 Remote sensing has been found to be an effective tool in detecting earthquake damage. Multilayer feedforward neural networks, radial basis neural networks, and random forests have all been evaluated for their ability to accurately classify images from the 2010 portal, Prince, Haiti earthquake. Textural and structural features such as entropy, dissimilarity, laplacian of Gaussian, and rectangular fit were also examined. These algorithms achieved nearly a 90% kernel density match when validated against unitar slash unosat data. The multilayer feedforward network was able to achieve an error rate below 40% while spectral features were not as important. This suggests that future implementations of machine learning algorithms could benefit from using panchromatic or pan sharpened imagery alone. This article was authored by Austin J. Cooner, Young Xiao, and James B. Campbell.