Accounting for spatially biased sampling effort in presence‐only species distribution modelling

By J. Stolar, Scott E. Nielsen. 2015

174 citations recorded by the source corpus.

Subfields: Cell Biology, Ecological Modeling, Nature and Landscape Conservation

View Paper: https://www.semanticscholar.org/paper/f68dc88505576afc37fbb4e0477d4cbbf971c9be

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cell Biology

1. Janet Franklin
2. Kenneth E. Nussear
3. Richard D. Inman
4. Todd C. Esque

In Ecological Modeling

1. Janet Franklin
2. James E. M. Watson
3. Christopher M Thomas
4. Brian Huntley
5. J. Pearce‐Higgins
6. R. A. Garcia
7. H. Resit Akçakaya
8. A. Hoffmann

In Nature and Landscape Conservation

1. Janet Franklin
2. Christopher M Thomas
3. James E. M. Watson
4. J. Secondi
5. Yoan Fourcade
6. Brian Huntley
7. J. Pearce‐Higgins
8. R. A. Garcia

Citations in the corpus

• Paintings predict the distribution of species, or the challenge of selecting environmental predictors and evaluation statistics (2018, background): “Previous studies have already shown that AUC cannot provide an efficient measure of SDM performance (Jim enez-Valverde, 2014; Lobo et al., 2008; Smith, 2013), and especially that it does not inform about models’ biological significance (Fourcade et al., 2014; Stolar & Nielsen, 2015).”
• Improving species distribution model predictive accuracy using species abundance: Application with boosted regression trees (2020, background): “Further, Stolar and Nielsen (2015) improved model performance dealing with spatially biased sampling by adding a weighting term in the logistic regression.”
• Climate change vulnerability assessment of species (2018, background): “…include Bayesian approaches (Manceur & Kühn, 2014; Rocchini et al., 2017), subsampling in geographic space (Aiello-Lammens et al., 2015) or in environmental space (Varela, Anderson, & Fernández-González, 2014), and weighting presences by the inverse of their density (Stolar & Nielsen, 2015).”
• Comparing sample bias correction methods for species distribution modeling using virtual species (2021, methodology): “…studies suggesting that G-Filter methods may outperform the FactorBiasOut method in some instances (KramerSchadt et al. 2013, Fourcade et al. 2014, Stolar and Nielsen 2015), but others showing E-Filter methods as superior to G-Filter methods when using climatic variables (Varela et al. 2014), or…”