Species Distribution Modeling: Comparison of Fixed and Mixed Effects Models Using INLA

Abstract

Abstract:Invasive alien species are among the most important, least controlled, and least reversible of human impacts on the world's ecosystems, with negative consequences affecting biodiversity and socioeconomic systems. Species distribution models have become a fundamental tool in assessing the potential spread of invasive species in face of their native counterparts. In this study we compared two different modeling techniques: (i) fixed effects models accounting for the effect of ecogeographical variables (EGVs); and (ii) mixed effects models including also a Gaussian random field (GRF) to model spatial correlation (Matérn covariance function). To estimate the potential distribution of Pittosporum undulatum and Morella faya (respectively, invasive and native trees), we used geo-referenced data of their distribution in Pico and São Miguel islands (Azores) and topographic, climatic and land use EGVs. Fixed effects models run with maximum likelihood or the INLA (Integrated Nested Laplace Approximation) approach provided very similar results, even when reducing the size of the presences data set. The addition of the GRF increased model adjustment (lower Deviance Information Criterion), particularly for the less abundant tree, M. faya. However, the random field parameters were clearly affected by sample size and species distribution pattern. A high degree of spatial autocorrelation was found and should be taken into account when modeling species distribution.

Limitations of Species Distribution Models Based on Available Climate Change Data: A Case Study in the Azorean Forest

“…The canopy is pyramidal, 3-5 m in diameter, the leaves are evergreen, ovate, and with a wavy margin, and shows white-creamy perfumed flowers in loose umbellate cymes that bear one to four insect pollinated flowers [85][86][87][88][89]. It is widespread in the three islands but especially in Pico Island [71,74,[90][91][92].…”

Species distribution models and empirical test: Comparing predictions with well‐understood geographical distribution of Bothrops alternatus in Argentina

“…In this case, B. alternatus 's home‐range is usually not very wide and there are areas within its distribution (the Pampean hills in Buenos Aires province) where the species presents environmental differences in the presence/absence at 1 km resolution in its distribution (Bellini et al., ; Giraudo, ; Giraudo & Arzamendia, ; Giraudo et al., ; Scrocchi et al., ). We performed a Spearman correlation test in order to get the least collinear predictor subset using Infostat 5.1 (Di Rienzo et al., ). We chose variables with a correlation value lower than 0.7 and confirmed the selection of the variables with the knowledge about the natural history of the species (Bellini et al., ; Giraudo, ; Giraudo et al., ; Scrocchi et al., ) (Supporting Information ).…”

“…These issues need to be further analyzed with others focuses. Recently, advances approaches were developed most of them through the Bayesian approach, that has become a good option to deal when the distribution of the species is modeled using pointreferences data due to the ease with which prior information can be incorporated along with the fact that it provides a more realistic and accurate estimation of uncertainty (DutraSilva, Brito de Azevedo, Bento Elias, & Silva, 2017;Martínez-Minaya, Cameletti, Conesa, & Pennino, 2018;Rodríguez de Rivera & López-Quílez, 2017). So, more studies testing and comparing ED, FGM, and Bayesian approach are need it, even if our study was not focuses on recent developed Bayesian approach (see Martínez-Minaya et al, 2018 for a revision).…”

Assessing the Spatial and Spatio-Temporal Distribution of Forest Species via Bayesian Hierarchical Modeling

“…Other studies have been developed to understand species distribution through a Bayesian approach using INLA, i.e., [58] analyzing the spatial distribution of caribou, or [59] analyzing the presence of invasive species and shrubs in Azores. One of the most interesting differences for our case is the temporal approach, as we work with data from three different inventories.…”