Title

A comprehensive evaluation of predictive performance of 33 species distribution models at species and community levels

Authors

Anna Norberg, Helsingin Yliopisto
Nerea Abrego, Norges teknisk-naturvitenskapelige universitet
F. Guillaume Blanchet, Université de Sherbrooke
Frederick R. Adler, The University of Utah
Barbara J. Anderson, Manaaki Whenua - Landcare Research
Jani Anttila, Helsingin Yliopisto
Miguel B. Araújo, CSIC - Museo Nacional de Ciencias Naturales (MNCN)
Tad Dallas, Helsingin Yliopisto
David Dunson, Duke University
Jane Elith, University of Melbourne
Scott D. Foster, Commonwealth Scientific and Industrial Research Organization
Richard Fox, Butterfly Conservation
Janet Franklin, University of California, Riverside
William Godsoe, Lincoln University, New Zealand
Antoine Guisan, Université de Lausanne (UNIL)
Bob O'Hara, Norges teknisk-naturvitenskapelige universitet
Nicole A. Hill, Institute for Marine and Antarctic Studies
Robert D. Holt, University of Florida
Francis K.C. Hui, The Australian National University
Magne Husby, Nord universitet
John Atle Kålås, Norwegian Institute for Nature Research
Aleksi Lehikoinen, Finnish Museum of Natural History
Miska Luoto, Helsingin Yliopisto
Heidi K. Mod, Université de Lausanne (UNIL)
Graeme Newell, Arthur Rylah Institute for Environmental Research
Ian Renner, The University of Newcastle, Australia
Tomas Roslin, Helsingin Yliopisto
Janne Soininen, Helsingin Yliopisto
Wilfried Thuiller, Universite Grenoble Alpes
Jarno Vanhatalo, Helsingin Yliopisto
David Warton, UNSW Sydney
Matt White, Arthur Rylah Institute for Environmental Research
Niklaus E. Zimmermann, Eidgenössische Forschungsanstalt für Wald, Schnee und Landschaft WSL

Document Type

Article

Publication Date

1-1-2019

Abstract

© 2019 The Authors. Ecological Monographs published by Wiley Periodicals, Inc. on behalf of Ecological Society of America 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.

Publication Source (Journal or Book title)

Ecological Monographs

This document is currently not available here.

Share

COinS