Non-stationarity and local approaches to modelling the distributions of wildlife

Despite a growing interest in species distribution modelling, relatively little attention has been paid to spatial autocorrelation and non-stationarity. Both spatial autocorrelation (the tendency for adjacent locations to be more similar than distant ones) and non-stationarity (the variation in modelled relationships over space) are likely to be common properties of ecological systems. This paper focuses on non-stationarity and uses two local techniques, geographically weighted regression (GWR) and varying coefficient modelling (VCM), to assess its impact on model predictions. We extend two published studies, one on the presence–absence of calandra larks in Spain and the other on bird species richness in Britain, to compare GWR and VCM with the more usual global generalized linear modelling (GLM) and generalized additive modelling (GAM). For the calandra lark data, GWR and VCM produced better-fitting models than GLM or GAM. VCM in particular gave significantly reduced spatial autocorrelation in the model residuals. GWR showed that individual predictors became stationary at different spatial scales, indicating that distributions are influenced by ecological processes operating over multiple scales. VCM was able to predict occurrence accurately on independent data from the same geographical area as the training data but not beyond, whereas the GAM produced good results on all areas. Individual predictions from the local methods often differed substantially from the global models. For the species richness data, VCM and GWR produced far better predictions than ordinary regression. Our analyses suggest that modellers interpolating data to produce maps for practical actions (e.g. conservation) should consider local methods, whereas they should not be used for extrapolation to new areas. We argue that local methods are complementary to global methods, revealing details of habitat associations and data properties which global methods average out and miss.     

Improving generalized regression analysis for the spatial prediction of forest communities

Aim This study used data from temperate forest communities to assess: (1) five different stepwise selection methods with generalized additive models, (2) the effect of weighting absences to ensure a prevalence of 0.5, (3) the effect of limiting absences beyond the environmental envelope defined by presences, (4) four different methods for incorporating spatial autocorrelation, and (5) the effect of integrating an interaction factor defined by a regression tree on the residuals of an initial environmental model. Location State of Vaud, western Switzerland. Methods Generalized additive models (GAMs) were fitted using the grasp package (generalized regression analysis and spatial predictions, http://www.cscf.ch/grasp ). Results Model selection based on cross‐validation appeared to be the best compromise between model stability and performance (parsimony) among the five methods tested. Weighting absences returned models that perform better than models fitted with the original sample prevalence. This appeared to be mainly due to the impact of very low prevalence values on evaluation statistics. Removing zeroes beyond the range of presences on main environmental gradients changed the set of selected predictors, and potentially their response curve shape. Moreover, removing zeroes slightly improved model performance and stability when compared with the baseline model on the same data set. Incorporating a spatial trend predictor improved model performance and stability significantly. Even better models were obtained when including local spatial autocorrelation. A novel approach to include interactions proved to be an efficient way to account for interactions between all predictors at once. Main conclusions Models and spatial predictions of 18 forest communities were significantly improved by using either: (1) cross‐validation as a model selection method, (2) weighted absences, (3) limited absences, (4) predictors accounting for spatial autocorrelation, or (5) a factor variable accounting for interactions between all predictors. The final choice of model strategy should depend on the nature of the available data and the specific study aims. Statistical evaluation is useful in searching for the best modelling practice. However, one should not neglect to consider the shapes and interpretability of response curves, as well as the resulting spatial predictions in the final assessment.     

Spatial autocorrelation in predictors reduces the impact of positional uncertainty in occurrence data on species distribution modelling

Aim To investigate the impact of positional uncertainty in species occurrences on the predictions of seven commonly used species distribution models (SDMs), and explore its interaction with spatial autocorrelation in predictors. Methods A series of artificial datasets covering 155 scenarios including different combinations of five positional uncertainty scenarios and 31 spatial autocorrelation scenarios were simulated. The level of positional uncertainty was defined by the standard deviation of a normally distributed zero‐mean random variable. Each dataset included two environmental gradients (predictor variables) and one set of species occurrence sample points (response variable). Seven commonly used models were selected to develop SDMs: generalized linear models, generalized additive models, boosted regression trees, multivariate adaptive regression spline, random forests, genetic algorithm for rule‐set production and maximum entropy. A probabilistic approach was employed to model and simulate five levels of error in the species locations. To analyse the propagation of positional uncertainty, Monte Carlo simulation was applied to each scenario for each SDM. The models were evaluated for performance using simulated independent test data with Cohen’s Kappa and the area under the receiver operating characteristic curve. Results Positional uncertainty in species location led to a reduction in prediction accuracy for all SDMs, although the magnitude of the reduction varied between SDMs. In all cases the magnitude of this impact varied according to the degree of spatial autocorrelation in predictors and the levels of positional uncertainty. It was shown that when the range of spatial autocorrelation in the predictors was less than or equal to three times the standard deviation of the positional error, the models were less affected by error and, consequently, had smaller decreases in prediction accuracy. When the range of spatial autocorrelation in predictors was larger than three times the standard deviation of positional error, the prediction accuracy was low for all scenarios. Main conclusions The potential impact of positional uncertainty in species occurrences on the predictions of SDMs can be understood by comparing it with the spatial autocorrelation range in predictor variables.     

Generalized models vs. classification tree analysis: Predicting spatial distributions of plant species at different scales

Abstract. Statistical models of the realized niche of species are increasingly used, but systematic comparisons of alternative methods are still limited. In particular, only few studies have explored the effect of scale in model outputs. In this paper, we investigate the predictive ability of three statistical methods (generalized linear models, generalized additive models and classification tree analysis) using species distribution data at three scales: fine (Catalonia), intermediate (Portugal) and coarse (Europe). Four Mediterranean tree species were modelled for comparison. Variables selected by models were relatively consistent across scales and the predictive accuracy of models varied only slightly. However, there were slight differences in the performance of methods. Classification tree analysis had a lower accuracy than the generalized methods, especially at finer scales. The performance of generalized linear models also increased with scale. At the fine scale GLM with linear terms showed better accuracy than GLM with quadratic and polynomial terms. This is probably because distributions at finer scales represent a linear sub‐sample of entire realized niches of species. In contrast to GLM, the performance of GAM was constant across scales being more data‐oriented. The predictive accuracy of GAM was always at least equal to other techniques, suggesting that this modelling approach is more robust to variations of scale because it can deal with any response shape.     

Modelling the occurrence of threatened plant species in taiga landscapes: methodological and ecological perspectives

Aim Understanding the spatial patterns of species distribution and predicting the occurrence of high biological diversity and rare species are central themes in biogeography and environmental conservation. The aim of this study was to model and scrutinize the relative contributions of climate, topography, geology and land‐cover factors to the distributions of threatened vascular plant species in taiga landscapes in northern Finland. Location North‐east Finland, northern Europe. Methods The study was performed using a data set of 28 plant species and environmental variables at a 25‐ha resolution. Four different stepwise selection algorithms [Akaike information criterion (AIC), Bayesian information criterion (BIC), adaptive backfitting, cross selection] with generalized additive models (GAMs) were fitted to identify the main environmental correlates for species occurrences. The accuracies of the distribution models were evaluated using fourfold cross‐validation based on the area under the curve (AUC) derived from receiver operating characteristic plots. The GAMs were tentatively extrapolated to the whole study area and species occurrence probability maps were produced using GIS techniques. The effect of spatial autocorrelation on the modelling results was also tested by including autocovariate terms in the GAMs. Results According to the AUC values, the model performance varied from fair to excellent. The AIC algorithm provided the highest mean performance (mean AUC = 0.889), whereas the lowest mean AUC (0.851) was obtained from BIC. Most of the variation in the distribution of threatened plant species was related to growing degree days, temperature of the coldest month, water balance, cover of mire and mean elevation. In general, climate was the most powerful explanatory variable group, followed by land cover, topography and geology. Inclusion of the autocovariate only slightly improved the performance of the models and had a minor effect on the importance of the environmental variables. Main conclusions The results confirm that the landscape‐scale distribution patterns of plant species can be modelled well on the basis of environmental parameters. A spatial grid system with several environmental variables derived from remote sensing and GIS data was found to produce useful data sets, which can be employed when predicting species distribution patterns over extensive areas. Landscape‐scale maps showing the predicted occurrences of individual or multiple threatened plant species may provide a useful basis for focusing field surveys and allocating conservation efforts.     

Scaling down distribution maps from atlas data: a test of different approaches with virtual species

Aim Conservation managers are increasingly looking for modelled projections of species distributions to inform management strategies; however, the coarse resolution of available data usually compromises their helpfulness. The aim of this paper is to delineate and test different approaches for converting coarse‐grain occurrence data into high‐resolution predictions, and to clarify the conceptual circumstances affecting the accuracy of downscaled models. Location We used environmental data from a real landscape, southern Africa, and simulated species distributions within this landscape. Methods We built 10 virtual species at a resolution of 5 arcmin, and for each species we simulated atlas range maps at four decreasing resolutions (15, 30, 60, 120 arcmin). We tested the ability of three downscaling strategies to produce high‐resolution predictions using two modelling techniques: generalized linear models and generalized boosted models. We calibrated reference models with high‐resolution data and we compared the relative reduction of predictive performance in the downscaled models by using a null model approach. We also estimated the applicability of downscaling procedures to different situations by using distribution data for Mediterranean reptiles. Results All reference models achieved high performance measures. For all strategies, we observed a reduction of predictive performance proportional to the degree of downscaling. The differences in evaluation indices between reference models and downscaled projections obtained from atlases at 15 and 30 arcmin were never statistically significant. The accuracy of projections scaled down from 60 arcmin largely depended on the combination of approach and algorithm adopted. Projections scaled down from 120 arcmin gave misleading results in all cases. Main conclusions Moderate levels of downscaling allow for reasonably accurate results, regardless of the technique used. The most general effect of scaling down coarse‐grain data is the reduction of model specificity. The models can successfully delineate a species’ environmental association up until a 12‐fold downscaling, although with an increasing approximation that causes the overestimation of true distributions. We suggest appropriate procedures to mitigate the commission error introduced by downscaling at intermediate levels (approximately 12‐fold). Reductions of grain size > 12‐fold are discouraged.     

Updating bird species distribution at large spatial scales: applications of habitat modelling to data from long-term monitoring programs

Mapping of species distributions at large spatial scales has been often based on the representation of gathered observations in a general grid atlas framework. More recently, subsampling and subsequent interpolation or habitat spatial modelling techniques have been incorporated in these projects to allow more detailed species mapping. Here, we explore the usefulness of data from long-term monitoring (LTM) projects, primarily aimed at estimating trends in species abundance and collected at shorter time intervals (usually yearly) than atlas data, to develop predictive habitat models. We modelled habitat occupancy for 99 species using a bird LTM program and evaluated the predictive accuracy of these models using independent data from a contemporary and comprehensive breeding bird atlas project from the same region. Habitat models from LTM data using generalized linear modelling were significant for all the species and generally showed a high predictive power, albeit lower than that from atlas models. Sample size and species range size and niche breadth were the most important factors behind variability in model predictive accuracy, whereas the spatial distribution of sampling units at a given sample size had minor effects. Although predictive accuracy of habitat modelling was strongly species dependent, increases in sample size and, secondarily, a better spatial distribution of sampling units should lead to more powerful predictive distribution models. We suggest that data from LTM programs, now established in a large number of countries, has the potential for being a major source of good quality data suitable for the estimation and regularly update of distributions at large spatial scales for a number of species.     

Effect of species rarity on the accuracy of species distribution models for reptiles and amphibians in southern California

Aim Several studies have found that more accurate predictive models of species’ occurrences can be developed for rarer species; however, one recent study found the relationship between range size and model performance to be an artefact of sample prevalence, that is, the proportion of presence versus absence observations in the data used to train the model. We examined the effect of model type, species rarity class, species’ survey frequency, detectability and manipulated sample prevalence on the accuracy of distribution models developed for 30 reptile and amphibian species. Location Coastal southern California, USA. Methods Classification trees, generalized additive models and generalized linear models were developed using species presence and absence data from 420 locations. Model performance was measured using sensitivity, specificity and the area under the curve (AUC) of the receiver‐operating characteristic (ROC) plot based on twofold cross‐validation, or on bootstrapping. Predictors included climate, terrain, soil and vegetation variables. Species were assigned to rarity classes by experts. The data were sampled to generate subsets with varying ratios of presences and absences to test for the effect of sample prevalence. Join count statistics were used to characterize spatial dependence in the prediction errors. Results Species in classes with higher rarity were more accurately predicted than common species, and this effect was independent of sample prevalence. Although positive spatial autocorrelation remained in the prediction errors, it was weaker than was observed in the species occurrence data. The differences in accuracy among model types were slight. Main conclusions Using a variety of modelling methods, more accurate species distribution models were developed for rarer than for more common species. This was presumably because it is difficult to discriminate suitable from unsuitable habitat for habitat generalists, and not as an artefact of the effect of sample prevalence on model estimation.     

The importance of incorporating imperfect detection in biodiversity assessments: a case study of small mammals in an Australian region

Aim Assessments of biodiversity are an essential requirement of conservation management planning. Species distributional modelling is a popular approach to quantifying biodiversity whereby occurrence data are related to environmental covariates. An important confounding factor that is often overlooked in the development of such models is uncertainty due to imperfect detection. Here, I demonstrate how an analytical approach that accounts for the bias due to imperfect detection can be applied retrospectively to an existing biodiversity survey data set to produce more realistic estimates of species distributions and unbiased covariate relationships. Location Pilbara biogeographic region, Australia. Methods As a component of the Pilbara survey, presence/absence (i.e. undetected) data on small ground‐dwelling mammals were collected. I applied a multiseason occupancy modelling approach to six of the most common species encountered during this survey. Detection and occupancy rates, as well as extinction and colonization probabilities, were determined, and the influence of covariates on these parameters was examined using the multi‐model inference approach. Results Detection probabilities for all six species were considerably lower than 1.0 and varied across time and species. Naïve estimates of occupancy underestimated occupancy rates corrected for species detectability by up to 45%. Seasonal variation in occupancy status was attributed to changes in detection for two of the focal species, while reproductive events explained variation in occupancy in three others. Covariates describing the substrate strongly influenced site occupancy for most of the species modelled. A comparison of the occupancy model with a generalized linear model, assuming perfect detection, showed that the effects of the covariates were underestimated in the latter model. Main conclusions The application of the multiseason occupancy modelling approach to the Pilbara mammal data set demonstrated a powerful framework for examining changes in site occupancy, as well as local colonization and extinction rates of species which are not confounded by variable species detection rates.     

A new method for dealing with residual spatial autocorrelation in species distribution models

Species distribution modelling (SDM) is a widely used tool and has many applications in ecology and conservation biology. Spatial autocorrelation (SAC), a pattern in which observations are related to one another by their geographic distance, is common in georeferenced ecological data. SAC in the residuals of SDMs violates the ‘independent errors’ assumption required to justify the use of statistical models in modelling species’ distributions. The autologistic modelling approach accounts for SAC by including an additional term (the autocovariate) representing the similarity between the value of the response variable at a location and neighbouring locations. However, autologistic models have been found to introduce bias in the estimation of parameters describing the influence of explanatory variables on habitat occupancy. To address this problem we developed an extension to the autologistic approach by calculating the autocovariate on SAC in residuals (the RAC approach). Performance of the new approach was tested on simulated data with a known spatial structure and on strongly autocorrelated mangrove species’ distribution data collected in northern Australia. The RAC approach was implemented as generalized linear models (GLMs) and boosted regression tree (BRT) models. We found that the BRT models with only environmental explanatory variables can account for some SAC, but applying the standard autologistic or RAC approaches further reduced SAC in model residuals and substantially improved model predictive performance. The RAC approach showed stronger inferential performance than the standard autologistic approach, as parameter estimates were more accurate and statistically significant variables were accurately identified. The new RAC approach presented here has the potential to account for spatial autocorrelation while maintaining strong predictive and inferential performance, and can be implemented across a range of modelling approaches.     

Dealing with uncertain absences in habitat modelling: a case study of a rare ground-dwelling parrot

In the development of a species distribution model based on regression techniques such as generalized linear or additive modelling (GLM/GAM), a basic assumption is that records of species presence and absence are real. However, a common concern in many studies examining species distributions is that absences cannot be inferred with certainty. This is particularly the case where the species is rare, difficult to detect and/or does not occupy all available habitat considered suitable. The western ground parrot ( Pezoporus wallicus flaviventris ) of southern Western Australia, Australia, is a case in point, as not only is it rare and difficult to detect, but it is also unlikely to occupy all available suitable habitat. A recent survey of ground parrots provided the opportunity to develop a predictive distribution model. As the data were susceptible to false absences, these were replaced with randomly selected 'pseudo' absences and modelled using GLM. As a comparison, presence-only information was modelled using a relatively new approach, MAXENT, a machine-learning technique that has been shown to perform comparatively well. The predictive performance of both models, as assessed by the receiver operating characteristic plot (ROC) was high (AUC > 0.8), with MAXENT performing only marginally better than the GLM. These approaches both indicated that the ground parrot prefers areas relatively high in altitude, distant from rivers, gently sloping to level habitat, with an intermediate cover of vegetation and where there is a mosaic of vegetation ages. In this case, the use of presence-only information resulted in the identification of important environmental attributes defining the occurrence of the ground parrot, but additional factors that account for the inability of the bird to occupy all suitable habitat should be a component of model refinement.     

Predicting species distributions from checklist data using site‐occupancy models

Aim (1) To increase awareness of the challenges induced by imperfect detection, which is a fundamental issue in species distribution modelling; (2) to emphasize the value of replicate observations for species distribution modelling; and (3) to show how ‘cheap’ checklist data in faunal/floral databases may be used for the rigorous modelling of distributions by site‐occupancy models. Location Switzerland. Methods We used checklist data collected by volunteers during 1999 and 2000 to analyse the distribution of the blue hawker, Aeshna cyanea (Odonata, Aeshnidae), a common dragonfly in Switzerland. We used data from repeated visits to 1‐ha pixels to derive ‘detection histories’ and apply site‐occupancy models to estimate the ‘true’ species distribution, i.e. corrected for imperfect detection. We modelled blue hawker distribution as a function of elevation and year and its detection probability of elevation, year and season. Results The best model contained cubic polynomial elevation effects for distribution and quadratic effects of elevation and season for detectability. We compared the site‐occupancy model with a conventional distribution model based on a generalized linear model, which assumes perfect detectability (p = 1). The conventional distribution map looked very different from the distribution map obtained using site‐occupancy models that accounted for the imperfect detection. The conventional model underestimated the species distribution by 60%, and the slope parameters of the occurrence–elevation relationship were also underestimated when assuming p = 1. Elevation was not only an important predictor of blue hawker occurrence, but also of the detection probability, with a bell‐shaped relationship. Furthermore, detectability increased over the season. The average detection probability was estimated at only 0.19 per survey. Main conclusions Conventional species distribution models do not model species distributions per se but rather the apparent distribution, i.e. an unknown proportion of species distributions. That unknown proportion is equivalent to detectability. Imperfect detection in conventional species distribution models yields underestimates of the extent of distributions and covariate effects that are biased towards zero. In addition, patterns in detectability will erroneously be ascribed to species distributions. In contrast, site‐occupancy models applied to replicated detection/non‐detection data offer a powerful framework for making inferences about species distributions corrected for imperfect detection. The use of ‘cheap’ checklist data greatly enhances the scope of applications of this useful class of models.     

Uncertainty of bioclimate envelope models based on the geographical distribution of species

Aim We explored the effects of prevalence, latitudinal range and spatial autocorrelation of species distribution patterns on the accuracy of bioclimate envelope models of butterflies. Location Finland, northern Europe. Methods The data of a national butterfly atlas survey (NAFI) carried out in 1991–2003 with a resolution of 10 × 10 km were used in the analyses. Generalized additive models (GAM) were constructed, for each of 98 species, to estimate the probability of occurrence as a function of climate variables. Model performance was measured using the area under the curve (AUC) of a receiver operating characteristic (ROC) plot. Observed differences in modelling accuracy among species were related to the species’ geographical attributes using multivariate GAM. Results Accuracies of the climate–butterfly models varied from low to very high (AUC values 0.59–0.99), with a mean of 0.79. The modelling performance was related negatively to the latitudinal range and prevalence, and positively to the spatial autocorrelation of the species distribution. These three factors accounted for 75.2% of the variation in the modelling accuracy. Species at the margin of their range or with low prevalence were better predicted than widespread species, and species with clumped distributions better than scattered dispersed species. Main conclusions The results from this study indicate that species’ geographical attributes highly influence the behaviour and uncertainty of species–climate models, which should be taken into account in biogeographical modelling studies and assessments of climate change impacts.     

Accounting for multi‐scale spatial autocorrelation improves performance of invasive species distribution modelling (iSDM)

Aim Analyses of species distributions are complicated by various origins of spatial autocorrelation (SAC) in biogeographical data. SAC may be particularly important for invasive species distribution models (iSDMs) because biological invasions are strongly influenced by dispersal and colonization processes that typically create highly structured distribution patterns. We examined the efficacy of using a multi‐scale framework to account for different origins of SAC, and compared non‐spatial models with models that accounted for SAC at multiple levels. Location We modelled the spatial distribution of an invasive forest pathogen, Phytophthora ramorum, in western USA. Methods We applied one conventional statistical method (generalized linear model, GLM) and one nonparametric technique (maximum entropy, Maxent) to a large dataset on P. ramorum occurrence (n = 3787) to develop four types of model that included environmental variables and that either ignored spatial context or incorporated it at a broad scale using trend surface analysis, a local scale using autocovariates, or multiple scales using spatial eigenvector mapping. We evaluated model accuracies and amounts of explained spatial structure, and examined the changes in predictive power of the environmental and spatial variables. Results Accounting for different scales of SAC significantly enhanced the predictive capability of iSDMs. Dramatic improvements were observed when fine‐scale SAC was included, suggesting that local range‐confining processes are important in P. ramorum spread. The importance of environmental variables was relatively consistent across all models, but the explanatory power decreased in spatial models for factors with strong spatial structure. While accounting for SAC reduced the amount of residual autocorrelation for GLM but not for Maxent, it still improved the performance of both approaches, supporting our hypothesis that dispersal and colonization processes are important factors to consider in distribution models of biological invasions. Main conclusions Spatial autocorrelation has become a paradigm in biogeography and ecological modelling. In addition to avoiding the violation of statistical assumptions, accounting for spatial patterns at multiple scales can enhance our understanding of dynamic processes that explain ecological mechanisms of invasion and improve the predictive performance of static iSDMs.     

Hierarchical models facilitate spatial analysis of large data sets: a case study on invasive plant species in the northeastern United States

Many critical ecological issues require the analysis of large spatial point data sets – for example, modelling species distributions, abundance and spread from survey data. But modelling spatial relationships, especially in large point data sets, presents major computational challenges. We use a novel Bayesian hierarchical statistical approach, 'spatial predictive process' modelling, to predict the distribution of a major invasive plant species, Celastrus orbiculatus , in the northeastern USA. The model runs orders of magnitude faster than traditional geostatistical models on a large data set of c . 4000 points, and performs better than generalized linear models, generalized additive models and geographically weighted regression in cross-validation. We also use this approach to model simultaneously the distributions of a set of four major invasive species in a spatially explicit multivariate model. This multispecies analysis demonstrates that some pairs of species exhibit negative residual spatial covariation, suggesting potential competitive interaction or divergent responses to unmeasured factors.     

Does the interpolation accuracy of species distribution models come at the expense of transferability?

Model transferability (extrapolative accuracy) is one important feature in species distribution models, required in several ecological and conservation biological applications. This study uses 10 modelling techniques and nationwide data on both (1) species distribution of birds, butterflies, and plants and (2) climate and land cover in Finland to investigate whether good interpolative prediction accuracy for models comes at the expense of transferability – i.e. markedly worse performance in new areas. Models’ interpolation and extrapolation performance was primarily assessed using AUC (the area under the curve of a receiver characteristic plot) and Kappa statistics, with supplementary comparisons examining model sensitivity and specificity values. Our AUC and Kappa results show that extrapolation to new areas is a greater challenge for all included modelling techniques than simple filling of gaps in a well‐sampled area, but there are also differences among the techniques in the degree of transferability. Among the machine‐learning modelling techniques, MAXENT, generalized boosting methods (GBM), and artificial neural networks (ANN) showed good transferability while the performance of GARP and random forest (RF) decreased notably in extrapolation. Among the regression‐based methods, generalized additive models (GAM) and generalized linear models (GLM) showed good transferability. A desirable combination of good prediction accuracy and good transferability was evident for three modelling techniques: MAXENT, GBM, and GAM. However, examination of model sensitivity and specificity revealed that model types may differ in their tendencies to either increased over‐prediction of presences or absences in extrapolation, and some of the methods show contrasting changes in sensitivity vs specificity (e.g. ANN and GARP). Among the three species groups, the best transferability was seen with birds, followed closely by butterflies, whereas reliable extrapolation for plant species distribution models appears to be a major challenge at least at this scale. Overall, detailed knowledge of the behaviour of different techniques in various study settings and with different species groups is of utmost importance in predictive modelling.     

Modelling the distribution and compositional variation of plant communities at the continental scale

Aim

We investigate whether (1) environmental predictors allow to delineate the distribution of discrete community types at the continental scale and (2) how data completeness influences model generalization in relation to the compositional variation of the modelled entities.

Location

Europe.

Methods

We used comprehensive datasets of two community types of conservation concern in Europe: acidophilous beech forests and base‐rich fens. We computed community distribution models (CDMs) calibrated with environmental predictors to predict the occurrence of both community types, evaluating geographical transferability, interpolation and extrapolation under different scenarios of sampling bias. We used generalized dissimilarity modelling (GDM) to assess the role of geographical and environmental drivers in compositional variation within the predicted distributions.

Results

For the two community types, CDMs computed for the whole study area provided good performance when evaluated by random cross‐validation and external validation. Geographical transferability provided lower but relatively good performance, while model extrapolation performed poorly when compared with interpolation. Generalized dissimilarity modelling showed a predominant effect of geographical distance on compositional variation, complemented with the environmental predictors that also influenced habitat suitability.

Main conclusions

Correlative approaches typically used for modelling the distribution of individual species are also useful for delineating the potential area of occupancy of community types at the continental scale, when using consistent definitions of the modelled entity and high data completeness. The combination of CDMs with GDM further improves the understanding of diversity patterns of plant communities, providing spatially explicit information for mapping vegetation diversity and related habitat types at large scales.

     

Validation of species–climate impact models under climate change

Increasing concern over the implications of climate change for biodiversity has led to the use of species–climate envelope models to project species extinction risk under climate‐change scenarios. However, recent studies have demonstrated significant variability in model predictions and there remains a pressing need to validate models and to reduce uncertainties. Model validation is problematic as predictions are made for events that have not yet occurred. Resubstituition and data partitioning of present‐day data sets are, therefore, commonly used to test the predictive performance of models. However, these approaches suffer from the problems of spatial and temporal autocorrelation in the calibration and validation sets. Using observed distribution shifts among 116 British breeding‐bird species over the past ～20 years, we are able to provide a first independent validation of four envelope modelling techniques under climate change. Results showed good to fair predictive performance on independent validation, although rules used to assess model performance are difficult to interpret in a decision‐planning context. We also showed that measures of performance on nonindependent data provided optimistic estimates of models' predictive ability on independent data. Artificial neural networks and generalized additive models provided generally more accurate predictions of species range shifts than generalized linear models or classification tree analysis. Data for independent model validation and replication of this study are rare and we argue that perfect validation may not in fact be conceptually possible. We also note that usefulness of models is contingent on both the questions being asked and the techniques used. Implementations of species–climate envelope models for testing hypotheses and predicting future events may prove wrong, while being potentially useful if put into appropriate context.     

Predicting species distributions: a critical comparison of the most common statistical models using artificial species

Aim To test statistical models used to predict species distributions under different shapes of occurrence–environment relationship. We addressed three questions: (1) Is there a statistical technique that has a consistently higher predictive ability than others for all kinds of relationships? (2) How does species prevalence influence the relative performance of models? (3) When an automated stepwise selection procedure is used, does it improve predictive modelling, and are the relevant variables being selected? Location We used environmental data from a real landscape, the state of California, and simulated species distributions within this landscape. Methods Eighteen artificial species were generated, which varied in their occurrence response to the environmental gradients considered (random, linear, Gaussian, threshold or mixed), in the interaction of those factors (no interaction vs. multiplicative), and on their prevalence (50% vs. 5%). The landscape was then randomly sampled with a large (n = 2000) or small (n = 150) sample size, and the predictive ability of each statistical approach was assessed by comparing the true and predicted distributions using five different indexes of performance (area under the receiver‐operator characteristic curve, Kappa, correlation between true and predictive probability of occurrence, sensitivity and specificity). We compared generalized additive models (GAM) with and without flexible degrees of freedom, logistic regressions (general linear models, GLM) with and without variable selection, classification trees, and the genetic algorithm for rule‐set production (GARP). Results Species with threshold and mixed responses, additive environmental effects, and high prevalence generated better predictions than did other species for all statistical models. In general, GAM outperforms all other strategies, although differences with GLM are usually not significant. The two variable‐selection strategies presented here did not discriminate successfully between truly causal factors and correlated environmental variables. Main conclusions Based on our analyses, we recommend the use of GAM or GLM over classification trees or GARP, and the specification of any suspected interaction terms between predictors. An expert‐based variable selection procedure was preferable to the automated procedures used here. Finally, for low‐prevalence species, variability in model performance is both very high and sample‐dependent. This suggests that distribution models for species with low prevalence can be improved through targeted sampling.     

Do community‐level models describe community variation effectively?

Aim The aim of community‐level modelling is to improve the performance of species distributional models by taking patterns of co‐occurrence among species into account. Here, we test this expectation by examining how well three community‐level modelling strategies (‘assemble first, predict later’, ‘predict first, assemble later’, and ‘assemble and predict together’) spatially project the observed composition of species assemblages. Location Europe. Methods Variation in the composition of European tree assemblages and its spatial and environmental correlates were examined with cluster analysis and constrained analysis of principal coordinates. Results were used to benchmark spatial projections from three community‐based strategies: (1) assemble first, predict later (cluster analysis first, then generalized linear models, GLMs); (2) predict first, assemble later (GLMs first, then cluster analysis); and (3) assemble and predict together (constrained quadratic ordination). Results None of the community‐level modelling strategies was able to accurately model the observed distribution of tree assemblages in Europe. Uncertainty was particularly high in southern Europe, where modelled assemblages were markedly different from observed ones. Assembling first and predicting later led to distribution models with the simultaneous occurrence of several types of assemblages in southern Europe that do not co‐occur, and the remaining strategies yielded models with the presence of non‐analogue assemblages that presently do not exist and that are much more strongly correlated with environmental gradients than with the real assemblages. Main conclusions Community‐level models were unable to characterize the distribution of European tree assemblages effectively. Models accounting for co‐occurrence patterns along environmental gradients did not outperform methods that assume individual responses of species to climate. Unrealistic assemblages were generated because of the models’ inability to capture fundamental processes causing patterns of covariation among species. The usefulness of these forms of community‐based models thus remains uncertain and further research is required to demonstrate their utility.