Selecting thresholds for the prediction of species occurrence with presence‐only data

By Canran Liu, Matt D. White, G. Newell. 2013

1,471 citations recorded by the source corpus.

Subfields: Ecological Modeling, Ecology, Nature and Landscape Conservation

View Paper: https://www.semanticscholar.org/paper/7ab1db1014d4141b8d0c5ff7b7e441120fb5592d

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

Climate change amplifies plant invasion hotspots in Nepal (2019, background): “Furthermore, the IAPs benefit from global warming and atmospheric CO2 enrichment more than native plants (Liu et al., 2013; Verlinden & Nijs, 2010).”
On the selection of thresholds for predicting species occurrence with presence‐only data (2015, methodology): “2005), has been proved valid to use with presence-only data when random points are used instead of true absences, where sensitivity is the proportion of correctly predicted presences among all the presences (which is also called recall in other fields), and specificity is the proportion of correctly”
Two alternative evaluation metrics to replace the true skill statistic in the assessment of species distribution models (2019, methodology): “For these reasons, whereas maximising TSS may be instrumental when presence-absence thresholds are required (Liu et al. 2013), TSS may not perform well in presence-background model evaluations (Somodi et al.”
Niche breadth and geographic range size as determinants of species survival on geological time scales (2015, methodology): “On average, this method produces broader niche estimates when prevalence is low to moderate compared to the LTP method (Liu et al., 2013).”
Evaluating correlative and mechanistic niche models for assessing the risk of pest establishment (2014, background): “More details about different threshold selection for presence-only models are discussed by Liu et al. (2013).”
Creating individual accessible area hypotheses improves stacked species distribution model performance (2018, background): “Instead, fixed presence thresholds were chosen to reflect confidence in data quality and comparatively higher certainty of presence over absence localities (Liu et al., 2013; Peterson et al., 2011).”
Using species distribution models to inform IUCN Red List assessments (2014, background): “Traditionally, threshold probabilities are chosen in a way that maximizes the discrimination of sites with known presences from the rest of the landscape, or from locations with known absences (Franklin 2009; Liu et al. 2005; Liu et al. 2013).”