You are here: Home Results Task 5.1.3. Optimizing biodiversity scenarios by multi-model predictions

Task 5.1.3. Optimizing biodiversity scenarios by multi-model predictions

Task lead: Wilfried Thuiller, Centre national de la recherche scientifique, France

This task, which is now completed, was dedicated to the design and test of consensus methods for species distribution forecasting. These techniques basically rely on the comparison and combination of individual ecological niche models (e.g. ANN: Artificial neural network, CTA: Classification Tree Analysis, GAM: Generalized Additive Models, GBM: Generalized Boosted Trees, GLM: generalized Linear Model, MARS: multiple adaptive regression spline, MDA: Mixture Discriminant Analysis,….) or different modeling approaches (e.g ecological niche models and spread models) to optimize the accuracy of species distribution predictions and projections in space and time.

Typical consensus methods combine probabilities of species occurrence using different functions (e.g. Weighted Average (WA), Mean(All), Median(All), Median(PCA)) or compare model performances, select the most consensual model or the best performing. Analyses were performed in the context of climate change and species invasions for threatened plant species and one conspicuous invasive ant species.

The conclusions highlighted

(i) the need to consider consensus method for more robust and more accurate species distribution forecasting and especially

(ii) the benefit of using weighted function algorithms. 

  • Marmion, M., Parviainen, M., Luoto, M., Heikkinen, R.K., & Thuiller, W. (2009) Evaluation of consensus methods in predictive species distribution modelling. Diversity and Distributions, 15, 59-69.
  • Roura-Pascual, N., Brotons, L., Peterson, A.T., & Thuiller, W. (2009) Consensual predictions of potential distributional areas for invasive species. Biological Invasion. 11:1017-1031
  • Diniz-Filho, J.A., Bini, L.M., Rangel, T.F.L.B., Loyola, R.D., Hof, C., Nogués-Bravo, D. & Araújo, M.B. 2009. Partitioning and mapping uncertainties in ensembles of forecasts of species turnover under climate changes. Ecography 32: 897-906.
Document Actions