Spatial prediction of species’ distributions from occurrence-only records: combining point pattern analysis, ENFA and regression-kriging

Abstract

A computational framework to map species' distributions (realized density) using occurrence-only data and environmental predictors is presented and illustrated using a textbook example and two case studies: distribution of root vole (Microtes oeconomus) in the Netherlands, and distribution of white-tailed eagle nests (Haliaeetus albicilla) in Croatia. The framework combines strengths of point pattern analysis (kernel smoothing), Ecological Niche Factor Analysis (ENFA) and geostatistics (logistic regression-kriging), as implemented in the spatstat, adehabitat and gstat packages of the R environment for statistical computing. A procedure to generate pseudo-absences is proposed. It uses Habitat Suitability Index (HSI, derived through ENFA) and distance from observations as weight maps to allocate pseudo-absence points. This design ensures that the simulated pseudo-absence points fall further away from the occurrence points in both feature and geographical spaces. After the pseudoabsences have been produced, they are combined with occurrence locations and used to build regression-kriging prediction models. The output of prediction are either probability of species' occurrence or density measures. Addition of the pseudoabsence locations has proven effective -the adjusted R-square increased from 0.71 to 0.80 for root vole (562 records), and from 0.69 to 0.83 for white-tailed eagle (135 records) respectively; pseudo-absences improve spreading of the points in feature space and ensure consistent mapping over the whole area of interest. Results of cross validation (leave-one-out method) for these two species showed that the model explains 98% of the total variability for the root vole, and 94% of the total variability for the white-tailed eagle. The framework could be further extended to Generalized multivariate Linear Geostatistical Models and spatial prediction of multiple species. A copy of the R script and detailed instruction on how to run such analysis are available via contact author's website.

Ecological niche modeling in Maxent: the importance of model complexity and the performance of model selection criteria

“…Therefore the poor behavior of AUC Train is approximately what would be seen if no model selection criterion was applied at all. Although AIC and AIC c have been used for ENMs before (Hao et al 2007, Dormann et al 2008, Hengl et al 2009, little information about their actual performance has been available. Here we demonstrate that they may make a valuable contribution to the toolbox of investigators using Maxent to model species distributions.…”

Integrating Archaeological Theory and Predictive Modeling: a Live Report from the Scene

“…Nevertheless, much of the theory underpinning ecological predictive models seems to be highly generalized, and still inductive modeling using linear or logistic regression methods prevails (for some examples, see Hoving et al 2004;Mathys et al 2006;Zimmermann and Breitenmoser 2007;Hengl et al 2009). In recent years, random forest models-a machine learning technique-have become more popular (e.g., Cutler et al 2007;Peters et al 2007).…”

Improving the understanding of rainfall distribution and characterisation in the Cathedral Peak catchments using a geo-statistical technique

“…Regression-Kriging has been applied widely in various fields such as climatology (Bajat et al, 2013;Tadić, 2010), soil science (Hengl et al, 2004;Omuto and Vargas, 2015;Zhu and Lin, 2010), and species distribution modelling (Meng, 2006;Hengl et al, 2009). …”