 This paper reviews the current state of remote sensing research related to slum mapping. It finds that there is a lack of understanding of the contextual factors of slums, as well as a need for better physical slum characteristics to be identified. Additionally, the use of new technology has improved the ability to recognize objects in slums, but the complexity of their morphology makes it difficult to extract accurate information from these images. Finally, the paper suggests that texture-based methods are best suited for global slum mapping, while machine learning algorithms are most effective for local slum mapping. This article was authored by Monica Cuffer, Karen Pfeffer, and Richard Slyuses.