The iterative ensemble modelling approach increases the accuracy of fish distribution models

Methodological absences, i.e. when a species is not detected although it is actually present, are known to reduce the prediction accuracy of species distribution models (SDMs). To deal with this problem, we assessed whether a new iterative ensemble modelling (IEM) approach better predicts the spatial distribution of a set of 31 freshwater fish species, exhibiting a wide range of prevalence and methodological absences. Model efficiency was compared using one threshold‐independent (AUC) and three threshold‐dependent indicators of model predictive performance: the percentage of misclassified sites; the Kappa index; and the True Skill Statistic. We then reconstructed species assemblages from individual species predictions and compared observed assemblages to those predicted using EM and IEM using the Jaccard index. Compared to an EM approach, IEM improved model predictive performance for most difficult‐to‐detect species. The iterative approach outperformed EM at modelling the distribution of difficult‐to‐detect species, provided that presence data are representative of the niche of the species. At the assemblage level, the discrepancy between observed and IEM predicted assemblages was significantly lower than that between observed and EM predicted assemblages, showing that IEM can be used to predict the distribution of entire species assemblages. The IEM approach provides a way to consider difficult‐to‐detect species in species distribution models.     

Model-Based Control of Observer Bias for the Analysis of Presence-Only Data in Ecology

Presence-only data, where information is available concerning species presence but not species absence, are subject to bias due to observers being more likely to visit and record sightings at some locations than others (hereafter “observer bias”). In this paper, we describe and evaluate a model-based approach to accounting for observer bias directly – by modelling presence locations as a function of known observer bias variables (such as accessibility variables) in addition to environmental variables, then conditioning on a common level of bias to make predictions of species occurrence free of such observer bias. We implement this idea using point process models with a LASSO penalty, a new presence-only method related to maximum entropy modelling, that implicitly addresses the “pseudo-absence problem” of where to locate pseudo-absences (and how many). The proposed method of bias-correction is evaluated using systematically collected presence/absence data for 62 plant species endemic to the Blue Mountains near Sydney, Australia. It is shown that modelling and controlling for observer bias significantly improves the accuracy of predictions made using presence-only data, and usually improves predictions as compared to pseudo-absence or “inventory” methods of bias correction based on absences from non-target species. Future research will consider the potential for improving the proposed bias-correction approach by estimating the observer bias simultaneously across multiple species.     

The effect of sample size on the accuracy of species distribution models: considering both presences and pseudo‐absences or background sites

Most high‐performing species distribution modelling techniques require both presences, and either absences or pseudo‐absences or background points. In this paper, we explore the effect of sample size, towards developing improved strategies for modelling. We generated 1800 virtual species with three levels of prevalence using ten modelling techniques, while varying the number of training presences (NTP) and the number of random points (NRP representing pseudo‐absences or background sites). For five of the ten modelling techniques we built two versions of models: one with an equal total weight (ETW) setting where the total weight for pseudo‐absence is equivalent to the total weight for presence, and another with an unequal total weight (UTW) setting where the total weight for pseudo‐absence is not required to be equal to the total weight for presence. We compared two strategies for NRP: a small multiplier strategy (i.e. setting NRP at a few times as large as NTP), and a large number strategy (i.e. using numerous random points). We produced ensemble models (by averaging the predictions from 30 models built with the same set of training presences and different sets of random points in equivalent numbers) for three NTP magnitudes and two NRP strategies. We found that model accuracy altered as NRP increased with four distinct patterns of performance: increasing, decreasing, arch‐shaped and horizontal. In most cases ETW improved model performance. Ensemble models had higher accuracy than the corresponding single models, and this improvement was pronounced when NTP was low. We conclude that a large NRP is not always an appropriate strategy. The best choice for NRP will depend on the modelling techniques used, species prevalence and NTP. We recommend building ensemble models instead of single models, using the small multiplier strategy for NRP with ETW, especially when only a small number of species presence records are available.     

Effects of the number of presences on reliability and stability of MARS species distribution models: the importance of regional niche variation and ecological heterogeneity

Question: What are the effects of the number of presences on models generated with multivariate adaptive regression splines (MARS)? Do these effects vary with data quality and quantity and species ecology? Location: Spain and Ecuador. Methods: We used two data sets: (1) two trees from Spain, representing high‐occurrence number data sets with real absences and unbalanced prevalence; (2) two herbs from Ecuador, representing low‐occurrence number data sets without real absences and balanced prevalence. For model quality, we used two different measures: reliability and stability. For each sample size, different replicates were generated at random and then used to generate a consensus model. Results: Model reliability and stability decrease with sample size. Optimal minimum sample size varies depending on many factors, many of which are unknown. Regional niche variation and ecological heterogeneity are critical. Conclusions: (1) Model predictive power improves greatly with more than 18‐20 presences. (2) Model reliability depends on data quantity and quality as well as species ecological characteristics. (3) Depending on the number of presences in the data set, investigators must carefully distinguish between models that should be treated with skepticism and those whose predictions can be applied with reasonable confidence. (4) For species combining few initial presences and wide environmental range variation, it is advisable to generate several replicate models that partition the initial data and generate a consensus model. (5) Models of species with a narrow environmental range variation can be highly stable and reliable, even when generated with few presences.     

Novel methods improve prediction of species' distributions from occurrence data

Prediction of species' distributions is central to diverse applications in ecology, evolution and conservation science. There is increasing electronic access to vast sets of occurrence records in museums and herbaria, yet little effective guidance on how best to use this information in the context of numerous approaches for modelling distributions. To meet this need, we compared 16 modelling methods over 226 species from 6 regions of the world, creating the most comprehensive set of model comparisons to date. We used presence-only data to fit models, and independent presence-absence data to evaluate the predictions. Along with well-established modelling methods such as generalised additive models and GARP and BIOCLIM, we explored methods that either have been developed recently or have rarely been applied to modelling species' distributions. These include machine-learning methods and community models, both of which have features that may make them particularly well suited to noisy or sparse information, as is typical of species' occurrence data. Presence-only data were effective for modelling species' distributions for many species and regions. The novel methods consistently outperformed more established methods. The results of our analysis are promising for the use of data from museums and herbaria, especially as methods suited to the noise inherent in such data improve.     

The uncertain nature of absences and their importance in species distribution modelling

Species distribution models (SDM) are commonly used to obtain hypotheses on either the realized or the potential distribution of species. The reliability and meaning of these hypotheses depends on the kind of absences included in the training data, the variables used as predictors and the methods employed to parameterize the models. Information about the absence of species from certain localities is usually lacking, so pseudo‐absences are often incorporated to the training data. We explore the effect of using different kinds of pseudo‐absences on SDM results. To do this, we use presence information on Aphodius bonvouloiri, a dung beetle species of well‐known distribution. We incorporate different types of pseudo‐absences to create different sets of training data that account for absences of methodological (i.e. false absences), contingent and environmental origin. We used these datasets to calibrate SDMs with GAMs as modelling technique and climatic variables as predictors, and compare these results with geographical representations of the potential and realized distribution of the species created independently. Our results confirm the importance of the kind of absences in determining the aspect of species distribution identified through SDM. Estimations of the potential distribution require absences located farther apart in the geographic and/or environmental space than estimations of the realized distribution. Methodological absences produce overall bad models, and absences that are too far from the presence points in either the environmental or the geographic space may not be informative, yielding important overestimations. GLMs and Artificial Neural Networks yielded similar results. Synthetic discrimination measures such as the Area Under the Receiver Characteristic Curve (AUC) must be interpreted with caution, as they can produce misleading comparative results. Instead, the joint examination of ommission and comission errors provides a better understanding of the reliability of SDM results.     

Akaike information criterion should not be a “test” of geographical prediction accuracy in ecological niche modelling

Model complexity in ecological niche modelling has been recently considered as an important issue that might affect model performance. New methodological developments have implemented the Akaike information criterion (AIC) to capture model complexity in the Maxent algorithm model. AIC is calculated based on the number of parameters and likelihoods of continuous raw outputs. ENMeval R package allows users to perform a species-specific tuning of Maxent settings running models with different combinations of regularization multiplier and feature classes and finally, all these models are compared using AIC corrected for small sample size. This approach is focused to find the “best” model parametrization and it is thought to maximize the model complexity and therefore, its predictability. We found that most niche modelling studies examined by us (68%) tend to consider AIC as a criterion of predictive accuracy in geographical distribution. In other words, AIC is used as a criterion to choose those models with the highest capacity to discriminate between presences and absences. However, the link between AIC and geographical predictive accuracy has not been tested so far. Here, we evaluated this relationship using a set of simulated (virtual) species. We created a set of nine virtual species with different ecological and geographical traits (e.g., niche position, niche breadth, range size) and generated different sets of true presences and absences data across geography. We built a set of models using Maxent algorithm with different regularization values and features schemes and calculated AIC values for each model. For each model, we obtained binary predictions using different threshold criteria and validated using independent presence and absences data. We correlated AIC values against standard validation metrics (e.g., Kappa, TSS) and the number of pixels correctly predicted as presences and absences. We did not find a correlation between AIC values and predictive accuracy from validation metrics. In general, those models with the lowest AIC values tend to generate geographical predictions with high commission and omission errors. The results were consistent across all species simulated. Finally, we suggest that AIC should not be used if users are interested in prediction more than explanation in ecological niche modelling.     

Fish distribution predictions from different points of view: comparing associative neural networks,geostatistics and regression models

Accurate prediction of species distributions based on sampling and environmental data is essential for further scientific analysis, such as stock assessment, detection of abundance fluctuation due to climate change or overexploitation, and to underpin management and legislation processes. The evolution of computer science and statistics has allowed the development of sophisticated and well-established modelling techniques as well as a variety of promising innovative approaches for modelling species distribution. The appropriate selection of modelling approach is crucial to the quality of predictions about species distribution. In this study, modelling techniques based on different approaches are compared and evaluated in relation to their predictive performance, utilizing fish density acoustic data. Generalized additive models and mixed models amongst the regression models, associative neural networks (ANNs) and artificial neural networks ensemble amongst the artificial neural networks and ordinary kriging amongst the geostatistical techniques are applied and evaluated. A verification dataset is used for estimating the predictive performance of these models. A combination of outputs from the different models is applied for prediction optimization to exploit the ability of each model to explain certain aspects of variation in species acoustic density. Neural networks and especially ANNs appear to provide more accurate results in fitting the training dataset while generalized additive models appear more flexible in predicting the verification dataset. The efficiency of each technique in relation to certain sampling and output strategies is also discussed.     

Do Stacked Species Distribution Models Reflect Altitudinal Diversity Patterns?

The objective of this study was to evaluate the performance of stacked species distribution models in predicting the alpha and gamma species diversity patterns of two important plant clades along elevation in the Andes. We modelled the distribution of the species in the Anthurium genus (53 species) and the Bromeliaceae family (89 species) using six modelling techniques. We combined all of the predictions for the same species in ensemble models based on two different criteria: the average of the rescaled predictions by all techniques and the average of the best techniques. The rescaled predictions were then reclassified into binary predictions (presence/absence). By stacking either the original predictions or binary predictions for both ensemble procedures, we obtained four different species richness models per taxa. The gamma and alpha diversity per elevation band (500 m) was also computed. To evaluate the prediction abilities for the four predictions of species richness and gamma diversity, the models were compared with the real data along an elevation gradient that was independently compiled by specialists. Finally, we also tested whether our richness models performed better than a null model of altitudinal changes of diversity based on the literature. Stacking of the ensemble prediction of the individual species models generated richness models that proved to be well correlated with the observed alpha diversity richness patterns along elevation and with the gamma diversity derived from the literature. Overall, these models tend to overpredict species richness. The use of the ensemble predictions from the species models built with different techniques seems very promising for modelling of species assemblages. Stacking of the binary models reduced the over-prediction, although more research is needed. The randomisation test proved to be a promising method for testing the performance of the stacked models, but other implementations may still be developed.     

Invasive species distribution models – how violating the equilibrium assumption can create new insights

Aim Two core assumptions of species distribution models (SDMs) do not hold when modelling invasive species. Invasives are not in equilibrium with their environment and niche quantification and transferability in space and time are limited. Here, we test whether combining global‐ and regional‐scale data in a novel framework can overcome these limitations. Beyond simply improving regional niche modelling of non‐native species, the framework also makes use of the violation of regional equilibrium assumptions, and aims at estimating the stage of invasion, range filling and risk of spread in the near future for 27 invasive species in the French Alps. Innovation For each invader we built three sets of SDMs using a committee averaging method: one global model and two regional models (a conventional model and one using the global model output to weight pseudo‐absences). Model performances were compared using the area under the receiver operating characteristic curve, the true skill statistic, sensitivity and specificity scores. Then, we extracted the predictions for observed presences and compared them to global and regional models. This comparison made it possible to identify whether invasive species were observed within or outside of their regional and global niches. Main conclusions This study provides a novel methodological framework for improving the regional modelling of invasive species, where the use of a global model output to weight pseudo‐absences in a regional model significantly improved the predictive performance of regional SDMs. Additionally, the comparison of the global and regional model outputs revealed distinct patterns of niche estimates and range filling among the species. These differences allowed us to draw conclusions about the stage of invasion and the risk of spread in the near future, which both correspond to experts' expectations. This framework can be easily applied to a large number of species and is therefore useful for control of biological invasions and eradication planning.     

Evaluation of species distribution models by resampling of sites surveyed a century ago by Joseph Grinnell

Species distribution models (SDMs) are commonly applied to predict species’ responses to anticipated global change, but lack of data from future time periods precludes assessment of their reliability. Instead, performance against test data in the same era is assumed to correlate with accuracy in the future. Moreover, high‐confidence absence data is required for testing model accuracy but is often unavailable since a species may be present when undetected. Here we evaluate the performance of eight SDMs trained with historic (1900–1939) or modern (1970–2009) climate data and occurrence records for 18 mammalian species. Models were projected to the same or the opposing time period and evaluated with data obtained from surveys conducted by Joseph Grinnell and his colleagues in the Sierra Nevada of California from 1900 to 1939 and modern resurveys from 2003 to 2011. Occupancy modeling was used to confidently assign absences at test sites where species were undetected. SDMs were evaluated using species’ presences combined with this high‐confidence absence (HCA) set, a low‐confidence set in which non‐detections were assumed to indicate absence (LCA), and randomly located ‘pseudoabsences’ (PSA). Model performance increased significantly with the quality of absences (mean AUC ± SE: 0.76 ± 0.01 for PSA, 0.79 ± 0.01 for LCA, and 0.81 ± 0.01 for HCA), and apparent differences between SDMs declined as the quality of test absences increased. Models projecting across time performed as well as when projecting within the same time period when assessed with threshold‐independent metrics. However, accuracy of presence and absence predictions sometimes declined in cross‐era projections. Although most variation in performance occurred among species, autecological traits were only weakly correlated with model accuracy. Our study indicates that a) the quality of evaluation data affects assessments of model performance; b) within‐era performance correlates positively but unreliably with cross‐era performance; and c) SDMs can be reliably but cautiously projected across time.     

Predicting species distributions from museum and herbarium records using multiresponse models fitted with multivariate adaptive regression splines

Current circumstances — that the majority of species distribution records exist as presence‐only data (e.g. from museums and herbaria), and that there is an established need for predictions of species distributions — mean that scientists and conservation managers seek to develop robust methods for using these data. Such methods must, in particular, accommodate the difficulties caused by lack of reliable information about sites where species are absent. Here we test two approaches for overcoming these difficulties, analysing a range of data sets using the technique of multivariate adaptive regression splines (MARS). MARS is closely related to regression techniques such as generalized additive models (GAMs) that are commonly and successfully used in modelling species distributions, but has particular advantages in its analytical speed and the ease of transfer of analysis results to other computational environments such as a Geographic Information System. MARS also has the advantage that it can model multiple responses, meaning that it can combine information from a set of species to determine the dominant environmental drivers of variation in species composition. We use data from 226 species from six regions of the world, and demonstrate the use of MARS for distribution modelling using presence‐only data. We test whether (1) the type of data used to represent absence or background and (2) the signal from multiple species affect predictive performance, by evaluating predictions at completely independent sites where genuine presence–absence data were recorded. Models developed with absences inferred from the total set of presence‐only sites for a biological group, and using simultaneous analysis of multiple species to inform the choice of predictor variables, performed better than models in which species were analysed singly, or in which pseudo‐absences were drawn randomly from the study area. The methods are fast, relatively simple to understand, and useful for situations where data are limited. A tutorial is included.     

Integrating detection probabilities in species distribution models of amphibians breeding in Mediterranean temporary ponds

Aim The imperfect detection of species may lead to erroneous conclusions about species–environment relationships. Accuracy in species detection usually requires temporal replication at sampling sites, a time‐consuming and costly monitoring scheme. Here, we applied a lower‐cost alternative based on a double‐sampling approach to incorporate the reliability of species detection into regression‐based species distribution modelling. Location Doñana National Park (south‐western Spain). Methods Using species‐specific monthly detection probabilities, we estimated the detection reliability as the probability of having detected the species given the species‐specific survey time. Such reliability estimates were used to account explicitly for data uncertainty by weighting each absence. We illustrated how this novel framework can be used to evaluate four competing hypotheses as to what constitutes primary environmental control of amphibian distribution: breeding habitat, aestivating habitat, spatial distribution of surrounding habitats and/or major ecosystems zonation. The study was conducted on six pond‐breeding amphibian species during a 4‐year period. Results Non‐detections should not be considered equivalent to real absences, as their reliability varied considerably. The occurrence of Hyla meridionalis and Triturus pygmaeus was related to a particular major ecosystem of the study area, where suitable habitat for these species seemed to be widely available. Characteristics of the breeding habitat (area and hydroperiod) were of high importance for the occurrence of Pelobates cultripes and Pleurodeles waltl. Terrestrial characteristics were the most important predictors of the occurrence of Discoglossus galganoi and Lissotriton boscai, along with spatial distribution of breeding habitats for the last species. Main conclusions We did not find a single best supported hypothesis valid for all species, which stresses the importance of multiscale and multifactor approaches. More importantly, this study shows that estimating the reliability of non‐detection records, an exercise that had been previously seen as a naïve goal in species distribution modelling, is feasible and could be promoted in future studies, at least in comparable systems.     

Distribution models of estuarine fish species: The effect of sampling bias,species ecology and threshold selection on models' accuracy

Species distribution models (SDMs) relate presence/absence data to environmental variables, allowing to predict species environmental requirements and potential distribution. They have been increasingly used in fields such as ecology, biogeography and evolution, and often support conservation priorities and strategies. Thus, it becomes crucial to understand how trustworthy and reliable their predictions are. Different approaches, such as using ensemble methods (combining forecasts of different single models), or applying the most suitable threshold to transform continuous probability maps into species presences or absences, have been used to reduce model-based uncertainty. Taking into account the influence of biased sampling imprecision in species location, small datasets and species ecological characteristics, may also help to detect and compensate for uncertainty in the model building process. To investigate the effect of applying an ensemble approach, several threshold selection criteria and different datasets representing seasonal and spatial sampling bias, on models' accuracy, SDMs were built for four estuarine fish species with distinct use of the estuarine systems. Overall, predictions obtained with the ensemble approach were more accurate. Variability in accuracy metrics obtained with the nine threshold selection criteria applied was more pronounced for species with low prevalence and when sensitivity was calculated. Higher values of accuracy measures were registered with the threshold that maximizes the sum of sensitivity and specificity, and the threshold where the predicted prevalence equals the observed, whereas the 0.5 cut-off was unreliable, originating the lowest values for these metrics. Accuracy of models created from a spatially biased sampling was overall higher than accuracy of models created with a seasonally biased sampling or with the multi-year database created and this pattern was consistently obtained for marine migrant species, which use estuaries as nursery areas, presenting a seasonally and regular use of these ecosystems. The ecological dependence between these fish species and estuaries may add difficulties in the model building process, and needs to be taken into account, to improve their accuracy. The present study highlights the need for a thorough analysis of the critical underlying issues of the complete model building process to predict the distribution of estuarine fish species, due to the particular and dynamic nature of these ecosystems.     

基于集成模型的小黄鱼越冬群体适宜生境及其环境影响因素

小黄鱼是中韩渔业共同利用鱼种,其跨界洄游习性限制了对越冬场范围的调查和评估,导致对越冬群体适宜栖息地分布缺乏了解。本研究基于越冬期我国自然海域的物种分布点位数据和5个环境数据,运用8个物种分布模型(SDM)分析了小黄鱼越冬场分布范围,采用5折交叉验证,利用受试者工作特征曲线下面积(AUC)评价模型预测性能,并通过加权集成方法构建综合生境模型预测越冬场核心分布位置。结果表明: 出现/未出现数据模型预测准确度普遍高于仅出现模型;在出现/未出现数据模型中,机器学习方法预测准确度高于经典回归模型,支持向量模型(SVM)准确度最高(AUC=0.85),广义线性模型(GLM)准确度最低(AUC=0.73)。集成模型AUC较单一独立模型的准确度有所提升,表明集成模型能有效降低单一独立模型所带来的不确定性,提高模型预测准确度。变量重要性分析结果显示,盐度和温度是决定小黄鱼越冬场地理分布的重要因素,适宜分布区集中在黄海南部外海、东海北部外海和浙江省沿岸海域,而黄海南部沿岸海域和东海中南部外海为不适宜越冬区。研究结果为预测小黄鱼潜在越冬场提供了理论基础,可支撑越冬场渔业资源的空间规划和可持续利用。     

Application of common predictive habitat techniques for post-border weed risk management

Weed risk assessment has become an accepted methodology for examining the likelihood and consequence of a plant species becoming invasive outside of its native range. Weed risk assessment draws upon biological and ecological information to estimate the likelihood and magnitude of the threats posed by introducing non-indigenous plants. In geographical terms, this has traditionally been understood as within a new country following importation of plant material. However, recent risk assessment development has focused more specifically on intracountry risk posed by already-present invasive plants and is referred to as post-border weed risk management. This form of assessment calls for fine-scale predictions of invasive species habitat suitability. This study applies some of the more popular and widely available habitat prediction models that represent a variety of different statistical approaches (linear regression, logistic regression, Bayesian probability, Classification and Regression Trees, Genetic Algorithm for Rule-set Production) to a single invasive plant, the vertebrate-dispersed, fleshy fruited European olive ( Olea europaea L.) in southern Australia. The relationships between the dependant ( O. europaea distribution) and independent (soil and climate) variables are used in the models to produce predictive maps for each model. Accuracy was calculated for each model output as well as a combined surface to examine whether recent calls for ensemble modelling of distributions produces improved predictions. Overall, the combined prediction demonstrated superior accuracy compared to any individual model outputs. The combined outputs can be likened to mapped gradations of predicted habitat suitability. The type of output produced in this study should form a critical component of post-border weed risk management but more importantly, the methodology will add to this important discipline.     

A Factor Graph Approach to Automated GO Annotation

As volume of genomic data grows, computational methods become essential for providing a first glimpse onto gene annotations. Automated Gene Ontology (GO) annotation methods based on hierarchical ensemble classification techniques are particularly interesting when interpretability of annotation results is a main concern. In these methods, raw GO-term predictions computed by base binary classifiers are leveraged by checking the consistency of predefined GO relationships. Both formal leveraging strategies, with main focus on annotation precision, and heuristic alternatives, with main focus on scalability issues, have been described in literature. In this contribution, a factor graph approach to the hierarchical ensemble formulation of the automated GO annotation problem is presented. In this formal framework, a core factor graph is first built based on the GO structure and then enriched to take into account the noisy nature of GO-term predictions. Hence, starting from raw GO-term predictions, an iterative message passing algorithm between nodes of the factor graph is used to compute marginal probabilities of target GO-terms. Evaluations on Saccharomyces cerevisiae, Arabidopsis thaliana and Drosophila melanogaster protein sequences from the GO Molecular Function domain showed significant improvements over competing approaches, even when protein sequences were naively characterized by their physicochemical and secondary structure properties or when loose noisy annotation datasets were considered. Based on these promising results and using Arabidopsis thaliana annotation data, we extend our approach to the identification of most promising molecular function annotations for a set of proteins of unknown function in Solanum lycopersicum.     

The effect of a gradual response to the environment on species distribution modeling performance

Species distribution models (SDMs) have been widely used in ecology, biogeography, and conservation. Although ecological theory predicts that species occupancy is dynamic, the outputs of SDMs are generally converted into a single occurrence map, and model performance is evaluated in terms of success to predict presences and absences. The aim of this study was to characterize the effects of a gradual response in species occupancy to environmental gradients into the performance of SDMs. First we outline guidelines for the appropriate simulation of artificial species that allows controlling for gradualism and prevalence in the occupancy patterns over an environmental gradient. Second, we derive theoretical expected values for success measures based on presence‐absence predictions (AUC, Kappa, sensitivity and specificity). And finally we used artificial species to exemplify and test the effect of a gradual probabilistic occupancy response to environmental gradients on SDM performance. Our results show that when a species responds gradually to an environmental gradient, conventional measures of SDM predictive success based on presence‐absence cannot be expected to attain currently accepted performance values considered as good, even for a model that recovers perfectly well the true probability of occurrence. A gradual response imposes a theoretical expected value for these measures of performance that can be calculated from the species properties. However, irrespective of the statistical modeling strategy used and of how gradual the species response is, one can recover the true probability of occurrence as a function of environmental variables provided that species and sample prevalence are similar. Therefore, model performance based on presence‐absence should be judged against the theoretical expected value rather than to absolute values currently in use such as AUC > 0.8. Overall, we advocate for a wider use of the probability of occurrence and emphasize the need for further technical developments in this sense.     

Evaluation of consensus methods in predictive species distribution modelling

Aim  Spatial modelling techniques are increasingly used in species distribution modelling. However, the implemented techniques differ in their modelling performance, and some consensus methods are needed to reduce the uncertainty of predictions. In this study, we tested the predictive accuracies of five consensus methods, namely Weighted Average (WA), Mean(All), Median(All), Median(PCA), and Best, for 28 threatened plant species.
Location  North-eastern Finland, Europe.
Methods  The spatial distributions of the plant species were forecasted using eight state-of-the-art single-modelling techniques providing an ensemble of predictions. The probability values of occurrence were then combined using five consensus algorithms. The predictive accuracies of the single-model and consensus methods were assessed by computing the area under the curve (AUC) of the receiver-operating characteristic plot.
Results  The mean AUC values varied between 0.697 (classification tree analysis) and 0.813 (random forest) for the single-models, and from 0.757 to 0.850 for the consensus methods. WA and Mean(All) consensus methods provided significantly more robust predictions than all the single-models and the other consensus methods.
Main conclusions  Consensus methods based on average function algorithms may increase significantly the accuracy of species distribution forecasts, and thus they show considerable promise for different conservation biological and biogeographical applications.     

Silvicolous on a Small Scale: Possibilities and Limitations of Habitat Suitability Models for Small,Elusive Mammals in Conservation Management and Landscape Planning

Species distribution and endangerment can be assessed by habitat-suitability modelling. This study addresses methodical aspects of habitat suitability modelling and includes an application example in actual species conservation and landscape planning. Models using species presence-absence data are preferable to presence-only models. In contrast to species presence data, absences are rarely recorded. Therefore, many studies generate pseudo-absence data for modelling. However, in this study model quality was higher with null samples collected in the field. Next to species data the choice of landscape data is crucial for suitability modelling. Landscape data with high resolution and ecological relevance for the study species improve model reliability and quality for small elusive mammals like Muscardinus avellanarius. For large scale assessment of species distribution, models with low-detailed data are sufficient. For regional site-specific conservation issues like a conflict-free site for new wind turbines, high-detailed regional models are needed. Even though the overlap with optimally suitable habitat for M. avellanarius was low, the installation of wind plants can pose a threat due to habitat loss and fragmentation. To conclude, modellers should clearly state the purpose of their models and choose the according level of detail for species and environmental data.