 Efforts are increasingly being made to classify the world's wetland resources, an important ecosystem and habitat that is diminishing in abundance. Non-parametric machine learning algorithms such as Decision Tree, DT, Rule Based, RB, and Random Forest, RF, have been used to classify these wetlands. High resolution satellite imagery can provide more specificity to the classified and product, and ancillary data layers such as the Normalized Difference Vegetation Index, and Hydrogeomorphic Layers such as Distance to a Stream can be coupled to improve overall accuracy, OA, in wetland studies. In this paper, we compared three non-parametric machine learning algorithms, DT, RB, and RF, using a large field-based dataset, and equals 228, from the Selengah River Delta of Lake Baikal, Russia. We also explored the use of ancillary data layers selected to improve OA, with a goal of providing end users with a recommended classifier to use and the most parsimonious suite of input parameters for classifying wetland-dominated landscapes. Though all classifiers appeared suitable. This article was authored by Tedros Embarhani, Charles Elaine, Chosheng Wu, and others. We are article.tv, links in the description below.