Evaluating the ability of habitat suitability models to predict species presences

By A. Hirzel, G. L. Lay, V. Helfer, C. Randin, Antoine Guisan. 2006

1,521 citations recorded by the source corpus.

Subfields: Ecological Modeling, Ecology, Nature and Landscape Conservation

View Paper: https://www.semanticscholar.org/paper/0503f4361462b9875086b98588a9265697930b27

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

Predicting the distribution of vulnerable marine ecosystems in the deep sea using presence-background models (2014, methodology): “…that the outputs of deep-sea SDMs are used carefully, and evaluated based on existing ecological knowledge, expert opinion and according to the results of the variety of methods that exist for assessing model performance (Franklin and Miller, 2009; Hirzel et al., 2006; Phillips and Elith, 2010).”
A strict maximum likelihood explanation of MaxEnt, and some implications for distribution modelling (2013, methodology): “However, MaxEnt model estimates Q = [q1, ..., qi, ..., qN]T can be interpreted as estimates of PPP if and only if the prevalence of the modelled target in the study area, i.e., the modelled targetʻs frequency of presence (Hirzel et al. 2006, Halvorsen 2012), is known.”
Uses and misuses of bioclimatic envelope modeling. (2012, methodology): “More promising approaches include those that generate predictions mainly focused at reduction of errors of omission (Peterson et al. 2008a) and focus on predictions of presences rather than absences (e.g., Hirzel et al. 2006, Phillips and Elith 2010).”
Living on the edge - modelling habitat suitability for species at the edge of their fundamental niche (2008, methodology): “The model quality was quantified using the continuous Boyce index (Hirzel et al., 2006), a threshold independent modification of the Boyce index (Boyce et al., 2002), which quantifies the relationship between the observed and expected number of validation points for different values of the HSI.”
Understanding what controls the spatial distribution of fish populations using a multi-model approach (2011, methodology): “…to as habitat models 60 (Guisan and Zimmermann, 2000), species distribution models (Guisan and Thuiller, 2005) or habitat suitability models (Hirzel et al., 2006) and their aim is to relate observations of animal presence or abundance to various attributes of the environment using a…”
Predictor complexity and feature selection affect Maxent model transferability: Evidence from global freshwater invasive species (2020, methodology): “…value will be obtained if native- and invasive-range submodels both grossly under- or overpredict suitability) Boyce Index The Continuous Boyce Index, which measures concordance between predicted habitat suitability gradients and the distribution of withheld testing points (Hirzel et al., 2006).”
Range-wide analysis of wildlife habitat: Implications for conservation (2010, methodology): “Therefore, a modification (Hirzel et al., 2006) was implemented in which the HSI was divided into 100 bins and an observed/expected frequency was calculated in each shift of a moving window of 10 continuous bins.”
Effects of Climate Change on Ticks and Tick-Borne Diseases in Europe (2009, background): “The basic concept underlying species occurrence modeling is the definition of the ecological niche: each species is found within specific ranges for environmental variables that support individual survival and reproduction [43].”
Modelling and predicting fungal distribution patterns using herbarium data (2008, methodology): “Therefore, modifying existing statistical tools and developing new methods so that herbarium data, despite their shortcomings, can be used for modelling habitat suitability, is currently a growing field (e.g. Hirzel et al., 2002, 2006; Reutter et al., 2003; Engler et al., 2004).”
Using presence‐only modelling to predict Asian elephant habitat use in a tropical forest landscape: implications for conservation (2010, methodology): “The HS model was validated using a continuous Boyce validation technique available within Biomapper software (Hirzel et al., 2006; Pearce & Boyce, 2006).”
Testing the ability of species distribution models to infer variable importance (2019, background): “CBI is the Pearson rank correlation between the ratio of binned frequencies of predictions at test occurrence sites and actual occurrences, and the ranks of the bins (Boyce et al. 2002; Hirzel et al. 2006).”
Selecting predictors to maximize the transferability of species distribution models: lessons from cross‐continental plant invasions (2017, methodology): “B was 193 computed with the bin-independent approach using a moving window along continuous predictions 194 (Hirzel et al. 2006).”
Challenges of predicting the potential distribution of a slow-spreading invader: a habitat suitability map for an invasive riparian tree (2010, neutral): “expected for a good model should show a monotonically increasing curve (Bradley et al. 2009; Hirzel et al. 2006).”
Equilibrium or not? Modelling potential distribution of invasive species in different stages of invasion (2012, methodology): “To alleviate the threshold constraint, we used an additional statistic: the continuous Boyce index (Boyce et al., 2002; Hirzel et al., 2006).”