Measuring the relative effect of factors affecting species distribution model predictions

By Emeric Thibaud, B. Petitpierre, O. Broennimann, A. C. Davison, Antoine Guisan. 2014

126 citations recorded by the source corpus.

Subfields: Ecological Modeling, Ecology, Nature and Landscape Conservation

View Paper: https://www.semanticscholar.org/paper/674c72384e5e1e50a23bbde935d073f08159db06

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

1. Wilfried Thuiller
2. Antoine Guisan
3. Jane Elith
4. Janet Franklin
5. A. Townsend Peterson
6. Miguel B. Araújo
7. N. E. Zimmermann
8. Miska Luoto

In Ecology

1. Wilfried Thuiller
2. Antoine Guisan
3. Jane Elith
4. Janet Franklin
5. Miska Luoto
6. Miguel B. Araújo
7. N. E. Zimmermann
8. A. Townsend Peterson

In Nature and Landscape Conservation

1. Wilfried Thuiller
2. Antoine Guisan
3. Jane Elith
4. Miguel B. Araújo
5. Janet Franklin
6. A. Townsend Peterson
7. N. E. Zimmermann
8. Miska Luoto

Citations in the corpus

• A comparison between Ensemble and MaxEnt species distribution modelling approaches for conservation: A case study with Egyptian medicinal plants (2020, methodology): “Thibaud et al. (2014) suggested that MaxEnt outperformed traditional presence-absence approaches, but Guillera-Arroita et al. (2014) demonstrated that presence-absence approaches such as GLM can predict well using small sample sizes if properly analysed, emphasizing that presence-absence is a more…”
• Testing the ability of species distribution models to infer variable importance (2019, methodology): “As a result, models calibrated on small samples are likely to have highly variable performance (Kadmon et al 2003; Hernandez et al. 2006; Thibaud et al. 2014; Soultan & Safi 2017), and thus by inference, less ability to measure variable importance.”
• Identifying predictable foraging habitats for a wide‐ranging marine predator using ensemble ecological niche models (2015, methodology): “However, we note that the use of multiple performance metrics in EENM construction and evaluation is clearly preferable to any single metric (Allouche et al., 2006; Jim enez-Valverde, 2012; Thibaud et al., 2014).”
• A comprehensive evaluation of predictive performance of 33 species distribution models at species and community levels (2019, methodology): “…species occurrence, decreasing predictive power both for interpolation as well as extrapolation (predictions made for dissimilar environmental conditions or different region as data used for model fitting; Diniz-Filho et al. 2003, Diggle and Ribeiro 2007, Fieberg et al. 2010, Thibaud et al. 2014).”
• Effects of spatial autocorrelation and imperfect detection on species distribution models (2018, background): “Some authors have claimed that spatial autocorrelation is not a big problem in ecology and especially in SDMs (Hawkins, 2012; Thibaud et al., 2014).”