Monitoring At-Risk Species in the Southeastern U.S. Can Be Improved with an Ensemble Habitat Modeling Approach

Dr. Carlos Ramirez-Reyes1, D. Todd Jones-Farrand3, Garret Street1,2, Francisco Vilella4, Kristine O. Evans 1,2

1. Department of Wildlife, Fisheries and Aquaculture, Mississippi State University

2. Quantitative Ecology & Spatial Technologies Laboratory, Mississippi State University

3. U.S. Fish and Wildlife Service 302 Natural Resources, University of Missouri 4. U.S. Geological Survey, Mississippi Cooperative Fish and Wildlife Research Unit

Effective conservation planning requires reliable information on the distribution of species, which is often incomplete due to limited availability of data. Species distribution models (SDMs) and associated tools have proliferated in the past decades and have proven valuable in evaluating suitability and critical habitat for species. However, conservation practitioners have not fully adopted SDMs to inform surveys and other monitoring efforts. Instead, most efforts rely on expert knowledge and other traditional methods to locate extant populations. In particular, the Species Status Assessment (SSA) initiative of the U.S. Fish and Wildlife Service would benefit from incorporating SDM approaches to facilitate conservation decisions. Here, we describe an SDM approach for at-risk species that could be considered for SSA and similar species monitoring efforts. We applied 4 modeling techniques (generalized additive, maximum entropy, generalized boosted, and weighted ensemble) to recent monitoring data for 4 at-risk plant species (Scutellaria ocmulgee, Balduina atropurpurea, Rhynchospora crinipes and Torreya taxifolia) in the Southeastern U.S. Our results showed that ensemble distribution models reduced uncertainty caused by differences among modeling techniques and improved the predictive accuracy of fitted models. These models highlight areas with high habitat suitability for a particular species and therefore candidates for additional monitoring and survey efforts. We suggest that this approach could be adopted into the SSA framework to develop more robust and efficient assessments of at-risk species.