 This study compared three different methods for mapping mangroves in the Brisbane River area, southeast Queensland, Australia. The first method, spectral angle mapper, SAM, produced accurate class polygons with only a few unclassified pixels, overall accuracy of 69% and CAPA score of 0.57. The second method, linear spectral unmixing, LSU, produced a patchy polygon pattern with many unclassified pixels, overall accuracy of 56% and CAPA score of 0.41. Finally, the third method, object-based image analysis, O B I A, produced the most accurate results, overall accuracy of 76% and CAPA score of 0.67. The O B I A method combined a rule-based and nearest neighbor classification method, resulting in the highest overall accuracy. This article was authored by Muhammad Kamal and Stuart Finn.