Abstract

Predictions from species distribution models (SDMs) are commonly used in support of environmental decision-making to explore potential impacts of climate change on biodiversity. However, because future climates are likely to differ from current climates, there has been ongoing interest in understanding the ability of SDMs to predict species responses under novel conditions (i.e., model transferability). Here, we explore the spatial and environmental limits to extrapolation in SDMs using forest inventory data from 11 model algorithms for 108 tree species across the western United States. Algorithms performed well in predicting occurrence for plots that occurred in the same geographic region in which they were fitted. However, a substantial portion of models performed worse than random when predicting for geographic regions in which algorithms were not fitted. Our results suggest that for transfers in geographic space, no specific algorithm was better than another as there were no significant differences in predictive performance across algorithms. There were significant differences in predictive performance for algorithms transferred in environmental space with GAM performing best. However, the predictive performance of GAM declined steeply with increasing extrapolation in environmental space relative to other algorithms. The results of this study suggest that SDMs may be limited in their ability to predict species ranges beyond the environmental data used for model fitting. When predicting climate-driven range shifts, extrapolation may also not reflect important biotic and abiotic drivers of species ranges, and thus further misrepresent the realized shift in range. Future studies investigating transferability of process based SDMs or relationships between geodiversity and biodiversity may hold promise.

Highlights

  • Unprecedented environmental change caused by human activity threatens biodiversity and its associated ecosystem functions and services that humanity relies upon (Chapin et al, 2000; Scheffers et al, 2016)

  • Limits to Extrapolation in Geographic and Environmental Space To address Questions 2–4, we examined the relationship between predictive performance and extrapolation distance outside the 19-dimensional climatic space and outside the 2-dimensional geographic space of the training data

  • When testing plots within the training region, the ranked area under the receiver operating curve (AUC) for random forest was much better than when predicting to a novel region, suggesting that the algorithms were overfit (Figure 3)

Read more

Summary

Introduction

Unprecedented environmental change caused by human activity threatens biodiversity and its associated ecosystem functions and services that humanity relies upon (Chapin et al, 2000; Scheffers et al, 2016). In this era of rapid global change, forecasts of biodiversity changes have the potential to inform conservation decisions to minimize extinctions (Botkin et al, 2007). Despite the limitations of SDMs (Pearson and Dawson, 2003; Belmaker et al, 2015), they remain a common and useful tool for predicting potential changes in species distributions and suitable habitat (Record et al, 2018). Understanding the limitations of SDMs is necessary to inform their appropriate use

Objectives
Methods
Results
Discussion
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call