The best of two worlds: using stacked generalization for integrating expert range maps in species distribution models

Abstract

Species distribution models (SDMs) are powerful tools for assessing suitable habitat across large areas and at fine spatial resolution. Yet, the usefulness of SDMs for mapping species realized distributions is often limited, since data biases or missing information on dispersal barriers or biotic interactions hinder them from accurately delineating species range limits. One way to overcome this limitation is to integrate SDMs with expert range maps, which provide coarse-scale information on the extent of species ranges that is complementary to information offered by SDMs. Here, we propose a new approach for integrating expert range maps in SDMs based on an ensemble method called stacked generalization. Specifically, our approach relies on training a meta-learner regression model using predictions from one or more SDM algorithms alongside the distance of training points to expert-defined ranges as predictor variables. We demonstrate our approach with an occurrence dataset for 49 bat species covering three biodiversity hotspots in the Eastern Mediterranean, Western Asia, and Central Asia. Our approach offers a flexible method to integrate expert range maps with any combination of SDM modeling algorithms, thus facilitating the use of algorithm ensembles. In addition, it provides a novel, data-driven way to account for uncertainty in expert-defined ranges not requiring prior knowledge about their accuracy, which is often lacking. Our approach holds considerable promise for better understanding species distributions, and thus for biogeographical research and conservation planning. In addition, our work highlights the overlooked potential of stacked generalization as an ensemble method in species distribution modeling.