Journal article

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

Anna Norberg, Nerea Abrego, F Guillaume Blanchet, Frederick R Adler, Barbara J Anderson, Jani Anttila, Miguel B Araujo, Tad Dallas, David Dunson, Jane Elith, Scott D Foster, Richard Fox, Janet Franklin, William Godsoe, Antoine Guisan, Bob O'Hara, Nicole A Hill, Robert D Holt, Francis KC Hui, Magne Husby Show all



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 ..

View full abstract

University of Melbourne Researchers


Awarded by Academy of Finland

Awarded by Research Council of Norway (CoE grant)

Awarded by Ministry of Science, Innovation and Universities

Awarded by U.S. Department of Agriculture through NSFAwards

Funding Acknowledgements

This work was funded by the Research Foundation of the University of Helsinki (A. Norberg), the Academy of Finland (CoE grant 284601 and grant 309581 to O. Ovaskainen, grant 308651 to N. Abrego, grant 1275606 to A. Lehikoinen), the Research Council of Norway (CoE grant 223257), the Jane and Aatos Erkko Foundation, and the Ministry of Science, Innovation and Universities (grant CGL2015-68438-P to M. B. Araujo). Contributions were also made by members of the Biotic Interactions Working Group ( at the National Institute for Mathematical and Biological Synthesis, sponsored by the National Science Foundation, the U.S. Dept. of Homeland Security, and the U.S. Department of Agriculture through NSFAwards #EF-0832858 and #DBI-1300426, with additional support from The University of Tennessee, Knoxville. We would like to thank the thousands of researchers and volunteers who have contributed to the data sets utilized in this study. In particular, we thank Ake Lindstrom for making Swedish bird monitoring data available to us. The bird surveys in Sweden were supported by grants from the Swedish Environmental Protection Agency and carried out in collaboration with all 21 County Administrative Boards of Sweden, and the bird surveys in Norway were supported by the Norwegian Environment Agency.