Putting a cart before the search: Successful habitat prediction for a rare forest herb

The realms of rare species conservation and metapopulation biology theory are often interrelated, and hence share several basic challenges. Two of the most important are the critical and frequently difficult tasks of distinguishing a priori between habitat and nonhabitat, and then delimiting suitable habitat patches in a study area. We combined classification tree analysis, a subset of classification and regression tree (CART) modeling, with digital data layers of environmental variables in a geographic information system (GIS) to predict suitable habitat and potential new population occurrences for turkeybeard (Xerophyllum asphodeloides), a rare liliaceous understory herb associated with southern Appalachian pine-oak (Pinus-Quercus) forests, in northwestern Virginia. Sample values from eight environmental data layers and population survey data were used in the modeling process to produce a cross-validated classification tree that predicted suitable habitat in the study area. Elevation, slope, forest type, and fire frequency were the four main explanatory variables in the model. Approximately 4% of the study area was classified into five suitable habitat classes, with a misclassification error rate of 4.74%. The final 13-leaf tree correctly classified 74% of the known presence areas and 90% of the known absence areas, and ground-truthing surveys resulted in the discovery of eight new occupied habitat patches. Results of this study are important for conservation and management of X. asphodeloides, as well as for the applicability of the habitat modeling techniques to enhancing the study of metapopulations and disturbance regimes in Appalachian forests. In addition, they confirm the potential and value of CART and GIS-based modeling approaches to species distribution problems. Our model was successful at defining suitable habitat and discovering new populations of a rare species at the landscape scale. Similar application to other rare species could prove very useful for addressing these and other ecological and conservation issues, such as planning transplantation or reintroduction experiments, identifying metapopulation fragmentation thresholds, and formulating conservation strategies.