Transferability and model evaluation in ecological niche modeling: a comparison of GARP and Maxent

By A. Townsend Peterson, Monica Papes, M. Eaton. 2007

995 citations recorded by the source corpus.

Subfields: Ecological Modeling, Ecology, Nature and Landscape Conservation

View Paper: https://www.semanticscholar.org/paper/ef20e8c5c8c28ecef6c588f482caa665133ba86e

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

Does the interpolation accuracy of species distribution models come at the expense of transferability (2012, methodology): “These 10 model types have been described in detail by Stockwell and Peters (1999), Phillips et al. (2006), Olden et al.”
Accounting for multi‐scale spatial autocorrelation improves performance of invasive species distribution modelling (iSDM) (2012, background): “The potential for overfitting may limit extrapolation and transferability of Maxent models across geographical regions (Peterson et al., 2007; cf. Phillips, 2008) but leaves only a small amount of residual variation, especially in large datasets.”
Here be dragons: a tool for quantifying novelty due to covariate range and correlation change when projecting species distribution models (2014, background): “…to which an SDM is transferable to places or times different from those used for model calibration and how this limitation influences the interpretation of model results (Davis et al., 1998; Ara ujo & Guisan, 2006; Randin et al., 2006; Dormann, 2007; Peterson et al., 2007; Rocchini et al., 2011).”
The Mediterranean Sea as a ‘cul‐de‐sac’ for endemic fishes facing climate change (2010, methodology): “Because AUC (Swets, 1988) and Kappa (Cohen, 1960) methods have been severely criticized (Termansen et al., 2006; Austin, 2007; Peterson et al., 2007; Lobo et al., 2008), we based our evaluation on TSS, as recommended by Allouche et al.”
Characterizing and predicting species distributions across environments and scales: Argentine ant occurrences in the eye of the beholder (2009, background): “…environmental conditions are cause for concern given that a key goal of ENMs involves accurately predicting distributions outside the original study area and into regions that may differ strongly in their environmental conditions (Thuiller et al., 2004; Randin et al., 2006; Peterson et al., 2007).”
Global habitat suitability of cold‐water octocorals (2012, background): “The selection of environmental layers is a critical step in preparation for habitat suitability modelling because many modelling techniques are adversely affected by incorporating too many variables, potentially causing over-fitting of the model (Peterson et al., 2007).”
The effect of the extent of the study region on GIS models of species geographic distributions and estimates of niche evolution: preliminary tests with montane rodents (genus Nephelomys) in Venezuela (2010, background): “Finally, the conceptual issues and principles espoused here should also help resolve some currently controversial issues regarding characterization of the background (the study region used for model calibration) and its association with the region from which the calibration localities derive (Peters”
A strict maximum likelihood explanation of MaxEnt, and some implications for distribution modelling (2013, background): “Inferior performance of MaxEnt has only been found in a few, exceptional cases [Peterson et al. (2007), Rota et al. (2011); but see Phillips (2008)].”
Selecting predictors to maximize the transferability of species distribution models: lessons from cross‐continental plant invasions (2017, methodology): “…transferability can 67 result from many, possibly interrelated factors, such as violation of the niche conservatism 68 assumption (Broennimann et al., 2007; Early & Sax, 2014; Guisan et al., 2014) or methodological 69 limitations (Randin et al., 2006; Peterson et al., 2007; Wenger & Olden, 2012).”
Ecological niche conservatism: a time‐structured review of evidence (2011, background): “As such, direct comparisons among studies and across taxa, regions or biomes are complicated for methodological and artefactual reasons, as has been pointed out recently in several publications (Peterson et al., 2007, 2008; Lobo et al., 2008; Warren et al., 2008).”