The DOI matches its Crossref record; 29 of the 29 references it cites were found in a registry or an index.
Testing whether ensemble modelling is advantageous for maximising predictive performance of species distribution models
Open accessAbstract
Predictive performance is important to many applications of species distribution models (SDMs). The SDM ‘ensemble’ approach, which combines predictions across different modelling methods, is believed to improve predictive performance, and is used in many recent SDM studies. Here, we aim to compare the predictive performance of ensemble species distribution models to that of individual models, using a large presence–absence dataset of eucalypt tree species. To test model performance, we divided our dataset into calibration and evaluation folds using two spatial blocking strategies (checkerboard‐pattern and latitudinal slicing). We calibrated and cross‐validated all models within the calibration folds, using both repeated random division of data (a common approach) and spatial blocking. Ensembles were built using the software package ‘biomod2’, with standard (‘untuned’) settings. Boosted regression tree (BRT) models were also fitted to the same data, tuned according to published procedures. We then used evaluation folds to compare ensembles against both their component untuned individual models, and against the BRTs. We used area under the receiver‐operating characteristic curve (AUC) and log‐likelihood for assessing model performance. In all our tests, ensemble models performed well, but not consistently better than their component untuned individual models or tuned BRTs across all tests. Moreover, choosing untuned individual models with best cross‐validation performance also yielded good external performance, with blocked cross‐validation proving better suited for this choice, in this study, than repeated random cross‐validation. The latitudinal slice test was only possible for four species; this showed some individual models, and particularly the tuned one, performing better than ensembles. This study shows no particular benefit to using ensembles over individual tuned models. It also suggests that further robust testing of performance is required for situations where models are used to predict to distant places or environments.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
The Elements of Statistical Learning
Hastie, T., Tibshirani, R., & Friedman, J. (2009) · Springer Series in Statistics · doi:10.1007/978-0-387-84858-7 · Cited by 25,970
Novel methods improve prediction of species’ distributions from occurrence data
Elith*, J., H. Graham*, C., P. Anderson, R., Dudík, M., Ferrier, S., Guisan, A., J. Hijmans, R., Huettmann, F., R. Leathwick, J., Lehmann, A., et al. (2006) · Ecography · doi:10.1111/j.2006.0906-7590.04596.x · Cited by 9,088
Self-citationA review of methods for the assessment of prediction errors in conservation presence/absence models
FIELDING, A. H., & BELL, J. F. (1997) · Environmental Conservation · doi:10.1017/s0376892997000088 · Cited by 6,956
Predicting species distribution: offering more than simple habitat models
Guisan, A., & Thuiller, W. (2005) · Ecology Letters · doi:10.1111/j.1461-0248.2005.00792.x · Cited by 6,587
A working guide to boosted regression trees
Elith, J., Leathwick, J. R., & Hastie, T. (2008) · Journal of Animal Ecology · doi:10.1111/j.1365-2656.2008.01390.x · Cited by 6,484
Self-citationCross‐validation strategies for data with temporal, spatial, hierarchical, or phylogenetic structure
Roberts, D. R., Bahn, V., Ciuti, S., Boyce, M. S., Elith, J., Guillera‐Arroita, G., Hauenstein, S., Lahoz‐Monfort, J. J., Schröder, B., Thuiller, W., et al. (2017) · Ecography · doi:10.1111/ecog.02881 · Cited by 3,689
Self-citationEnsemble forecasting of species distributions
ARAUJO, M., & NEW, M. (2007) · Trends in Ecology & Evolution · doi:10.1016/j.tree.2006.09.010 · Cited by 3,640
Merow, C., Smith, M. J., & Silander, J. A. (2013) · Ecography · doi:10.1111/j.1600-0587.2013.07872.x · Cited by 3,392
BIOMOD – a platform for ensemble forecasting of species distributions
Thuiller, W., Lafourcade, B., Engler, R., & Araújo, M. B. (2009) · Ecography · doi:10.1111/j.1600-0587.2008.05742.x · Cited by 2,749
Evaluating the predictive performance of habitat models developed using logistic regression
Pearce, J., & Ferrier, S. (2000) · Ecological Modelling · doi:10.1016/s0304-3800(00)00322-7 · Cited by 2,002
Habitat Suitability and Distribution Models: With Applications in R
Guisan, A., Thuiller, W., & Zimmermann, N. E. (2017) · Cambridge University Press eBooks · doi:10.1017/9781139028271 · Cited by 1,479
Evaluation of consensus methods in predictive species distribution modelling
Marmion, M., Parviainen, M., Luoto, M., Heikkinen, R. K., & Thuiller, W. (2009) · Diversity and Distributions · doi:10.1111/j.1472-4642.2008.00491.x · Cited by 1,435
Elith, J., & Graham, C. H. (2009) · Ecography · doi:10.1111/j.1600-0587.2008.05505.x · Cited by 1,098
Self-citationValavi, R., Elith, J., Lahoz‐Monfort, J. J., & Guillera‐Arroita, G. (2019) · Methods in Ecology and Evolution · doi:10.1111/2041-210x.13107 · Cited by 1,056
Self-citationModel‐based uncertainty in species range prediction
Pearson, R. G., Thuiller, W., Araújo, M. B., Martinez‐Meyer, E., Brotons, L., McClean, C., Miles, L., Segurado, P., Dawson, T. P., & Lees, D. C. (2006) · Journal of Biogeography · doi:10.1111/j.1365-2699.2006.01460.x · Cited by 981
Is my species distribution model fit for purpose? Matching data and models to applications
Guillera‐Arroita, G., Lahoz‐Monfort, J. J., Elith, J., Gordon, A., Kujala, H., Lentini, P. E., McCarthy, M. A., Tingley, R., & Wintle, B. A. (2015) · Global Ecology and Biogeography · doi:10.1111/geb.12268 · Cited by 961
Self-citationdismo: Species Distribution Modeling
Hijmans, R. J., Phillips, S., Leathwick, J., & Elith, J. (2010) · CRAN: Contributed Packages · doi:10.32614/cran.package.dismo · Cited by 888
Self-citationAn evaluation of methods for modelling species distributions
Segurado, P., & Araújo, M. B. (2004) · Journal of Biogeography · doi:10.1111/j.1365-2699.2004.01076.x · Cited by 875 · cited 1×
“However, the relative predictive performance of algorithms is often situation-dependent, and past algorithm comparisons have not been able to identify any single class of algorithms as consistently superior at prediction (Segurado and Araújo 2004, Elith et al.”
BackgroundMiller, J. (2010) · Geography Compass · doi:10.1111/j.1749-8198.2010.00351.x · Cited by 689
What do we gain from simplicity versus complexity in species distribution models?
Merow, C., Smith, M. J., Edwards, T. C., Guisan, A., McMahon, S. M., Normand, S., Thuiller, W., Wüest, R. O., Zimmermann, N. E., & Elith, J. (2014) · Ecography · doi:10.1111/ecog.00845 · Cited by 683
Self-citationHao, T., Elith, J., Guillera‐Arroita, G., & Lahoz‐Monfort, J. J. (2019) · Diversity and Distributions · doi:10.1111/ddi.12892 · Cited by 674
Self-citationAssessing transferability of ecological models: an underappreciated aspect of statistical validation
Wenger, S. J., & Olden, J. D. (2012) · Methods in Ecology and Evolution · doi:10.1111/j.2041-210x.2011.00170.x · Cited by 642
Diniz‐Filho, J. A. F., Mauricio Bini, L., Fernando Rangel, T., Loyola, R. D., Hof, C., Nogués‐Bravo, D., & Araújo, M. B. (2009) · Ecography · doi:10.1111/j.1600-0587.2009.06196.x · Cited by 615
Fithian, W., Elith, J., Hastie, T., & Keith, D. A. (2015) · Methods in Ecology and Evolution · doi:10.1111/2041-210x.12242 · Cited by 452
Self-citationDormann, C. F., Calabrese, J. M., Guillera‐Arroita, G., Matechou, E., Bahn, V., Bartoń, K., Beale, C. M., Ciuti, S., Elith, J., Gerstner, K., et al. (2018) · Ecological Monographs · doi:10.1002/ecm.1309 · Cited by 400
Self-citationTransferring biodiversity models for conservation: Opportunities and challenges
Sequeira, A. M. M., Bouchet, P. J., Yates, K. L., Mengersen, K. L., & Caley, M. J. (2018) · Methods in Ecology and Evolution · doi:10.1111/2041-210x.12998 · Cited by 142
Hartley, S., Harris, R. J., & Lester, P. J. (2006) · Ecology Letters · doi:10.1111/j.1461-0248.2006.00954.x · Cited by 135
Evaluating ensemble forecasts of plant species distributions under climate change
Crimmins, S., Dobrowski, S., & Mynsberge, A. R. (2013) · Ecological Modelling · doi:10.1016/j.ecolmodel.2013.07.006 · Cited by 95
Zhu, G., & Peterson, A. T. (2017) · Biological Invasions · doi:10.1007/s10530-017-1460-y · Cited by 93
Cited by
Valavi, R., Guillera‐Arroita, G., Lahoz‐Monfort, J. J., & Elith, J. (2022) · Ecological Monographs · doi:10.1002/ecm.1486 · Cited by 830
Self-citationWant to model a species niche? A step-by-step guideline on correlative ecological niche modelling
Sillero, N., Arenas-Castro, S., Enriquez‐Urzelai, U., Vale, C. G., Sousa-Guedes, D., Martínez-Freiría, F., Real, R., & Barbosa, A. M. (2021) · Ecological Modelling · doi:10.1016/j.ecolmodel.2021.109671 · Cited by 456
Abedin, I., Putra, A., Kang, H.-E., Singh, A., Singh, S., Jung, W.-K., Kim, H.-W., & Kundu, S. (2025) · doi:10.21203/rs.3.rs-7140563/v1 · Cited by 1
Metadata
- Authors
- Hao, T., Elith, J., Lahoz‐Monfort, J. J., & Guillera‐Arroita, G.
- Venue
- Ecography
- Publisher
- Wiley
- Published
- 2020-01-27
- Volume
- 43
- Issue
- 4
- Pages
- 549-558
- ISSN
- 0906-7590 (ISSN-L)
- 1600-0587
- OpenAlex
- W3003960167
- Cited by
- 477
- References
- 29
- FWCI
- 88.18
- Type
- journal article
- Language
- en
- Open access
- gold
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.
