An improved approach for predicting the distribution of rare and endangered species from occurrence and pseudo-absence data

By Robin Engler, Antoine Guisan, Luca Rechsteiner. 2004

998 citations recorded by the source corpus.

Subfields: Ecological Modeling, Ecology, Nature and Landscape Conservation

View Paper: https://www.semanticscholar.org/paper/9d4788ccd97e93fb6ac1dad9c2e9d52b1f510f20

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

Predicting species distributions: a critical comparison of the most common statistical models using artificial species (2007, background): “Increasing sampling size guided by habitat modelling in an iterative process would certainly increase model performance (Engler et al., 2004; Reese et al., 2005; Guisan et al., 2006).”
The effect of spatial resolution on projected responses to climate warming (2012, background): “…models, along with the fact that finer resolution models have been found to perform better than coarser ones in predicting species’ distributions (Engler et al., 2004), leads us to conclude that more modelling should be carried out at a range of resolutions across different taxa and regions, at…”
A framework for species distribution modelling with improved pseudo-absence generation (2015, methodology): “Group discrimi-10 2 nation techniques have gained popularity in recent years, as they have been11 reported to yield better results than profile techniques (Engler et al., 2004;12 Chefaoui and Lobo, 2008; Elith and et al, 2006; Mateo et al., 2010).”
Use of niche models in invasive species risk assessments (2011, background): “On one hand, if the presence localities are not drawn from exhaustive environmental and spatial sampling efforts, biases with respect to environmental dimensions will certainly exist (see, e.g., Hirzel et al. 2001; Zaniewski et al. 2002; Engler et al. 2004; Kadmon et al. 2004; Hortal and Lobo 2005; ”
Threshold criteria for conversion of probability of species presence to either–or presence–absence (2007, methodology): “However, these methods are useful because reliable absence data are seldom available (MacKenzie et al., 2002; Wintle et al., 2005; but see, for example, Engler et al., 2004; Lobo et al., 2006, for ways of generating probable absences).”
Do pseudo-absence selection strategies influence species distribution models and their predictions? An information-theoretic approach based on simulated data (2009, methodology): “[18]: pseudo-absence selection clearly influences model fit as measured by the percent of deviance explained.”
Ecological niche modelling as a technique for assessing threats and setting conservation priorities for Asian slow lorises (Primates: Nycticebus) (2009, background): “…2000; Hirzel et al ., 2002; Brotons et al ., 2004; Elith et al ., 2006; Phillips et al ., 2006; Gibson et al ., 2007), particularly when the taxa are rare or cryptic, or biotic or human-induced factors prevent colonization of all suitable habitat areas (Hirzel et al ., 2001; Engler et al ., 2004).”
Modelling breeding habitat preferences of Bonelli’s eagle (Hieraaetus fasciatus) in relation to topography, disturbance, climate and land use at different spatial scales (2005, methodology): “…(GAMs) (Guisan et al. 2002; Seoane et al. 2004), neural networks (Hagan et al. 1996; Haykin 1999) and the recent developed ecological niche factor analysis (ENFA) (Engler et al. 2004) implemented in the Biomapper package (Hirzel et al. 2002), would probably perform with the data of this study.”
Using species distribution models in paleobiogeography: A matter of data, predictors and concepts (2011, background): “…areas where the species has not been recorded or the environmental conditions are a priori unsuitable (Ferrier andWatson, 1997; Zaniewski et al., 2002; Engler et al., 2004; Lobo et al., 2006) or simply chosen at random from the entire study area (Stockwell and Peters, 1999; Elith et al., 2006).”
GIS-based modeling of Javan Hawk-Eagle distribution using logistic and autologistic regression models (2008, methodology): “…data are available, one approach is to generate ‘‘pseudo-absence’’ data from background areas from which species data are missing (Stockwell and Peterson, 2002a; Zaniewski et al., 2002; Engler et al., 2004; Pearce and Boyce, 2006) and use them in the model as absence data for the relevant species.”
Prospective sampling based on model ensembles improves the detection of rare species (2010, background): “At a fine resolution, some coarse observations have to be discarded, possibly resulting in a reduced sample size and a loss of important ecological information (Engler et al. 2004).”
The influence of spatial errors in species occurrence data used in distribution models (2007, background): “A fourth area of suggested research deals with when and how to use inaccurate data, given that data with a relatively large error footprint/uncertainty may degrade models ( Engler, Guisan & Rechsteiner 2004 ).”
Use of Maximum Entropy Modeling in Wildlife Research (2009, neutral): “worse than random [15].”
Modelling potential distribution of the threatened tree species Juniperus oxycedrus: how to evaluate the predictions of different modelling approaches? (2011, background): “Prediction success can be measured with the minimal predicted area (MPA), which includes 90% of the known species occurrences, and all pixels with predictions above a defined probability threshold (Engler et al. 2004).”
Maxent modeling for predicting suitable habitat for threatened and endangered tree Canacomyrica monticola in New Caledonia (2009, methodology): “But distribution data on threatened and endangered species are often sparse (Ferrier et al., 2002; Engler et al., 2004) and clustered making commonly used habitat modeling approaches difficult.”
AUC: a misleading measure of the performance of predictive distribution models (2008, background): “In species distribution research, it has been proposed that ‘invented’ absences from environmentally distant areas be used as pseudo-absences (Engler et al ., 2004; Lobo et al ., 2006).”