The ghost of past species occurrence: improving species distribution models for presence-only data

By M. Lütolf, F. Kienast, Antoine Guisan. 2006

107 citations recorded by the source corpus.

Subfields: Ecological Modeling, Ecology, Evolution, Behavior and Systematics, Nature and Landscape Conservation

View Paper: https://www.semanticscholar.org/paper/dc6ada473282823c27d33b99fd9079b2b6f7333b

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, Evolution, Behavior and Systematics

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): “We hypothesize that these TGAs should be more discriminatory than pseudo-absences, and would result in more reliable models (Lütolf et al., 2006).”
Predicting species distributions from museum and herbarium records using multiresponse models fitted with multivariate adaptive regression splines (2007, background): “Although this approach to absence selection is uncommon (but see Lütolf et al ., 2006; Ferrier et al ., 2007), consideration of the nature of presence-only samples indicates that it may have strong practical advantages.”
Sample selection bias and presence-only distribution models: implications for background and pseudo-absence data. (2009, methodology): “While some studies explore this idea (e.g., Zaniewski et al. 2002, Engler et al. 2004, Lütolf et al. 2006), the ecological literature lacks a coherent theoretical exploration, and the proposed solutions seem to represent different and probably incompatible reasoning.”
Ecology of butterflies in Europe (2009, methodology): “These comprise strategies to select pseudo-absence data (Lütolf et al., 2006), environmental niche factor analysis (ENFA as realised”
Exploring the effects of quantity and location of pseudo-absences and sampling biases on the performance of distribution models with limited point occurrence data (2011, methodology): “Thus, as this type of pseudo-absence selection improves the results at lower relative occurrence areas, we suggest using this strategy for selecting pseudo-absence when there are no better alternatives for obtaining reliable absence data (see for example Lütolf et al. 2006).”
Invasive species distribution modeling (iSDM): Are absence data and dispersal constraints needed to predict actual distributions? (2009, methodology): “Although previous studies sug ested that more reliable pseudo-absence data can be derived from reas with unsuitable environmental conditions identified with the se of profile (presence-only) techniques (Zaniewski et al., 2002; ngler et al., 2004; Lutolf et al., 2006), this approach may only be ppro”
Species Distribution Modeling in the Tropics: Problems, Potentialities, and the Role of Biological Data for Effective Species Conservation (2009, background): “Reference Region Scope Verification Taxon Data1 Allouche et al. (2006) Israel Methodological Informal validation Plants P Anadón et al. (2007) Spain Species conservation Same data Reptiles P-A Anderson et al. (2002) Ecuador, Colombia, Venezuela Biogeography Partitioning Mammals P Araújo et al. (2005”
Dealing with uncertain absences in habitat modelling: a case study of a rare ground‐dwelling parrot (2007, methodology): “…addressing the use of presence-only data for modelling species distributions (Pearce & Boyce, 2006; Elith et al ., 2006; Hirzel et al ., 2006; Lütolf et al ., 2006; Olivier & Wotherspoon, 2006; Pearson et al ., 2006; Phillips et al ., 2006) with methods falling into two broad categories: (1)…”
Assessing the effect of prevalence on the predictive performance of species distribution models using simulated data (2011, methodology): “A performance measure that is in common use is AUC (Lütolf et al., 2006; Brotons et al., 2007; Graham et al., 2007; Jewell et al., 2007).”
The Effects of Sampling Bias and Model Complexity on the Predictive Performance of MaxEnt Species Distribution Models (2013, background): “A number of other studies have shown the importance of the background data selection method through a variety of SDM techniques [19,20,21,22,23,52] and studies have begun to also evaluate MaxEnt [12,14,53,54,55].”