Avoiding Pitfalls of Using Species Distribution Models in Conservation Planning

By Bette A. Loiselle, Christine A. Howell, Catherine H. Graham, Jaqueline M. Goerck, T. Brooks, Kimberly G. Smith, Paul H. Williams. 2003

519 citations recorded by the source corpus.

Subfields: Ecological Modeling, Ecology, Nature and Landscape Conservation

View Paper: https://www.semanticscholar.org/paper/5e8b53736797039097c4f42c0b14a6f1a9fefa91

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

Profile or group discriminative techniques? Generating reliable species distribution models using pseudo‐absences and target‐group absences from natural history collections (2010, methodology): “3; Anderson, 2003; Loiselle et al., 2003), except in the case of Maxent, because the technique is designed to work with presence versus background data, and therefore assumes that the background data will include both absences and presences (Phillips et al., 2009).”
Predicting species distributions from herbarium collections: does climate bias in collection sampling influence model outcomes? (2007, background): “In such cases, the potential geographical distributions of species can be ‘corrected’ to reflect true distributions more accurately (e.g. Loiselle et al., 2003; Anderson & Martı́nez-Meyer, 2004).”
An evaluation of the robustness of global amphibian range maps (2014, background): “Clearly, the decision of confidence bands to be used (e.g. 95%, 80% bands) would depend on the aims of the analyses, and on the relative cost of omission versus commission errors (Loiselle et al., 2003; Rondinini et al., 2006).”
Species, Data, and Conservation Planning (2004, background): “The extraordinary, pioneering work in this field by Pressey, Cowling, and others (e.g., Cowling et al. 2003) has contributed much to tackling this problem.”
Model‐based uncertainty in species range prediction (2006, methodology): “The AUC and k have been widely applied to assess the predictive performance of species range models (e.g. Loiselle et al., 2003; Thuiller, 2003; Brotons et al., 2004; Huntley et al., 2004; Parra et al., 2004).”
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, methodology): “For example, the two presences used by Ortega-Huerta & Peterson (2004) and byMcClean et al. (2005), four by Loiselle et al. (2003) and by Cuesta-Camacho et al. (2006), or the seven to 12 presences used by Anderson & Martinez-Meyer (2004).”
Assessing the accuracy of species distribution models: prevalence, kappa and the true skill statistic (TSS) (2006, methodology): “Ecologists and conservation managers increasingly rely on predictive models as a means for estimating patterns of species distribution ( Loiselle et al . 2003; Vaughan & Ormerod 2003; Rushton, Ormerod & Kerby 2004; Sanchez-Cordero et al . 2005).”
The sizes of species’ geographic ranges (2009, background): “Again, commission errors may be reduced by intersecting predicted occurrences with, or only examining them within, the bounds to a species’ marginal occurrences ( Loiselle et al . 2003 ).”
Unprotecting the rare species: a niche‐based gap analysis for odonates in a core Cerrado area (2011, background): “…et al., 2007; de Siqueira et al., 2009; De Almeida et al., 2010), the prediction of areas prone to biological invasions (Broennimann et al., 2007), gap analysis (Jimenez et al., 2005; Martinez et al., 2006) and the establishment of conservation priorities (Loiselle et al., 2003; Ko et al., 2009).”
Distribution modelling and statistical phylogeography: an integrative framework for generating and testing alternative biogeographical hypotheses (2007, methodology): “Ultimately, the choice of modelling algorithm should be based on both the resulting distribution estimate’s intended use and the available data (Fielding & Bell, 1997; Loiselle et al., 2003; Graham et al., 2004b; Elith et al., 2006).”
Planning for Climate Change: Identifying Minimum‐Dispersal Corridors for the Cape Proteaceae (2005, background): “Area selection is known to be sensitive to the choice of suitability model (Loiselle et al. 2003), but as yet we have no data with which to explore the effects of inadequacies in the models for the Cape Proteaceae.”
Environmental Niche Equivalency versus Conservatism: Quantitative Approaches to Niche Evolution (2008, background): “…establishing such thresholds have been proposed (Fielding and Bell 1997; Liu et al. 2005; Jiménez-Valverde and Lobo 2007), measures of niche overlap can be sensitive to this decision (Supporting Appendix S1, also see Loiselle et al. 2003 for a similar phenomenon regarding predicted distributions).”
Sample selection bias and presence-only distribution models: implications for background and pseudo-absence data. (2009, background): “Species distribution modeling (SDM) is an important tool for both conservation planning and theoretical research on ecological and evolutionary processes (Loiselle et al. 2003, Kozak et al. 2008).”
Assessing the effects of pseudo-absences on predictive distribution model performance (2008, background): “e c o l o g i c a l m o d e l l i n g 2 1 0 ( 2 0 0 8 ) 478–486 avai lab le at www.sc iencedi rec t .com journa l homepage: www.e lsev ier .com/ locate /eco lmodel Assessing the effects of pseudo-absences on predictive distribution model performance”