Journal article

Predictive performance of presence-only species distribution models: a benchmark study with reproducible code

Roozbeh Valavi, Gurutzeta Guillera-Arroita, Jose J Lahoz-Monfort, Jane Elith

ECOLOGICAL MONOGRAPHS | WILEY | Published : 2021

Abstract

Species distribution modeling (SDM) is widely used in ecology and conservation. Currently, the most available data for SDM are species presence-only records (available through digital databases). There have been many studies comparing the performance of alternative algorithms for modeling presence-only data. Among these, a 2006 paper from Elith and colleagues has been particularly influential in the field, partly because they used several novel methods (at the time) on a global data set that included independent presence–absence records for model evaluation. Since its publication, some of the algorithms have been further developed and new ones have emerged. In this paper, we explore patterns..

View full abstract

Grants

Awarded by Australian Research Council (ARC) Discovery Early Career Researcher Award


Awarded by ARC Discovery Project


Awarded by National Centre for Ecological Analysis and Synthesis, Santa Barbara, California


Funding Acknowledgements

R. Valavi was supported by an Australian Government Research Training Program Scholarship and a Rowden White Scholarship; G. Guillera-Arroita by an Australian Research Council (ARC) Discovery Early Career Researcher Award (DE160100904), and J. J. Lahoz-Monfort and J. Elith by ARC Discovery Project 160101003. We thank Matthew Cantele for providing the code for Circos software. We also thank Meelis Kull, Nick Golding, Martin Ingram, and David Wilkinson for their helpful suggestions and advice, and two reviewers and our handling editor for insightful comments. This analysis uses the data collated for the working group "Testing alternative methodologies for modeling species' ecological niches and predicting geographic distributions" (project ID: 4980) funded and hosted by the National Centre for Ecological Analysis and Synthesis, Santa Barbara, California. We thank NCEAS for the funding, the project leaders and participants, and those who contributed the data.