Predicting Species Occurrences: Issues of Accuracy and Scale

By Nicholas Gotelli. 2003

585 citations recorded by the source corpus.

Subfields: Ecological Modeling, Ecology, Evolution, Behavior and Systematics, Genetics

View Paper: https://www.semanticscholar.org/paper/d24104a83152826e2952e71cf20c6dbf8943a162

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 Genetics

Citations in the corpus

Using species distribution models to predict new occurrences for rare plants (2009, methodology): “Methodological advances in mathematical models, machine learning and statistical tools have resulted in significant improvements in model performance (Scott et al., 2002; Guisan & Thuiller, 2005; Olden et al., 2008).”
Comparative performance of generalized additive models and multivariate adaptive regression splines for statistical modelling of species distributions (2006, methodology): “While our past experience has mostly involved use f GAMs (e.g., Elith and Burgman, 2002; Leathwick and Austin, 001), our increasing use of extensive databases has someimes resulted in very slow model fitting, and at times we ave been unable to fit GAM models to full datasets because of emory…”
Uses and misuses of bioclimatic envelope modeling. (2012, background): “2010) and the topic has seen discussion in ‘‘perspec- tives’’ articles (Araújo and Rahbek 2006, Thuiller 2007), edited books (Scott et al. 2002), and textbooks (Franklin 2009, Peterson et al. 2011).”
Climate change, genetic markers and species distribution modelling (2015, unknown): “Species distribution modelling has its roots in wildlife studies of animal–habitat associations (Scott et al., 2002) that were themselves based on a conceptual framework of the Grinnelian niche as a spatial model of animal abundance (James, 1971).”
A maximum entropy approach to species distribution modeling (2004, background): “Natural history museum and herbarium collections constitute the richest source of occurrence localities (Ponder et al., 2001; Stockwell & Peterson, 2002).”
Absent or undetected? Effects of non-detection of species occurrence on wildlife-habitat models (2004, background): “…substantial efforts have been made to examine the relationship between species occupancy and environmental and habitat covariates (e.g., Hinsley et al., 1995, Mladenoff et al., 1995, Buckland et al., 1996; Bergeron et al., 1997; Wiser et al., 1998; Odom et al., 2001; Scott et al., 2002).”
Distribution patterns of boreal marshland birds: modelling the relationships to land cover and climate (2005, background): “The level of discrimination in the models is fair to good (AUC values 0.7–0.9) or excellent (AUC values > 0.9, Pearce & Ferrier, 2000; Pearce et al., 2002) for all species included in our analyses.”
Identifying appropriate spatial scales of predictors in species distribution models with the random forest algorithm (2013, background): “However, this raises two problems: firstly, the number of possible predictors can often be large (van Horne 2002).”
The application of predictive modelling of species distribution to biodiversity conservation (2007, background): “…2003; Mace et al ., 2005), models allow for the extrapolation of relatively few field samples and museum records to the entire potential range of a species, thus creating predicted distribution maps (e.g. Guisan & Zimmermann, 2000; Heglund, 2002; Anderson et al ., 2003; Guisan & Thuiller, 2005).”
Predicting species distributions from herbarium collections: does climate bias in collection sampling influence model outcomes? (2007, methodology): “…accuracy of modelling techniques if roads directly affect the distribution of species or if the transportation network does not accurately represent the environmental conditions of the region (Kadmon et al., 2004; see also Stockwell & Peterson, 2002 for a simulation test of roadside bias).”
Assessing the effects of pseudo-absences on predictive distribution model performance (2008, methodology): “Aspect diversity was calculated by means of the Shannon Index, which estimated the aspect variation in all 1-km pixels composing each 100 km2 cell.”
Are niche‐based species distribution models transferable in space? (2006, background): “In recent years, a large number of studies have used SDMs, developed for individual species at various spatial scales (for examples see Scott et al., 2002 ).”
Spatially autocorrelated sampling falsely inflates measures of accuracy for presence‐only niche models (2009, methodology): “Although traditionally used with presence/absence data, the AUC has increasingly been advocated for use in the evaluation of environmental niche models (Fielding, 2002).”
Effects of incorporating spatial autocorrelation into the analysis of species distribution data (2007, background): “Van Horne (2002) showed that mapping eagle occurrences at a spatial scale of 1 km caused a high level of spatial autocorrelation because these birds roam distances of tens of kilometres (see Scott et al., 2002; for further examples).”