The Ma-le'l Dunes are located at the upper end of the North Spit of Humboldt Bay, California and are home to a range of plant and animal species. The goal of this study was to determine which classification method is most accurate in identifying dune features when performed on a larger, more diverse area. The data sources used for this study were orthomosaic UAV image [2017] with 14 cm spatial resolution and NAIP image [2016] with 1 m spatial resolution. The dune feature classes were compared with two images using supervised, unsupervised and feature extraction classification methods and accuracy assessment was performed using 50 ground control points. The classified feature classes were beach grass, shore pine, other vegetation, sand, and water. Overall, the NAIP classified map showed a higher accuracy for all classification methods than the UAV classified map with 86% overall accuracy for supervised classification. A feature extraction method showed a low accuracy for both NAIP (46%) and UAV ortho classified images [30%]. Of the classified methods for the UAV orthomosiac image, unsupervised classification showed a high accuracy [44%]. The Ma-le'l dune habitats are more heterogeneous and some classes were overlapped (i.e. beach grass and sand) due to high microtopographic variation of the dune, causing less accuracy for the feature extraction method. Monitoring dune habitat and geomorphic change over time with UAV images is important in order to implement best management practices for species conservation and to mitigate coastal vulnerabilities.