The effect of sample size and species characteristics on performance of different species distribution modeling methods

TLDR

Species distribution models aim to estimate the spatial distributions of rare species, but limited occurrences make accurate modeling challenging. The study evaluated four presence‑only modeling methods across 18 species, varying sample sizes and evaluation metrics. The authors compared Bioclim, Domain, GARP, and Maxent on 18 species, manipulating sample sizes (5–25 occurrences) and using three evaluation metrics. Maxent outperformed the other methods with as few as 5–25 occurrences, while Domain and GARP performed moderately and Bioclim poorly; accuracy was higher for species with small ranges, and multiple evaluation metrics are required to assess presence‑only models, indicating that useful models can be built for some rare species.

Abstract

Species distribution models should provide conservation practioners with estimates of the spatial distributions of species requiring attention. These species are often rare and have limited known occurrences, posing challenges for creating accurate species distribution models. We tested four modeling methods (Bioclim, Domain, GARP, and Maxent) across 18 species with different levels of ecological specialization using six different sample size treatments and three different evaluation measures. Our assessment revealed that Maxent was the most capable of the four modeling methods in producing useful results with sample sizes as small as 5, 10 and 25 occurrences. The other methods compensated reasonably well (Domain and GARP) to poorly (Bioclim) when presented with datasets of small sample sizes. We show that multiple evaluation measures are necessary to determine accuracy of models produced with presence‐only data. Further, we found that accuracy of models is greater for species with small geographic ranges and limited environmental tolerance, ecological characteristics of many rare species. Our results indicate that reasonable models can be made for some rare species, a result that should encourage conservationists to add distribution modeling to their toolbox.