The continuing challenges of testing species distribution models

By I. Vaughan, S. J. Ormerod. 2005

337 citations recorded by the source corpus.

Subfields: Ecological Modeling, Ecology, Nature and Landscape Conservation

View Paper: https://www.semanticscholar.org/paper/bf5e62ed66154fc6b5f2d5b124fd0b5baf837c0e

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

Non‐stationarity and local approaches to modelling the distributions of wildlife (2007, background): “However, tests for over-fitting (Vaughan & Ormerod, 2005) showed that this was not a problem (Fig.”
Prevalence, thresholds and the performance of presence–absence models (2014, methodology): “Although prevalence-independence has been regarded as a desirable property of performance metrics (Vaughan & Ormerod 2005; Allouche, Tsoar & Kadmon 2006; Lobo, Jim enez-Valverde &Real 2008), we showed that consideration of prevalence is essential to measure model calibration (the ability to…”
A comparative evaluation of presence‐only methods for modelling species distribution (2007, background): “…., 2002; Guisan & Thuiller, 2005), and evaluating the relative performance of different methods remains a continuous challenge in ecology and conservation biology (Loiselle et al ., 2003; Thuiller, 2003; Ottaviani et al ., 2004; Vaughan & Ormerod, 2005; Elith et al ., 2006; Pearson et al ., 2006).”
Random forests as a tool for ecohydrological distribution modelling (2007, methodology): “Despite its weaknesses (Vaughan and Ormerod, 2005), the Cohen’s K was repeated on the remaining training elements ( L ∗ = 811 test (Cohen, 1960) was used to evaluate differences between training elements, and L ∗ = 812 training elements).”
Modelling species distributions using regression quantiles (2007, neutral): “Model validation is also an important issue, with strong pleas for the use of robust methods for model validation to ensure outputs maps are attributed with a measure of confidence (Guisan & Zimmerman 2000; Olden, Jackson & Peres-Neto 2002; Vaughan & Ormerod 2005).”
The ghost of unbalanced species distribution data in geographical model predictions (2006, methodology): “Greater research effort aimed at improving both the quality of training data sets (Vaughan & Ormerod, 2003) and the processes of validating, and testing of models (Vaughan & Ormerod, 2005) should be made.”
Modeling natural environmental gradients improves the accuracy and precision of diatom-based indicators (2007, background): “If a model explains much less variance in the validation samples than the calibration samples when both are from the same population of stream sites, overfitting probably has occurred (Vaughan and Ormerod 2005).”
Flow regime, temperature, and biotic interactions drive differential declines of trout species under climate change (2011, background): “This was an estimate of model transferability (45, 46).”
A comparison of the performance of threshold criteria for binary classification in terms of predicted prevalence and Kappa (2008, background): “Pearce and Ferrier (2000) and Vaughan and Ormerod (2005) discuss the implications of model calibration and methods of evaluation model calibration in greater detail.”
Conserving pelagic habitats: seascape modelling of an oceanic top predator (2011, background): “…equivalent to the area under the Receiver Operating Characteristics curve (AVC) and probably the most useful measurement for distribution modelling (Vaughan & Ormerod 2005), since it allowed the comparison of the predictive performance of all three models (time spent: continuous, foraging and…”
Combining richness and abundance into a single diversity index using matrix analogues of Shannon's and Simpson's indices (2006, positive): “Although mutual information occasionally appears in measures of ecological diversity (Colwell and Futuyma 1971, Ernoult et al. 2003, Cazelles 2004, Gorelick et al. 2004, Vaughan and Ormerod 2005), it still seems to be poorly known.”