Predicting plant species distributions using climate‐based model ensembles with corresponding measures of congruence and uncertainty. (17th March 2022)

• Record Type: Journal Article
• Authors: Stewart, Stephen B.; Fedrigo, Melissa; Kasel, Sabine; Roxburgh, Stephen H.; Choden, Kunzang; Tenzin, Karma; Allen, Kathryn; Nitschke, Craig R.
• Editors: Jarvis, Susan
• Is Part Of: Diversity & distributions. Volume 28:Number 5(2022)
• Page Start: 1105
• Page End: 1122
• Publication Date: 2022-03-17
• Subjects: Cantelli's inequality -- climate -- congruence -- ensemble -- species distribution modelling -- uncertainty; Biodiversity -- Periodicals; Biodiversity conservation -- Periodicals; 577
• DOI: 10.1111/ddi.13515
• Languages: English
• ISSNs: 1366-9516

Abstract

Abstract: Aim: The increasing availability of regional and global climate data presents an opportunity to build better ecological models; however, it is not always clear which climate dataset is most appropriate. The aim of this study was to better understand the impacts that alternative climate datasets have on the modelled distribution of plant species, and to develop systematic approaches to enhancing their use in species distribution models (SDMs). Location: Victoria, southeast Australia and the Himalayan Kingdom of Bhutan. Methods: We compared the statistical performance of SDMs for 38 plant species in Victoria and 12 plant species in Bhutan with multiple algorithms using globally and regionally calibrated climate datasets. Individual models were compared against one another and as SDM ensembles to explore the potential for alternative predictions to improve statistical performance. We develop two new spatially continuous metrics that support the interpretation of ensemble predictions by characterizing the per‐pixel congruence and variability of contributing models. Results: There was no clear consensus on which climate dataset performed best across all species in either study region. On average, multi‐model ensembles (across the same species with different climate data) increased AUC/TSS/Kappa/OA by up to 0.02/0.03/0.03/0.02 in Victoria and 0.06/0.11/0.11/0.05 in Bhutan. Ensembles performed better than most single models in both Victoria (AUC = 85%; TSS = 68%) and Bhutan (AUC = 86%; TSS = 69%). SDM ensembles using models fitted with alternative algorithms and/or climate datasets each provided a significant improvement over single model runs. Main conclusions: Our results demonstrate that SDM ensembles, built using alternative models of the same climate variables, can quantify model congruence and identify regions of the highest uncertainty while mitigating the risk of erroneous predictions. Algorithm selection is known to be a large source of error for SDMs, and our results demonstrate that climate dataset selection can be a comparably significant source of uncertainty.