 This study compared two popular machine learning algorithms, support vector machines, SVM, and random forests, RF, to identify tree species in two different forests. Both algorithms performed well with overall accuracy rates exceeding 90%, regardless of whether they were trained with object or pixel-based samples. Additionally, no significant differences were observed between the two algorithms when using object-based training samples. However, when more training samples were available, SVM outperformed RF. Furthermore, increasing the size of the object selected for classification improved the performance of both algorithms. This article was authored by Laurel Ballanti, Leonard Blegius, Ellen Hines, and others.