The Andes mountain forests are sparse relict populations of tree species that grow in association with local native shrubland species. The identification of forest conditions for conservation in areas such as these is based on remote sensing techniques and classification methods. However, the classification of Andes mountain forests is difficult because of noise in the reflectance data within land cover classes. The noise is the result of variations in terrain illumination resulting from complex topography and the mixture of different land cover types occurring at the sub-pixel level. Considering these issues, the selection of an optimum classification method to obtain accurate results is very important to support conservation activities. We carried out comparative non-parametric statistical analyses on the performance of several classifiers produced by three supervised machine-learning algorithms: Random Forest (RF), Support Vector Machine (SVM), and k-Nearest Neighbor (kNN). The SVM and RF methods were not significantly different in their ability to separate Andes mountain forest and shrubland land cover classes, and their best classifiers showed a significantly better classification accuracy (AUC values 0.81 and 0.79 respectively) than the one produced by the kNN method (AUC value 0.75) because the latter was more sensitive to noisy training data.