Comparing species distribution models constructed with different subsets of environmental predictors

Aim To assess the usefulness of combining climate predictors with additional types of environmental predictors in species distribution models for range-restricted species, using common correlative species distribution modelling approaches. Location Florida, USA Methods We used five different algorit...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Diversity & distributions Ročník 21; číslo 1; s. 23 - 35
Hlavní autori: Bucklin, David N., Basille, Mathieu, Benscoter, Allison M., Brandt, Laura A., Mazzotti, Frank J., Romañach, Stephanie S., Speroterra, Carolina, Watling, James I.
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Oxford Blackwell Publishing Ltd 01.01.2015
John Wiley & Sons Ltd
John Wiley & Sons, Inc
Predmet:
Accuracy
Algorithms
Bioclimate
Bioclimatology
Biodiversity
BIODIVERSITY RESEARCH
Biogeography
climate
Climate change
Environmental assessment
Extreme weather
Florida
human influence
Human influences
humans
land cover
prediction
species distribution modelling
statistical models
weather
Florida
ISSN:1366-9516, 1472-4642
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Aim To assess the usefulness of combining climate predictors with additional types of environmental predictors in species distribution models for range-restricted species, using common correlative species distribution modelling approaches. Location Florida, USA Methods We used five different algorithms to create distribution models for 14 vertebrate species, using seven different predictor sets: two with bioclimate predictors only, and five 'combination' models using bioclimate predictors plus 'additional' predictors from groups representing: human influence, land cover, extreme weather or noise (spatially random data).We use a linear mixed-model approach to analyse the effects of predictor set and algorithm on model accuracy, variable importance scores and spatial predictions. Results Regardless of modelling algorithm, no one predictor set produced significantly more accurate models than all others, though models including human influence predictors were the only ones with significantly higher accuracy than climate-only models. Climate predictors had consistently higher variable importance scores than additional predictors in combination models, though there was variation related to predictor type and algorithm. While spatial predictions varied moderately between predictor sets, discrepancies were significantly greater between modelling algorithms than between predictor sets. Furthermore, there were no differences in the level of agreement between binary 'presence–absence' maps and independent species range maps related to the predictor set used. Main conclusions Our results indicate that additional predictors have relatively minor effects on the accuracy of climate-based species distribution models and minor to moderate effects on spatial predictions. We suggest that implementing species distribution models with only climate predictors may provide an effective and efficient approach for initial assessments of environmental suitability.
Bibliografia:ArticleID:DDI12247
National Park Service (Everglades and Dry Tortugas National Parks)
istex:5D50FDE63F6952E844AA2F105C624DCDF0130B2D
South Florida and Caribbean Cooperative Ecosystem Studies Unit
US Fish and Wildlife Service
Figure S1 Boxplot comparing TSS for all 4-predictor models. Figure S2 Point plots displaying suitable area predictions (Ncells) for individual species. Figure S3 Box and whisker plot illustrating the effect of modelling algorithm on overlap between range maps and presence-absence maps, as measured by kappa. Figure S4 Response plots for human influence predictors in random forests bio.hi models for the (a) Florida worm lizard and (b) Florida panther. Table S1 Pairwise spatial correlation (Pearson's r) between all study predictors. Table S2 Accuracy (AUC and TSS) of best-performing algorithm and mean for all algorithms for each species and predictor set combination. Table S3 Predictor selection frequency and mean variable importance scores. Table S4 Pairwise mean (± 1 SD) spatial correlation between probabilistic suitability maps from the seven different predictor sets.
US Geological Survey (Greater Everglades Priority Ecosystems Science)
ark:/67375/WNG-B6G4FDB0-H
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1366-9516
1472-4642
DOI:10.1111/ddi.12247