Assessing the effects of pseudo-absences on predictive distribution model performance

Modelling species distributions with presence data from atlases, museum collections and databases is challenging. In this paper, we compare seven procedures to generate pseudo-absence data, which in turn are used to generate GLM-logistic regressed models when reliable absence data are not available. We use pseudo-absences selected randomly or by means of presence-only methods (ENFA and MDE) to model the distribution of a threatened endemic Iberian moth species (Graellsia isabelae). The results show that the pseudo-absence selection method greatly influences the percentage of explained variability, the scores of the accuracy measures and, most importantly, the degree of constraint in the distribution estimated. As we extract pseudo-absences from environmental regions further from the optimum established by presence data, the models generated obtain better accuracy scores, and over-prediction increases. When variables other than environmental ones influence the distribution of the species (i.e., non-equilibrium state) and precise information on absences is non-existent, the random selection of pseudo-absences or their selection from environmental localities similar to those of species presence data generates the most constrained predictive distribution maps, because pseudo-absences can be located within environmentally suitable areas. This study shows that if we do not have reliable absence data, the method of pseudo-absence selection strongly conditions the obtained model, generating different model predictions in the gradient between potential and realized distributions.     

Invasive species distribution modeling (iSDM): Are absence data and dispersal constraints needed to predict actual distributions?

Species distribution models (SDMs) based on statistical relationships between occurrence data and underlying environmental conditions are increasingly used to predict spatial patterns of biological invasions and prioritize locations for early detection and control of invasion outbreaks. However, invasive species distribution models (iSDMs) face special challenges because (i) they typically violate SDM's assumption that the organism is in equilibrium with its environment, and (ii) species absence data are often unavailable or believed to be too difficult to interpret. This often leads researchers to generate pseudo-absences for model training or utilize presence-only methods, and to confuse the distinction between predictions of potential vs. actual distribution. We examined the hypothesis that true-absence data, when accompanied by dispersal constraints, improve prediction accuracy and ecological understanding of iSDMs that aim to predict the actual distribution of biological invasions. We evaluated the impact of presence-only, true-absence and pseudo-absence data on model accuracy using an extensive dataset on the distribution of the invasive forest pathogen Phytophthora ramorum in California. Two traditional presence/absence models (generalized linear model and classification trees) and two alternative presence-only models (ecological niche factor analysis and maximum entropy) were developed based on 890 field plots of pathogen occurrence and several climatic, topographic, host vegetation and dispersal variables. The effects of all three possible types of occurrence data on model performance were evaluated with receiver operating characteristic (ROC) and omission/commission error rates. Results show that prediction of actual distribution was less accurate when we ignored true-absences and dispersal constraints. Presence-only models and models without dispersal information tended to over-predict the actual range of invasions. Models based on pseudo-absence data exhibited similar accuracies as presence-only models but produced spatially less feasible predictions. We suggest that true-absence data are a critical ingredient not only for accurate calibration but also for ecologically meaningful assessment of iSDMs that focus on predictions of actual distributions.     

Predicting the distributions of marine organisms at the global scale

We present and evaluate AquaMaps, a presence-only species distribution modelling system that allows the incorporation of expert knowledge about habitat usage and was designed for maximum output of standardized species range maps at the global scale. In the marine environment there is a significant challenge to the production of range maps due to large biases in the amount and location of occurrence data for most species. AquaMaps is compared with traditional presence-only species distribution modelling methods to determine the quality of outputs under equivalently automated conditions. The effect of the inclusion of expert knowledge to AquaMaps is also investigated. Model outputs were tested internally, through data partitioning, and externally against independent survey data to determine the ability of models to predict presence versus absence. Models were also tested externally by assessing correlation with independent survey estimates of relative species abundance. AquaMaps outputs compare well to the existing methods tested, and inclusion of expert knowledge results in a general improvement in model outputs. The transparency, speed and adaptability of the AquaMaps system, as well as the existing online framework which allows expert review to compensate for sampling biases and thus improve model predictions are proposed as additional benefits for public and research use alike.     

Maximum entropy modeling of species geographic distributions

The availability of detailed environmental data, together with inexpensive and powerful computers, has fueled a rapid increase in predictive modeling of species environmental requirements and geographic distributions. For some species, detailed presence/absence occurrence data are available, allowing the use of a variety of standard statistical techniques. However, absence data are not available for most species. In this paper, we introduce the use of the maximum entropy method (Maxent) for modeling species geographic distributions with presence-only data. Maxent is a general-purpose machine learning method with a simple and precise mathematical formulation, and it has a number of aspects that make it well-suited for species distribution modeling. In order to investigate the efficacy of the method, here we perform a continental-scale case study using two Neotropical mammals: a lowland species of sloth, Bradypus variegatus, and a small montane murid rodent, Microryzomys minutus. We compared Maxent predictions with those of a commonly used presence-only modeling method, the Genetic Algorithm for Rule-Set Prediction (GARP). We made predictions on 10 random subsets of the occurrence records for both species, and then used the remaining localities for testing. Both algorithms provided reasonable estimates of the species’ range, far superior to the shaded outline maps available in field guides. All models were significantly better than random in both binomial tests of omission and receiver operating characteristic (ROC) analyses. The area under the ROC curve (AUC) was almost always higher for Maxent, indicating better discrimination of suitable versus unsuitable areas for the species. The Maxent modeling approach can be used in its present form for many applications with presence-only datasets, and merits further research and development.     

Selecting pseudo-absence data for presence-only distribution modeling: How far should you stray from what you know?

An important decision in presence-only species distribution modeling is how to select background (or pseudo-absence) localities for model parameterization. The selection of such localities may influence model parameterization and thus, can influence the appropriateness and accuracy of the model prediction when extrapolating the species distribution across time and space. We used 12 species from the Australian Wet Tropics (AWT) to evaluate the relationship between the geographic extent from which pseudo-absences are taken and model performance, and shape and importance of predictor variables using the MAXENT modeling method. Model performance is lower when pseudo-absence points are taken from either a restricted or broad region with respect to species occurrence data than from an intermediate region. Furthermore, variable importance (i.e., contribution to the model) changed such that, models became increasingly simplified, dominated by just two variables, as the area from which pseudo-absence points were drawn increased. Our results suggest that it is important to consider the spatial extent from which pseudo-absence data are taken. We suggest species distribution modeling exercises should begin with exploratory analyses evaluating what extent might provide both the most accurate results and biologically meaningful fit between species occurrence and predictor variables. This is especially important when modeling across space or time—a growing application for species distributional modeling.     

Prediction of potential areas of species distributions based on presence-only data

We introduce a methodology to infer zones of high potential for the habitat of a species, useful for management of biodiversity, conservation, biogeography, ecology, or sustainable use. Inference is based on a set of sites where the presence of the species has been reported. Each site is associated with covariate values, measured on discrete scales. We compute the predictive probability that the species is present at each node of a regular grid. Possible spatial bias for sites of presence is accounted for. Since the resulting posterior distribution does not have a closed form, a Markov chain Monte Carlo (MCMC) algorithm is implemented. However, we also describe an approximation to the posterior distribution, which avoids MCMC. Relevant features of the approach are that specific notions of data acquisition such as sampling intensity and detectability are accounted for, and that available a priori information regarding areas of distribution of the species is incorporated in a clear-cut way. These concepts, arising in the presence-only context, are not addressed in alternative methods. We also consider an uncertainty map, which measures the variability for the predictive probability at each node on the grid. A simulation study is carried out to test and compare our approach with other standard methods. Two case studies are also presented.     

Movement distances enhance validity of predictive models

Including the distance species are able to move in predictive models improves conservation practice. Bird inventory projects carried out from 1993 to 2004 in Taiwan provide an opportunity to investigate the relationships among species distribution, movement distance, and the environment. We compared projected distributions of 17 Taiwanese endemic bird species using what we called the Standard Method (i.e. movement distance is zero) and what we called the Buffer Method (i.e. movement distance is longer than zero) in three presence-only models (GARP, MAXENT and LIVES). The Standard Method used species original occurrence records directly while the Buffer Method expanded the occurrence of species to areas 1 km² around each recorded location. We first tested the efficacy of the Buffer Method using ten common species of the 17, and then applied the method to two rare species of the 17. For both the common and rare species, the distributions predicted by the two methods showed slight but important differences. The Buffer Method for all species had a higher average predictive probability, while the Standard Method had a higher maximum predictive probability. Most of the values for the area under the curve (AUC) were over 0.8 with the exceptions of Taiwan Barbet (Megalaima nuchalis) and Taiwan Hwamei (Garrulax taewanus), which have recently separated from Indochinese Barbet (Megalaima annamensis) and Chinese Hwamei (Garrulax canorus), and since 2008 and 2006 have been regarded as species endemic to the study area. Kappa values showed good performance for all species using both methods. The Buffer Method, however, resulted in significantly higher sensitivity and accuracy values for all models of species (p < 0.05). We conclude that when modeling species distribution including the area where the species was censused along with areas within the minimum movement areas better defines the surrounding areas that might supplement core habitat requirements. Therefore, using the Buffer Method, species surrounding distribution can be obtained which provides a better understanding of the species distributions. Given that distribution size is a key to the conservation of species, we suggest the Buffer Method can be used in conservation planning.     

Arthropod assemblages are best predicted by plant species composition

Insects and spiders comprise more than two-thirds of the Earth's total species diversity. There is wide concern, however, that the global diversity of arthropods may be declining even more rapidly than the diversity of vertebrates and plants. For adequate conservation planning, ecologists need to understand the driving factors for arthropod communities and devise methods, that provide reliable predictions when resources do not permit exhaustive ground surveys. Which factor most successfully predicts arthropod community structure is still a matter of debate, however. The purpose of this study was to identify the factor best predicting arthropod assemblage composition. We investigated the species composition of seven functionally different arthropod groups (epigeic spiders, grasshoppers, ground beetles, weevils, hoppers, hoverflies, and bees) at 47 sites in The Netherlands comprising a range of seminatural grassland types and one heathland type. We then compared the actual arthropod composition with predictions based on plant species composition, vegetation structure, environmental data, flower richness, and landscape composition. For this we used the recently published method of predictive co-correspondence analysis, and a predictive variant of canonical correspondence analysis, depending on the type of predictor data. Our results demonstrate that local plant species composition is the most effective predictor of arthropod assemblage composition, for all investigated groups. In predicting arthropod assemblages, plant community composition consistently outperforms both vegetation structure and environmental conditions (even when the two are combined), and also performs better than the surrounding landscape. These results run against a common expectation of vegetation structure as the decisive factor. Such expectations, however, have always been biased by the fact that until recently no methods existed that could use an entire (plant) species composition in the explanatory role. Although more recent experimental diversity work has reawakened interest in the role of plant species, these studies still have not used (or have not been able to use) entire species compositions. They only consider diversity measures, both for plant and insect assemblages, which may obscure relationships. The present study demonstrates that the species compositions of insect and plant communities are clearly linked.     

Evaluation of Museum Collection Data for Use in Biodiversity Assessment

Abstract: Natural-history collections in museums contain data critical to decisions in biodiversity conservation. Collectively, these specimen-based data describe the distributions of known taxa in time and space. As the most comprehensive, reliable source of knowledge for most described species, these records are potentially available to answer a wide range of conservation and research questions. Nevertheless, these data have shortcomings, notably geographic gaps, resulting mainly from the ad hoc nature of collecting effort. This problem has been frequently cited but rarely addressed in a systematic manner. We have developed a methodology to evaluate museum collection data, in particular the reliability of distributional data for narrow-range taxa. We included only those taxa for which there were an appropriate number of records, expert verification of identifications, and acceptable locality accuracy. First, we compared the available data for the taxon of interest to the "background data," comprised of records for those organisms likely to be captured by the same methods or by the same collectors as the taxon of interest. The "adequacy"of background sampling effort was assessed through calculation of statistics describing the separation, density, and clustering of points, and through generation of a sampling density contour surface. Geographical information systems (GIS) technology was then used to model predicted distributions of species based on abiotic (e.g., climatic and geological) data. The robustness of these predicted distributions can be tested iteratively or by bootstrapping. Together, these methods provide an objective means to assess the likelihood of the distributions obtained from museum collection records representing true distributions. Potentially, they could be used to evaluate any point data to be collated in species maps, biodiversity assessment, or similar applications requiring distributional information.     

Updating coarse-scale species distribution models using small fine-scale samples

Large, fine-grained samples are ideal for predictive species distribution models used for management purposes, but such datasets are not available for most species and conducting such surveys is costly. We attempted to overcome this obstacle by updating previously available coarse-grained logistic regression models with small fine-grained samples using a recalibration approach. Recalibration involves re-estimation of the intercept or slope of the linear predictor and may improve calibration (level of agreement between predicted and actual probabilities). If reliable estimates of occurrence likelihood are required (e.g., for species selection in ecological restoration) calibration should be preferred to other model performance measures. This updating approach is not expected to improve discrimination (the ability of the model to rank sites according to species suitability), because the rank order of predictions is not altered. We tested different updating methods and sample sizes with tree distribution data from Spain. Updated models were compared to models fitted using only fine-grained data (refitted models). Updated models performed reasonably well at fine scales and outperformed refitted models with small samples (10-100 occurrences). If a coarse-grained model is available (or could be easily developed) and fine-grained predictions are to be generated from a limited sample size, updating previous models may be a more accurate option than fitting a new model. Our results encourage further studies on model updating in other situations where species distribution models are used under different conditions from their training (e.g., different time periods, different regions).     

Modelling species distributions with penalised logistic regressions: A comparison with maximum entropy models

An important aspect of species distribution modelling is the choice of the modelling method because a suboptimal method may have poor predictive performance. Previous comparisons have found that novel methods, such as Maxent models, outperform well-established modelling methods, such as the standard logistic regression. These comparisons used training samples with small numbers of occurrences per estimated model parameter, and this limited sample size may have caused poorer predictive performance due to overfitting. Our hypothesis is that Maxent models would outperform a standard logistic regression because Maxent models avoid overfitting by using regularisation techniques and a standard logistic regression does not. Regularisation can be applied to logistic regression models using penalised maximum likelihood estimation. This estimation procedure shrinks the regression coefficients towards zero, causing biased predictions if applied to the training sample but improving the accuracy of new predictions. We used Maxent and logistic regression (standard and penalised) to analyse presence/pseudo-absence data for 13 tree species and evaluated the predictive performance (discrimination) using presence-absence data. The penalised logistic regression outperformed standard logistic regression and equalled the performance of Maxent. The penalised logistic regression may be considered one of the best methods to develop species distribution models trained with presence/pseudo-absence data, as it is comparable to Maxent. Our results encourage further use of the penalised logistic regression for species distribution modelling, especially in those cases in which a complex model must be fitted to a sample with a limited size.     

The evaluation strip: A new and robust method for plotting predicted responses from species distribution models

Increasing use is being made in conservation management of statistical models that couple extensive collections of species and environmental data to make predictions of the geographic distributions of species. While the relationships fitted between a species and its environment are relatively transparent for many of these modeling techniques, others are more ‘black box’ in character, only producing geographic predictions and providing minimal or untraditional summaries of the fitted relationships on which these predictions are based. This in turn prevents robust evaluation of the ecological sensibility of such models, a necessary process if model predictions are to be treated with confidence. Here we propose a new but simple method for visualizing modeled responses that can be implemented with any modeling method, and demonstrate its application using five common methods applied to the prediction of an Australian tree species. This is achieved by insetting an “evaluation strip” into the spatial data layers, which, after predictions have been made, can be clipped out and used for creating plots of the modelled responses. We present findings of the application strip for algorithms GLMs, GAMs, CLIM, DOMAIN and MARS. Evaluation strips can be constructed to investigate either uni-variate responses, or the simultaneous variation in predicted values in relation to two variables. The latter option is particularly useful for evaluating responses in models that allow the fitting of complex interaction terms.     

Predicting species distributions from samples collected along roadsides

Predictive models of species distributions are typically developed with data collected along roads. Roadside sampling may provide a biased (nonrandom) sample; however, it is currently unknown whether roadside sampling limits the accuracy of predictions generated by species distribution models. We tested whether roadside sampling affects the accuracy of predictions generated by species distribution models by using a prospective sampling strategy designed specifically to address this issue. We built models from roadside data and validated model predictions at paired locations on unpaved roads and 200 m away from roads (off road), spatially and temporally independent from the data used for model building. We predicted species distributions of 15 bird species on the basis of point-count data from a landbird monitoring program in Montana and Idaho (U.S.A.). We used hierarchical occupancy models to account for imperfect detection. We expected predictions of species distributions derived from roadside-sampling data would be less accurate when validated with data from off-road sampling than when it was validated with data from roadside sampling and that model accuracy would be differentially affected by whether species were generalists, associated with edges, or associated with interior forest. Model performance measures (kappa, area under the curve of a receiver operating characteristic plot, and true skill statistic) did not differ between model predictions of roadside and off-road distributions of species. Furthermore, performance measures did not differ among edge, generalist, and interior species, despite a difference in vegetation structure along roadsides and off road and that 2 of the 15 species were more likely to occur along roadsides. If the range of environmental gradients is surveyed in roadside-sampling efforts, our results suggest that surveys along unpaved roads can be a valuable, unbiased source of information for species distribution models.     

Quantifying parameter uncertainty in a coral reef model using Metropolis-Coupled Markov Chain Monte Carlo

Coral reefs are threatened ecosystems, so it is important to have predictive models of their dynamics. Most current models of coral reefs fall into two categories. The first is simple heuristic models which provide an abstract understanding of the possible behaviour of reefs in general, but do not describe real reefs. The second is complex simulations whose parameters are obtained from a range of sources such as literature estimates. We cannot estimate the parameters of these models from a single data set, and we have little idea of the uncertainty in their predictions.We have developed a compromise between these two extremes, which is complex enough to describe real reef data, but simple enough that we can estimate parameters for a specific reef from a time series. In previous work, we fitted this model to a long-term data set from Heron Island, Australia, using maximum likelihood methods. To evaluate predictions from this model, we need estimates of the uncertainty in our parameters. Here, we obtain such estimates using Bayesian Metropolis-Coupled Markov Chain Monte Carlo. We do this for versions of the model in which corals are aggregated into a single state variable (the three-state model), and in which corals are separated into four state variables (the six-state model), in order to determine the appropriate level of aggregation. We also estimate the posterior distribution of predicted trajectories in each case.In both cases, the fitted trajectories were close to the observed data, but we had doubts about the biological plausibility of some parameter estimates. We suggest that informative prior distributions incorporating expert knowledge may resolve this problem. In the six-state model, the posterior distribution of state frequencies after 40 years contained two divergent community types, one dominated by free space and soft corals, and one dominated by acroporid, pocilloporid, and massive corals. The three-state model predicts only a single community type. We conclude that the three-state model hides too much biological heterogeneity, but we need more data if we are to obtain reliable predictions from the six-state model. It is likely that there will be similarly large, but currently unevaluated, uncertainty in the predictions of other coral reef models, many of which are much more complex and harder to fit to real data.     

Microbial biodegradation of plastics: Challenges,opportunities, and a critical perspective

● Health hazards of plastic waste on environment are discussed. ● Microbial species involved in biodegradation of plastics are being reviewed. ● Enzymatic biodegradation mechanism of plastics is outlined. ● Analytical techniques to evaluate the plastic biodegradation are presented. The abundance of synthetic polymers has increased due to their uncontrolled utilization and disposal in the environment. The recalcitrant nature of plastics leads to accumulation and saturation in the environment, which is a matter of great concern. An exponential rise has been reported in plastic pollution during the corona pandemic because of PPE kits, gloves, and face masks made up of single-use plastics. The physicochemical methods have been employed to degrade synthetic polymers, but these methods have limited efficiency and cause the release of hazardous metabolites or by-products in the environment. Microbial species, isolated from landfills and dumpsites, have utilized plastics as the sole source of carbon, energy, and biomass production. The involvement of microbial strains in plastic degradation is evident as a substantial amount of mineralization has been observed. However, the complete removal of plastic could not be achieved, but it is still effective compared to the pre-existing traditional methods. Therefore, microbial species and the enzymes involved in plastic waste degradation could be utilized as eco-friendly alternatives. Thus, microbial biodegradation approaches have a profound scope to cope with the plastic waste problem in a cost-effective and environmental-friendly manner. Further, microbial degradation can be optimized and combined with physicochemical methods to achieve substantial results. This review summarizes the different microbial species, their genes, biochemical pathways, and enzymes involved in plastic biodegradation.     

Predicting Bird Species Distributions in Reconstructed Landscapes

Abstract:  Landscape optimization for biodiversity requires prediction of species distributions under alternative revegetation scenarios. We used Bayesian model averaging with logistic regression to predict probabilities of occurrence for 61 species of birds within highly fragmented box–ironbark forests of central Victoria, Australia. We used topographic, edaphic, and climatic variables as predictors so that the models could be applied to areas where vegetation has been cleared but may be replanted. Models were evaluated with newly acquired, independent data collected in large blocks of remnant native vegetation. Successful predictions were obtained for 18 of 45 woodland species (40%). Model averaging produced more accurate predictions than "single best" models. Models were most successful for smaller-bodied species that probably depend on particular vegetation types. Predictions for larger, generalist species, and seasonal migrants were less successful, partly because of changes in species distributions between model building (1995–1997) and validation (2004–2005) surveys. We used validated models to project occurrence probabilities for individual species across a 12,000-km² region, assuming native vegetation was present. These predictions are intended to be used as inputs, along with landscape context and temporal dynamics, into optimization algorithms to prioritize revegetation. Longer-term data sets to accommodate temporal dynamics are needed to improve the predictive accuracy of models.     

Mechanistic analysis of interspecific competition using foraging trade-offs: implications for duck assemblages

The role of interspecific competition and resource partitioning in determining the composition of species assemblages is often controversial. In many cases data on species co-occurrence or resource use (prey or habitat) have been interpreted without a clear understanding of how, or even whether, phenotypic differences constrain performance to allow resource partitioning or how these constraints and the density of resources and competitors should shape resource selection by each species. Instead, predictions have been based on assumed constraints, possibly leading to conflicting results. One such controversy involves the role of bill morphology in mediating resource partitioning among dabbling ducks (Anas spp.). To determine whether incorrect assumptions may have contributed to this controversy, I constructed mechanistic models that predict filter-feeding performance for seven species of ducks directly from bill morphology and kinetics and compared these predictions to those of earlier studies that tested the bill morphology hypothesis. The models predicted that species should share a preference for their most profitable (primary) prey while partitioning their less profitable (secondary) prey by size. Consequently, ducks should forage in the same habitats and exhibit high overlap in prey size when competitor/resource ratios are either high or low. In contrast, earlier studies expected that resource partitioning should always be evident, which implicitly assumes that species partition their primary resources. The models also predicted that the ecological similarity of species in assemblages should increase as prey abundance and size variability declines, contrary to the expectations of an earlier study. A more consistent understanding of the mechanisms regulating assemblages of dabbling ducks, and other species, might emerge if patterns of resource use and species co-occurrence were predicted directly from a mechanistic understanding of how performance trade-offs affect resource selection in the context of varying resource and competitor densities.     

Comparison of alternative strategies for invasive species distribution modeling

Species distribution models (SDMs) can provide useful information for managing biological invasions, such as identification of priority areas for early detection or for determining containment boundaries. However, prediction of invasive species using SDMs can be challenging because they typically violate the core assumption of being at equilibrium with their environment, which may lead to poorly guided management resulting from high levels of omission. Our goal was to provide a suite of potential decision strategies (DSs) that were not reliant on the equilibrium assumption but rather could be chosen to better match the management application, which in this case was to ensure containment through adequate surveillance. We used presence-only data and expert knowledge for model calibration and presence/absence data to evaluate the potential distribution of an introduced mesquite (Leguminoseae: Prosopis) invasion located in the Pilbara Region of northwest Western Australia. Five different DSs with varying levels of conservatism/risk were derived from a multi-criteria evaluation model using ordered weighted averaging. The performance of DSs over all possible thresholds was examined using receiver operating characteristic (ROC) analysis. DSs not on the convex hull of the ROC curves were discarded. Two threshold determination methods (TDMs) were compared on the two remaining DSs, one that assumed equilibrium (by maximizing overall prediction success) and another that assumed the invasion was ongoing (using a 95% threshold for true positives). The most conservative DS fitted the validation data most closely but could only predict 75% of the presence data. A more risk-taking DS could predict 95% of the presence data, which identified 8.5 times more area for surveillance, and better highlighted known populations that are still rapidly invading. This DS and TDM coupling was considered to be the most appropriate for our management application. Our results show that predictive niche modeling was highly sensitive to risk levels, but that these can be tailored to match specified management objectives. The methods implemented can be readily adapted to other invasive species or for conservation purposes.     

Ecological relevance of performance criteria for species distribution models

Species distribution models have often been developed based on ecological data. To develop reliable data-driven models, however, a sound model training and evaluation procedures are needed. A crucial step in these procedures is the assessment of the model performance, with as key component the applied performance criterion. Therefore, we reviewed seven performance criteria commonly applied in presence-absence modelling (the correctly classified instances, Kappa, sensitivity, specificity, the normalised mutual information statistic, the true skill statistic and the odds ratio) and analysed their application in both the model training and evaluation process. Although estimates of predictive performance have been used widely to assess final model quality, a systematic overview was missing because most analyses of performance criteria have been empirical and only focused on specific aspects of the performance criteria. This paper provides such an overview showing that different performance criteria evaluate a model differently and that this difference may be explained by the dependency of these criteria on the prevalence of the validation set. We showed theoretically that these prevalence effects only occur if the data are inseparable by an n-dimensional hyperplane, n being the number of input variables. Given this inseparability, different performance criteria focus on different aspects of model performance during model training, such as sensitivity, specificity or predictive accuracy. These findings have important consequences for ecological modelling because ecological data are mostly inseparable due to data noise and the complexity of the studied system. Consequently, it should be very clear which aspect of the model performance is evaluated, and models should be evaluated consistently, that is, independent of, or taking into account, species prevalence. The practical implications of these findings are clear. They provide further insight into the evaluation of ecological presence/absence models and attempt to assist modellers in their choice of suitable performance criteria.     

Predictive vegetation modeling for conservation: impact of error propagation from digital elevation data.

The effect of digital elevation model (DEM) error on environmental variables, and subsequently on predictive habitat models, has not been explored. Based on an error analysis of a DEM, multiple error realizations of the DEM were created and used to develop both direct and indirect environmental variables for input to predictive habitat models. The study explores the effects of DEM error and the resultant uncertainty of results on typical steps in the modeling procedure for prediction of vegetation species presence/absence. Results indicate that all of these steps and results, including the statistical significance of environmental variables, shapes of species response curves in generalized additive models (GAMs), stepwise model selection, coefficients and standard errors for generalized linear models (GLMs), prediction accuracy (Cohen's kappa and AUC), and spatial extent of predictions, were greatly affected by this type of error. Error in the DEM can affect the reliability of interpretations of model results and level of accuracy in predictions, as well as the spatial extent of the predictions. We suggest that the sensitivity of DEM-derived environmental variables to error in the DEM should be considered before including them in the modeling processes.