashore is presented. Variables derived from a digital elevation model and vegetation are used as inputs to train the model using a portion of the study site, while the remainder of the site is used to test the model. Model results are qualitatively assessed for accuracy and demonstrate that it is possible to extract coastal landform features can be identified using a non-subjective approach. The machine learning methodology outlined here is feasible and useful for identifying foredune, secondary dune, beach, and backbarrier entities from different coastal variables, and nonlinearities between these variables can be used to explain alongshore variation in these coastal landforms. This machine learning paradigm has the potential to advance our understanding of barrier island geomorphology and resiliency.