Selecting pseudo-absence data for presence-only distribution modeling: How far should you stray from what you know?

By Jeremy VanDerWal, L. Shoo, Catherine H. Graham, S. Williams. 2009

883 citations recorded by the source corpus.

Subfields: Ecological Modeling, Ecology, Nature and Landscape Conservation

View Paper: https://www.semanticscholar.org/paper/560e7242d55cb11f54924285207f497e24e2edc0

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

Ongoing invasions of the African clawed frog, Xenopus laevis: a global review (2012, background): “building (VanDerWal et al. 2009).”
Biotic interactions influence the projected distribution of a specialist mammal under climate change (2012, background): “A buffer of this size is optimal for our study region (VanDerWal et al., 2009) and was selected so that subtle changes in suitability could be detected at fine scales.”
Optimizing resiliency of reserve networks to climate change: multispecies conservation planning in the Pacific Northwest, USA (2010, background): “However, high AUC values for localized species models may be due in part to their restricted range in comparison to the extent of the analysis area (VanDerWal et al., 2009).”
Extent and fragmentation of suitable leopard habitat in South Africa (2013, background): “While the extent of the subsampled background region can affect the MaxEnt solution (VanDerWal et al., 2009), we did not restrict the background region in our analyses because leopards occur widely throughout South Africa (Dalerum et al., 2008).”
Using district-level occurrences in MaxEnt for predicting the invasion potential of an exotic insect pest in India (2014, background): “We dealt with some of these issues by dropping highly correlated variables to reduce multicollinearity effects and by training our model using background points from only nine cotton growing states.”
MaxEnt versus MaxLike: empirical comparisons with ant species distributions (2013, methodology): “Approaches for accounting for such sampling bias, including strategies for the selection of background points, are relatively well developed for MaxEnt (e.g., Phillips et al. 2009, VanDerWal et al. 2009), but remain unexplored for MaxLike.”
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): “The influence of ROA in model distribution performance requires further investigation (but see Bulluck et al. 2006 and VanDerWal et al. 2009).”
Environmental factors influencing the spread of the highly pathogenic avian influenza H5N1 virus in wild birds in Europe (2010, background): “Absences drawn from too small an area can produce spurious models, while absences drawn from too large an area can lead to artificially inflated test statistics as well as potentially less informative response variables (VanDerWal et al. 2009).”
Extinction risk of North American seed plants elevated by climate and land‐use change (2017, background): “Based on a study on Australian vertebrates by VanDerWal et al. (2009), a 200- km buffer has been recommended as an ‘optimal’ distance to produce models that both generalize well across a range of environmental conditions and do not overinflate predicted distributions at finer environmental…”