Evaluation of consensus methods in predictive species distribution modelling

By Mathieu Marmion, Miia Parviainen, Miska Luoto, Risto Heikkinen, Wilfried Thuiller. 2009

1,407 citations recorded by the source corpus.

Subfields: Ecological Modeling, Ecology, Nature and Landscape Conservation

View Paper: https://www.semanticscholar.org/paper/9ec0936f64df600e67c3106e063e6c9f99cb39b0

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Ecological Modeling

In Ecology

In Nature and Landscape Conservation

Citations in the corpus

The art of modelling range‐shifting species (2010, methodology): “…is to generate an ensemble of predictions basedon the standardapplicationof several differentmodelling methods (Thuiller 2004; Araújo & New 2007; Marmion et al. 2008; Roura-Pascual et al. 2009), so that the final prediction emphasizes agreement of predictions, and model-based uncertainty can…”
Species distribution models and mitochondrial DNA phylogeography suggest an extensive biogeographical shift in the high‐intertidal seaweed Pelvetia canaliculata (2014, methodology): “The weights of each modelling method were based on the discriminatory power as measured by the mean AUC (i.e. weighted average ensemble as defined by Marmion et al., 2009).”
Identifying priority areas for reducing species vulnerability to climate change (2012, background): “Furthermore, consistent with other studies (Marmion et al., 2009a), the current climate ensemble forecast outperformed all of the individual models.”
A comprehensive evaluation of predictive performance of 33 species distribution models at species and community levels (2019, methodology): “To further examine the performance of ensemble modeling (Thuiller 2004, Marmion et al. 2009), we averaged predictions produced by the individual model variants.”
A 40‐year, continent‐wide, multispecies assessment of relevant climate predictors for species distribution modelling (2014, methodology): “These include the prediction variability stemming from the choice of modelling algorithm (Elith et al., 2006; Buisson et al., 2010), which lead to the use of ensemble forecast methods (Ara ujo & New, 2007; Marmion et al., 2009) that emphasize the central tendency of several models.”
Partitioning and mapping uncertainties in ensembles of forecasts of species turnover under climate change (2009, methodology): “In addition to ecological uncertainties, there are several sources of methodological uncertainty that have been discussed in a number of recent studies (Thuiller et al. 2004, Araújo et al. 2005a, b, Pearson et al. 2006, 2007, Marmion et al. 2009).”
Effects of the number of presences on reliability and stability of MARS species distribution models: the importance of regional niche variation and ecological heterogeneity (2010, background): “This problem can be partially solved by generating a consensus model among the different responses of a given sample size, combining information from various partial models (Araújo & New 2007; Marmion et al. 2008), which could generate even better results than a single model generated with all the a”
Will climate change reduce the efficacy of protected areas for amphibian conservation in Italy (2011, methodology): “We computed a consensus of single-model projections for each scenario using the weighted average approach, which increases significantly the accuracy of species distribution forecasts (Araújo and New, 2007; Marmion et al., 2008).”
Predicting species distribution at range margins: testing the effects of study area extent, resolution and threshold selection in the Sahara–Sahel transition zone (2014, methodology): “The 10 replicates were averaged to generate a forecast of species presence probability, which is a robust procedure to derive consensus predictions of species likelihood of presence (Marmion et al., 2009).”
Different climatic envelopes among invasive populations may lead to underestimations of current and future biological invasions (2009, methodology): “A ‘frequency histogram’ approach, with models being given equal weights, was used to create ensembles of model projections (see Marmion et al., 2009) using ArcGIS.”
Applications and future challenges in marine species distribution modeling (2011, background): “have been suggested in order to assess possible uncertainties (Araujo and New, 2007; Marmion et al., 2009; Thuiller et al., 2009).”
Species distribution models in conservation biogeography: developments and challenges (2013, methodology): “(Marmion et al., 2009) 118 Methods: compared five consensus methods for SDM”
Predicting potential distributions of invasive species: where to go from here? (2010, background): “This raises the question of selecting one given HSM or a combination of the most reliable ones (e.g. ensemble forecasting, Araújo & New, 2007; Marmion et al., 2009; Roura-Pascual et al., 2009b).”
Shifts in plant distributions in response to climate warming in a biodiversity hotspot, the Hengduan Mountains (2018, result): “We obtained generally high AUC values (Table S8); the average values for all species were between 0.72 (Agrostis hugoniana) and 0.98 (Abies delavayi), suggesting that all the modelling results are consistent and reliable (Elith et al., 2006; Marmion et al., 2009).”