Identification and Classification of Geographically Isolated Wetlands in North Alabama using Geographic Object Based Image Analysis (GeOBIA)

Abstract

Due to recent Supreme Court rulings there has been an increased interest in the isolated wetlands of the United States. These types of wetlands while generally smaller in extent than traditional wetlands serve vital ecological roles such as water quality regulation and as a habitat of biological diversity. This thesis focuses specifically on mapping of geographically isolated wetlands, or those that are separated from traditional wetlands by a given spatial extent, using Geographic Object Based Image Analysis (GeOBIA). GeOBIA is a type of remote sensing analysis that identifies objects and features present within both raster and vector datasets via automated methodologies. This type of analysis offers the opportunity to greatly increase the efficiency of what has traditionally been a very labor intensive process of manual photo-interpretation. This analysis resulted in the delineation of 26,424 areas within the study area as geographically isolated wetlands. These results were assessed for accuracy through both manual inspection of aerial imagery and field verification which yielded accuracies of 83.7% and 87.7% respectively.