Characterizing the suitable habitat of Miconia calvescens in the East Maui Watershed

• Published in: Management of biological invasions 2021-06, Vol.12 (2), p.313-330
• Main Authors: Jorgensen, Niels, Leary, James, Renz, Mark, Mahnken, Brooke
• Format: Article
• Language: English
• Subjects: Algorithms; Geographical distribution; Habitats; Invasive species; Management; Miconia calvescens; Rainfall; Risk assessment; Watersheds
• ISSN: 1989-8649; 1989-8649
• DOI: 10.3391/mbi.2021.12.2.07

The East Maui Watershed (EMW) is a > 60,000-ha forested watershed with wide temperature and precipitation gradients being invaded by miconia (Miconia calvescens DC.). Current miconia management efforts focus on protecting important watershed and critical habitat areas from miconia invasion. Herein, we report on a miconia species distribution model to predict unoccupied areas that may be still vulnerable to invasion. This suitable habitat model was developed from an ensemble of five algorithms associating five physical features of EMW with miconia occurrence data from a 26-yr management history (1991–2016; n = 114,953). All of the algorithms performed well based on model evaluation statistics (e.g. AUC ≥ 0.83; TSS ≥ 0.36). Elevation, slope and rainfall were consistently important predictors, while aspect indices were non-contributors. The binary ensemble model suggests a total of ~ 56.9% of the area of interest is susceptible to invasion by miconia. An independent dataset collected in 2017–2018 (n = 5,222) was used to field validate the ensemble habitat suitability model (EHSM) and found that the model could correctly predict suitable habitat 94% of the time. All five of the model algorithms were updated using this new management data, and the predicted suitable area decreased 2.3%. While binary models are useful for risk assessment, the classification of an area as suitable or not suitable has limitations for land managers adopting for management activities. Utilizing the mean weighted consensus probability surface representation of the model allows for more scrutiny of potential suitable habitat. We suggest using this approach when planning future monitoring efforts, especially if specific areas have a higher prioritization for conservation than others.