Transferable species distribution modelling: comparative performance of Generalised Functional Response models

Aldossari, S., Husmeier, D. and Matthiopoulos, J. (2022) Transferable species distribution modelling: comparative performance of Generalised Functional Response models. Ecological Informatics, 71, 101803. (doi: 10.1016/j.ecoinf.2022.101803)

[img] Text
278259.pdf - Published Version
Available under License Creative Commons Attribution.

2MB

Abstract

Predictive species distribution models (SDMs) are becoming increasingly important in ecology, in the light of rapid environmental change. However, the predictions of most current SDMs are specific to the habitat composition of the environments in which they were fitted. This may limit SDM predictive power because species may respond differently to a given habitat depending on the availability of all habitats in their environment, a phenomenon known as a functional response in resource selection. The Generalised Functional Response (GFR) framework captures this dependence by formulating the SDM coefficients as functions of habitat availability. The original GFR implementation used global polynomial functions of habitat availability to describe the functional responses. In this study, we develop several refinements of this approach and compare their predictive performance using two simulated and two real datasets. We first use local radial basis functions (RBF), a more flexible approach than global polynomials, to represent the habitat selection coefficients, and balance bias with precision via regularization to prevent overfitting. Second, we use the RBF-GFR and GFR models in combination with the classification and regression tree CART, which has more flexibility and better predictive powers for non-linear modelling. As further extensions, we use random forests (RFs) and extreme gradient boosting (XGBoost), ensemble approaches that consistently lead to variance reduction in generalization error. We find that the different methods are ranked consistently across the datasets for out-of-data prediction. The traditional stationary approach to SDMs and the GFR model consistently perform at the bottom of the ranking (simple SDMs underfit, and polynomial GFRs overfit the data). The best methods in our list provide non-negligible improvements in predictive performance, in some cases taking the out-of-sample R2 from 0.3 up to 0.7 across datasets. At times of rapid environmental change and spatial non-stationarity ignoring the effects of functional responses on SDMs, results in two different types of prediction bias (under-prediction or mis-positioning of distribution hotspots). However, not all functional response models perform equally well. The more volatile polynomial GFR models can generate biases through over-prediction. Our results indicate that there are consistently robust GFR approaches that achieve impressive gains in transferability across very different datasets.

Item Type:Articles
Additional Information:This work was conducted as part of the PhD for Shaykhah Aldossari, funded by Saudi Arabia Cultural Bureau SACB in the UK.
Status:Published
Refereed:Yes
Glasgow Author(s) Enlighten ID:Matthiopoulos, Professor Jason and Husmeier, Professor Dirk and Aldossari, Shaykhah
Authors: Aldossari, S., Husmeier, D., and Matthiopoulos, J.
College/School:College of Medical Veterinary and Life Sciences > School of Biodiversity, One Health & Veterinary Medicine
College of Science and Engineering
College of Science and Engineering > School of Mathematics and Statistics > Statistics
Journal Name:Ecological Informatics
Publisher:Elsevier
ISSN:1574-9541
ISSN (Online):1878-0512
Published Online:08 September 2022
Copyright Holders:Copyright © 2022 The Author(s)
First Published:First published in Ecological Informatics 71: 101803
Publisher Policy:Reproduced under a Creative Commons License

University Staff: Request a correction | Enlighten Editors: Update this record