A comprehensive evaluation of predictive performance of 33 species distribution models at species and community levels
Norberg, A.; Abrego, N.; Guillaume Blanchet, F.; Adler, F. R.; Anderson, B. J.; Anttila, J.; Araújo, M. B.; Dallas, T.; Dunson, D.; Elith, J.; Foster, S. D.; Fox, R.; Franklin, J.; Godsoe, William; Guisan, A.; O'Hara, B.; Hill, N. A.; Holt, R. D.; Hui, F. K. C.; Husby, M.; Kålås, J. A.; Lehikoinen, A.; Luoto, M.; Mod, H. K.; Newell, G.; Renner, I.; Roslin, T.; Soininen, J.; Thuiller, W.; Vanhatalo, J.; Warton, D.; White, M.; Zimmermann, N. E.; Gravel, D.; Ovaskainen, O.
Abstract
A large array of species distribution model (SDM) approaches has been developed for explaining and predicting the occurrences of individual species or species assemblages. Given the wealth of existing models, it is unclear which models perform best for interpolation or extrapolation of existing data sets, particularly when one is concerned with species assemblages. We compared the predictive performance of 33 variants of 15 widely applied and recently emerged SDMs in the context of multispecies data, including both joint SDMs that model multiple species together, and stacked SDMs that model each species individually combining the predictions afterward. We offer a comprehensive evaluation of these SDM approaches by examining their performance in predicting withheld empirical validation data of different sizes representing five different taxonomic groups, and for prediction tasks related to both interpolation and extrapolation. We measure predictive performance by 12 measures of accuracy, discrimination power, calibration, and precision of predictions, for the biological levels of species occurrence, species richness, and community composition. Our results show large variation among the models in their predictive performance, especially for communities comprising many species that are rare. The results do not reveal any major trade-offs among measures of model performance; the same models performed generally well in terms of accuracy, discrimination, and calibration, and for the biological levels of individual species, species richness, and community composition. In contrast, the models that gave the most precise predictions were not well calibrated, suggesting that poorly performing models can make overconfident predictions. However, none of the models performed well for all prediction tasks. As a general strategy, we therefore propose that researchers fit a small set of models showing complementary performance, and then apply a cross-validation procedure involving separate data to establish which of these models performs best for the goal of the study.... [Show full abstract]
Keywords
community assembly; community modeling; environmental filtering; joint species distribution model; model performance; prediction; predictive power; species interactions; stacked species distribution model; EcologyFields of Research
0406 Physical Geography and Environmental Geoscience; 0501 Ecological Applications; 0602 EcologyDate
2019-08Type
Journal ArticleCollections
© 2019 The Authors.
Citation
Norberg et al. (2019). A comprehensive evaluation of predictive performance of 33 species distribution models at species and community levels. Ecological Monographs, 89(3), e01370. doi:10.1002/ecm.1370Related items
Showing items related by title, author, creator and subject.
-
How do species interactions affect species distribution models?
Godsoe, William; Harmon, L. J. (John Wiley & Sons, Inc. on behalf of The Oikos Editorial Office, 2012-09)One of the most promising recent advances in biogeography has been the increased interest and understanding of species distribution models – estimates of the probability that a species is present given environmental data. ... -
Widespread native and alien plant species occupy different habitats
Pouteau, R.; Hulme, Philip E.; Duncan, Richard P. (Wiley on behalf of Oikos Editorial Board, 2015)© 2014 The Authors.Theories to explain the success of alien species often assume that they are inherently different from native species. Although there is an increasing body of evidence showing that alien plants tend to ... -
Ensemble models to assess the risk of exotic plant pathogens in a changing climate
Narouei-Khandan, Hossein Ali (Lincoln University, 2014)In recent decades, species distribution models (SDMs) have been widely used in many ecological, environmental and climate-change research studies to model invasive species establishment. These models associate recorded ...