Flexible methods for species distribution modeling with small samples
Top Cited Papers
Open Access
Abstract
Species distribution models (SDMs) predict where species live or could potentially live and are a key resource for ecological research and conservation decision‐making. However, current SDM methods often perform poorly for rare or inadequately sampled species, which include most species on earth, as well as most of those of the greatest conservation concern. Here, we evaluated the performance of three modeling approaches designed for data‐deficient situations: plug‐and‐play modeling, density‐ratio modeling, and environmental‐range modeling. We compared the performance of algorithms within these approaches with the maximum entropy (MaxEnt) model, a widely used density‐ratio algorithm, both for data‐poor species and more generally. We also tested to what extent model cross‐validation performance on training data predicts model performance on independent, presence–absence data. We found that no algorithm performed best in all situations. Across all species, MaxEnt performed best on average but was outperformed by one or more of the plug‐and‐play, density‐ratio, or environmental‐range algorithms in 72% of cases. Six of the other algorithms had the area under the receiver operating characteristic curve (AUC) distributions not significantly different from MaxEnt's, and for data‐poor species (those with 20 or fewer occurrences), 24 of the algorithms considered had AUC distributions not significantly different from MaxEnt's. However, we found that the algorithm outputs (when thresholded to predict presence vs absence) spanned a wide sensitivity–specificity gradient. Specificity and prediction accuracy assessed on training data were strongly correlated with specificity and prediction accuracy assessed on independent presence–absence data. However, AUC and sensitivity were weakly correlated in training versus testing sets, with only 22% of species having the same model perform best when evaluated on training and independent, presence absence data. Finally, we show how ensembles of algorithms that span the sensitivity–specificity gradient can represent model disagreement in poorly sampled species and improve model predictions.Keywords
All Related Versions
This publication has 59 references indexed in Scilit:
- Effects of sample size, data quality, and species response in environmental space on modeling species distributionsLandscape Ecology, 2023
- Predictive performance of presence‐only species distribution models: a benchmark study with reproducible codeEcological Monographs, 2021
- A comprehensive evaluation of predictive performance of 33 species distribution models at species and community levelsEcological Monographs, 2019
- Outstanding Challenges in the Transferability of Ecological ModelsTrends in Ecology & Evolution, 2018
- Estimating environmental suitabilityEcosphere, 2018
- WorldClim 2: new 1‐km spatial resolution climate surfaces for global land areasInternational Journal of Climatology, 2017
- Computation of Multivariate Normal and t Probabilities2009
- Simultaneous Inference in General Parametric ModelsBiometrical Journal, 2008
- A toolbox for -centroids cluster analysisComputational Statistics & Data Analysis, 2006
- Maximum entropy modeling of species geographic distributionsEcological Modelling, 2006