Are niche‐based species distribution models transferable in space?

Aim To assess the geographical transferability of niche‐based species distribution models fitted with two modelling techniques. Location Two distinct geographical study areas in Switzerland and Austria, in the subalpine and alpine belts. Methods Generalized linear and generalized additive models (GLM and GAM) with a binomial probability distribution and a logit link were fitted for 54 plant species, based on topoclimatic predictor variables. These models were then evaluated quantitatively and used for spatially explicit predictions within (internal evaluation and prediction) and between (external evaluation and prediction) the two regions. Comparisons of evaluations and spatial predictions between regions and models were conducted in order to test if species and methods meet the criteria of full transferability. By full transferability, we mean that: (1) the internal evaluation of models fitted in region A and B must be similar; (2) a model fitted in region A must at least retain a comparable external evaluation when projected into region B, and vice‐versa; and (3) internal and external spatial predictions have to match within both regions. Results The measures of model fit are, on average, 24% higher for GAMs than for GLMs in both regions. However, the differences between internal and external evaluations (AUC coefficient) are also higher for GAMs than for GLMs (a difference of 30% for models fitted in Switzerland and 54% for models fitted in Austria). Transferability, as measured with the AUC evaluation, fails for 68% of the species in Switzerland and 55% in Austria for GLMs (respectively for 67% and 53% of the species for GAMs). For both GAMs and GLMs, the agreement between internal and external predictions is rather weak on average (Kulczynski's coefficient in the range 0.3–0.4), but varies widely among individual species. The dominant pattern is an asymmetrical transferability between the two study regions (a mean decrease of 20% for the AUC coefficient when the models are transferred from Switzerland and 13% when they are transferred from Austria). Main conclusions The large inter‐specific variability observed among the 54 study species underlines the need to consider more than a few species to test properly the transferability of species distribution models. The pronounced asymmetry in transferability between the two study regions may be due to peculiarities of these regions, such as differences in the ranges of environmental predictors or the varied impact of land‐use history, or to species‐specific reasons like differential phenotypic plasticity, existence of ecotypes or varied dependence on biotic interactions that are not properly incorporated into niche‐based models. The lower variation between internal and external evaluation of GLMs compared to GAMs further suggests that overfitting may reduce transferability. Overall, a limited geographical transferability calls for caution when projecting niche‐based models for assessing the fate of species in future environments.     

Differences in spatial predictions among species distribution modeling methods vary with species traits and environmental predictors

Prediction maps produced by species distribution models (SDMs) influence decision‐making in resource management or designation of land in conservation planning. Many studies have compared the prediction accuracy of different SDM modeling methods, but few have quantified the similarity among prediction maps. There has also been little systematic exploration of how the relative importance of different predictor variables varies among model types and affects map similarity. Our objective was to expand the evaluation of SDM performance for 45 plant species in southern California to better understand how map predictions vary among model types, and to explain what factors may affect spatial correspondence, including the selection and relative importance of different environmental variables. Four types of models were tested. Correlation among maps was highest between generalized linear models (GLMs) and generalized additive models (GAMs) and lowest between classification trees and GAMs or GLMs. Correlation between Random Forests (RFs) and GAMs was the same as between RFs and classification trees. Spatial correspondence among maps was influenced the most by model prediction accuracy (AUC) and species prevalence; map correspondence was highest when accuracy was high and prevalence was intermediate (average prevalence for all species was 0.124). Species functional type and the selection of climate variables also influenced map correspondence. For most (but not all) species, climate variables were more important than terrain or soil in predicting their distributions. Environmental variable selection varied according to modeling method, but the largest differences were between RFs and GLMs or GAMs. Although prediction accuracy was equal for GLMs, GAMs, and RFs, the differences in spatial predictions suggest that it may be important to evaluate the results of more than one model to estimate the range of spatial uncertainty before making planning decisions based on map outputs. This may be particularly important if models have low accuracy or if species prevalence is not intermediate.     

Predicting the distribution of shrub species in southern California from climate and terrain-derived variables

Abstract. Generalized additive, generalized linear, and classification tree models were developed to predict the distribution of 20 species of chaparral and coastal sage shrubs within the southwest ecoregion of California. Mapped explanatory variables included bioclimatic attributes related to primary environmental regimes: averages of annual precipitation, minimum temperature of the coldest month, maximum temperature of the warmest month, and topographically-distributed potential solar insolation of the wettest quarter (winter) and of the growing season (spring). Also tested for significance were slope angle (related to soil depth) and the geographic coordinates of each observation. Models were parameterized and evaluated based on species presence/absence data from 906 plots surveyed on National Forest lands. Although all variables were significant in at least one of the species’ models, those models based only on the bioclimatic variables predicted species presence with 3–26% error. While error would undoubtedly be greater if the models were evaluated using independent data, results indicate that these models are useful for predictive mapping – for interpolating species distribution data within the ecoregion. All three methods produced models with similar accuracy for a given species; GAMs were useful for exploring the shape of the response functions, GLMs allowed those response functions to be parameterized and their significance tested, and classification trees, while some-times difficult to interpret, yielded the lowest prediction errors (lower by 3–5%).     

Performance evaluation of cetacean species distribution models developed using generalized additive models and boosted regression trees

Species distribution models (SDMs) are important management tools for highly mobile marine species because they provide spatially and temporally explicit information on animal distribution. Two prevalent modeling frameworks used to develop SDMs for marine species are generalized additive models (GAMs) and boosted regression trees (BRTs), but comparative studies have rarely been conducted; most rely on presence‐only data; and few have explored how features such as species distribution characteristics affect model performance. Since the majority of marine species BRTs have been used to predict habitat suitability, we first compared BRTs to GAMs that used presence/absence as the response variable. We then compared results from these habitat suitability models to GAMs that predict species density (animals per km²) because density models built with a subset of the data used here have previously received extensive validation. We compared both the explanatory power (i.e., model goodness of fit) and predictive power (i.e., performance on a novel dataset) of the GAMs and BRTs for a taxonomically diverse suite of cetacean species using a robust set of systematic survey data (1991–2014) within the California Current Ecosystem. Both BRTs and GAMs were successful at describing overall distribution patterns throughout the study area for the majority of species considered, but when predicting on novel data, the density GAMs exhibited substantially greater predictive power than both the presence/absence GAMs and BRTs, likely due to both the different response variables and fitting algorithms. Our results provide an improved understanding of some of the strengths and limitations of models developed using these two methods. These results can be used by modelers developing SDMs and resource managers tasked with the spatial management of marine species to determine the best modeling technique for their question of interest.     

A spatio‐temporal framework for efficient inventories of natural resources: A case study with submersed macrophytes

Questions: Does a reduced nutrient load in open water increase species richness and the importance of regional and local site characteristics for species abundance and spatial distribution? Can we build lake‐specific models of macrophyte abundance and distribution based on site characteristics in order to prepare a cost‐efficient framework for future surveys? Location: Lake Constance, 47°39′N, 9°18′E. Methods: Generalized additive models (GAMs) were used to predict the potential distributions of eight species and overall species richness. Submersed macrophyte distribution in 1993 was compared with corresponding data from 1978, when eutrophication was at its maximum. Results: Spatial predictions for eight species and overall species richness were relatively accurate and independent of water chemistry. Depth was confirmed as a main predictor of species distribution, while effective fetch distance was retained in many models. Mineralogical variables of sediment composition represent allogenic and autogenic sediment sources and their east‐west gradient in Lake Constance corresponded to east‐west gradients of species distribution and richness. GAMs appeared more efficient than generalized linear models (GLMs) for modelling species responses to environmental gradients. Conclusions: Reduced trophic status increases species richness and the importance of regional and local site characteristics for species abundance and distribution. Our models represent a spatio‐temporal framework for future lake monitoring purposes and allow the development of effective monitoring; this could be generalized for many ecosystem types and would be particularly efficient for large lakes such as Lake Constance.     

Modelling habitat-suitability using museum collections: an example with three sympatric Apodemus species from the Alps

Aim, Location Although the alpine mouse Apodemus alpicola has been given species status since 1989, no distribution map has ever been constructed for this endemic alpine rodent in Switzerland. Based on redetermined museum material and using the Ecological-Niche Factor Analysis (ENFA), habitat-suitability maps were computed for A. alpicola , and also for the co-occurring A. flavicollis and A. sylvaticus .
Methods In the particular case of habitat suitability models, classical approaches (GLMs, GAMs, discriminant analysis, etc.) generally require presence and absence data. The presence records provided by museums can clearly give useful information about species distribution and ecology and have already been used for knowledge-based mapping. In this paper, we apply the ENFA which requires only presence data, to build a habitat-suitability map of three species of Apodemus on the basis of museum skull collections.
Results Interspecific niche comparisons showed that A. alpicola is very specialized concerning habitat selection, meaning that its habitat differs unequivocally from the average conditions in Switzerland, while both A. flavicollis and A. sylvaticus could be considered as 'generalists' in the study area.
Main conclusions Although an adequate sampling design is the best way to collect ecological data for predictive modelling, this is a time and money consuming process and there are cases where time is simply not available, as for instance with endangered species conservation. On the other hand, museums, herbariums and other similar institutions are treasuring huge presence data sets. By applying the ENFA to such data it is possible to rapidly construct a habitat suitability model. The ENFA method not only provides two key measurements regarding the niche of a species (i.e. marginality and specialization), but also has ecological meaning, and allows the scientist to compare directly the niches of different species.     

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.     

Does seasonal fine‐tuning of climatic variables improve the performance of bioclimatic envelope models for migratory birds?

We examined the influence of 'seasonal fine-tuning' of climatic variables on the performance of bioclimatic envelope models of migrating birds. Using climate data and national bird atlas data from a 10 × 10 km uniform grid system in Finland, we tested whether the replacement of one 'baseline' set of variables including summer (June–August) temperature and precipitation variables with climate variables tailored ('fine-tuned') for each species individually improved the bird-climate models. The fine-tuning was conducted on the basis of time of arrival and early breeding of the species. Two generalized additive models (GAMs) were constructed for each of the 63 bird species studied, employing (1) the baseline climate variables and (2) the fine-tuned climate variables. Model performance was measured as explanatory power (deviance change) and predictive power (area under the curve; AUC) statistics derived from cross-validation. Fine-tuned climate variables provided, in many cases, statistically significantly improved model performance compared to using the same baseline set of variables for all the species. Model improvements mainly concerned bird species arriving and starting their breeding in May–June. We conclude that the use of the fine-tuned climate variables tailored for each species individually on the basis of their arrival and critical breeding periods can provide important benefits for bioclimatic modelling.     

Testing the ability of species distribution models to infer variable importance

Models of species’ distributions and niches are frequently used to infer the importance of range- and niche-defining variables. However, the degree to which these models can reliably identify important variables and quantify their influence remains unknown. Here we use a series of simulations to explore how well models can 1) discriminate between variables with different influence and 2) calibrate the magnitude of influence relative to an ‘omniscient’ model. To quantify variable importance, we trained generalized additive models (GAMs), Maxent and boosted regression trees (BRTs) on simulated data and tested their sensitivity to permutations in each predictor. Importance was inferred by calculating the correlation between permuted and unpermuted predictions, and by comparing predictive accuracy of permuted and unpermuted predictions using AUC and the continuous Boyce index. In scenarios with one influential and one uninfluential variable, models failed to discriminate reliably between variables when training occurrences were < 8–64, prevalence was > 0.5, spatial extent was small, environmental data had coarse resolution and spatial autocorrelation was low, or when pairwise correlation between environmental variables was |r| > 0.7. When two variables influenced the distribution equally, importance was underestimated when species had narrow or intermediate niche breadth. Interactions between variables in how they shaped the niche did not affect inferences about their importance. When variables acted unequally, the effect of the stronger variable was overestimated. GAMs and Maxent discriminated between variables more reliably than BRTs, but no algorithm was consistently well-calibrated vis-à-vis the omniscient model. Algorithm-specific measures of importance like Maxent's change-in-gain metric were less robust than the permutation test. Overall, high predictive accuracy did not connote robust inferential capacity. As a result, requirements for reliably measuring variable importance are likely more stringent than for creating models with high predictive accuracy.     

Weak climatic associations among British plant distributions

Aim Species distribution models (SDMs) are used to infer niche responses and predict climate change‐induced range shifts. However, their power to distinguish real and chance associations between spatially autocorrelated distribution and environmental data at continental scales has been questioned. Here this is investigated at a regional (10 km) scale by modelling the distributions of 100 plant species native to the UK. Location UK. Methods SDMs fitted using real climate data were compared with those utilizing simulated climate gradients. The simulated gradients preserve the exact values and spatial structure of the real ones, but have no causal relationships with any species and so represent an appropriate null model. SDMs were fitted as generalized linear models (GLMs) or by the Random Forest machine‐learning algorithm and were either non‐spatial or included spatially explicit trend surfaces or autocovariates as predictors. Results Species distributions were significantly but erroneously related to the simulated gradients in 86% of cases (P < 0.05 in likelihood‐ratio tests of GLMs), with the highest error for strongly autocorrelated species and gradients and when species occupied 50% of sites. Even more false effects were found when curvilinear responses were modelled, and this was not adequately mitigated in the spatially explicit models. Non‐spatial SDMs based on simulated climate data suggested that 70–80% of the apparent explanatory power of the real data could be attributable to its spatial structure. Furthermore, the niche component of spatially explicit SDMs did not significantly contribute to model fit in most species. Main conclusions Spatial structure in the climate, rather than functional relationships with species distributions, may account for much of the apparent fit and predictive power of SDMs. Failure to account for this means that the evidence for climatic limitation of species distributions may have been overstated. As such, predicted regional‐ and national‐scale impacts of climate change based on the analysis of static distribution snapshots will require re‐evaluation.     

Species traits are associated with the quality of bioclimatic models

Aim To analyse the effects of nine species trait variables on the accuracy of bioclimatic envelope models built for 98 butterfly species. Location Finland, northern Europe. Methods Data from a national butterfly atlas monitoring scheme (NAFI) collected from 1991–2003 with a resolution of 10 × 10 km were used in the analyses. Generalized additive models (GAMs) were constructed for 98 butterfly species to predict their occurrence as a function of climatic variables. Modelling accuracy was measured as the cross‐validation area under the curve (AUC) of the receiver–operating characteristic plot. Observed variation in modelling accuracy was related to species traits using multiple GAMs. The effects of phylogenetic relatedness among butterflies were accounted for by using generalized estimation equations. Results The values of the cross‐validation AUC for the 98 species varied between 0.56 and 1.00 with a mean of 0.79. Five species trait variables were included in the GAM that explained 71.4% of the observed variation in modelling accuracy. Four variables remained significant after accounting for phylogenetic relatedness. Species with high mobility and a long flight period were modelled less accurately than species with low mobility and a short flight period. Large species (>50 mm in wing span) were modelled more accurately than small ones. Species inhabiting mires had especially poor models, whereas the models for species inhabiting rocky outcrops, field verges and open fells were more accurate compared with other habitats. Main conclusions These results draw attention to the importance of species traits variables for species–climate impact models. Most importantly, species traits may have a strong impact on the performance of bioclimatic envelope models, and certain trait groups can be inherently difficult to model reliably. These uncertainties should be taken into account by downweighting or excluding species with such traits in studies applying bioclimatic modelling and making assessments of the impacts of climate change.     

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.     

Species traits affect the performance of species distribution models for plants in southern California

Questions: To what extent do plant species traits, including life history, life form, and disturbance response characteristics, affect the degree to which species distributions are determined by physical environmental factors? Is the strength of the relationship between species distribution and environment stronger in some disturbance‐response types than in others? Location: California southwest ecoregion, USA. Methods: We developed species distribution models (SDMs) for 45 plant species using three primary modeling methods (GLMs, GAMs, and Random Forests). Using AUC as a performance measure of prediction accuracy, and measure of the strength of species–environment correlations, we used regression analyses to compare the effects of fire disturbance response type, longevity, dispersal mechanism, range size, cover, species prevalence, and model type. Results: Fire disturbance response type explained more variation in model performance than any other variable, but other species and range characteristics were also significant. Differences in prediction accuracy reflected variation in species life history, disturbance response, and rarity. AUC was significantly higher for longer‐lived species, found at intermediate levels of abundance, and smaller range sizes. Models performed better for shrubs than sub‐shrubs and perennial herbs. The disturbance response type with the highest SDM accuracy was obligate‐seeding shrubs with ballistic dispersal that regenerate via fire‐cued germination from a dormant seed bank. Conclusions: The effect of species characteristics on predictability of species distributions overrides any differences in modeling technique. Prediction accuracy may be related to how a suite of species characteristics co‐varies along environmental gradients. Including disturbance response was important because SDMs predict the realized niche. Classification of plant species into disturbance response types may provide a strong framework for evaluating performance of SDMs.     

Predictability of stream insect distributions is dependent on niche position,but not on biological traits or taxonomic relatedness of species

Species distributions can be analysed under two perspectives: the niche‐based approach, which focuses on species–environment relationships; and the dispersal‐based approach, which focuses on metapopulation dynamics. The degree to which each of these two components affect species distributions may depend on habitat fragmentation, species traits and phylogenetic constraints. We analysed the distributions of 36 stream insect species across 60 stream sites in three drainage basins at high latitudes in Finland. We used binomial generalised linear models (GLMs) in which the predictor variables were environmental factors (E models), within‐basin spatial variables as defined by Moran's eigenvector maps (M models), among‐basin variability (B models), or a combination of the three (E + M + B models) sets of variables. Based on a comparative analysis, model performance was evaluated across all the species using Gaussian GLMs whereby the deviance accounted for by binomial GLMs was fitted on selected explanatory variables: niche position, niche breadth, site occupancy, biological traits and taxonomic relatedness. For each type of model, a reduced Gaussian GLM was eventually obtained after variable selection (Bayesian information criterion). We found that niche position was the only variable selected in all reduced models, implying that marginal species were better predicted than non‐marginal species. The influence of niche position was strongest in models based on environmental variables (E models) or a combination of all types of variables (E + M + B models), and weakest in spatial autocorrelation models (M models). This suggests that species–environment relationships prevail over dispersal processes in determining stream insect distributions at a regional scale. Our findings have clear implications for biodiversity conservation strategies, and they also emphasise the benefits of considering both the niche‐based and dispersal‐based approaches in species distribution modelling studies.     

基于植物-地形关系的物种丰富度空间格局预测——GAMs途径的一种应用

将基于样本调查数据的群落-生境因子回归分析与GIS支持下的植物属性空间格局预测结合起来,是国际上植被-环境关系定量研究的新途径。通用可加性模型（GAM）的非参数属性使之具有对不同数据类型的广泛适应性,成为这种“回归分析＋空间预测”途经的有效手段;不同程度上依赖于数字高程模型的环境空间数据集是实现空间预测的必要条件。介绍了这一新的研究途径,并应用于案例研究区域植物多样性指标空间格局的预测和分析。野外调查的一组样方地形特征指标和植物多样性指标（包括样方物种丰富度及乔木、灌木、草本、常绿木本、珍稀种类的丰富度）,分别作为预测变量和响应变量,建立GAM模型。结合研究区域10m分辨率的数字高程模型,对该区域植物物种丰富度的空间格局进行空间预测,并对预测模型和结果进行统计分析和检验。结果表明：（1）不同的多样性指标具有不同的模型结构和模拟效果,重复模拟的结果稳定性也不同,反映了所受地形因子影响的差异;（2）影响各多样性指标空间格局的地形变量主要是坡位和坡度等小尺度特征,大尺度海拔因素的影响并不显著;（3）模拟结果与独立检验数据的相关分析表明,对乔木种、草本种、珍稀种的模拟全部有效;对常绿种和样方物种总数的模拟部分有效;而对灌木种丰富度的预测基本失败。（4）模型预测变量有效性和全面性决定了模型对数据的解释能力,样本大小对模型的稳定性和可靠性也有显著影响。就地形因子对生境条件的代表性、模拟误差的来源及GAMs模型的优缺点和应用前景进行了讨论。     

Lung cancer rate predictions using generalized additive models

Predictions of lung cancer incidence and mortality are necessary for planning public health programs and clinical services. It is proposed that generalized additive models (GAMs) are practical for cancer rate prediction. Smooth equivalents for classical age-period, age-cohort, and age-period-cohort models are available using one-dimensional smoothing splines. We also propose using two-dimensional smoothing splines for age and period. Variance estimation can be based on the bootstrap. To assess predictive performance, we compared the models with a Bayesian age-period-cohort model. Model comparison used cross-validation and measures of predictive performance for recent predictions. The models were applied to data from the World Health Organization Mortality Database for females in five countries. Model choice between the age-period-cohort models and the two-dimensional models was equivocal with respect to cross-validation, while the two-dimensional GAMs had very good predictive performance. The Bayesian model performed poorly due to imprecise predictions and the assumption of linearity outside of observed data. In summary, the two-dimensional GAM performed well. The GAMs make the important prediction that female lung cancer rates in these countries will be stable or begin to decline in the future.     

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.     

Species‐area relationships of lemurs in a fragmented landscape in Madagascar

We used species‐area relationships (SARs) to investigate the effects of habitat loss on lemur biogeography. We measured species richness via visual surveys on line transects within 42 fragments of dry deciduous forest at the Ambanjabe field site in Ankarafantsika National Park, Madagascar. We measured human disturbance and habitat characteristics within 38 of the 42 fragments. We measured the distance between each fragment and the nearest settlement, continuous forest, and nearest neighboring fragment. We fit 10 candidate SAR models to the data using nonlinear least squares regression and compared them using Akaike's Information Criterion (AIC). To determine how habitat characteristics, as well as area, influenced species richness, we ran a hierarchical partitioning procedure to select which variables to include in generalized additive models (GAMs) and compared them using AIC. Contrary to expectations, we found that lemurs form convex SARs, without a “small island effect”, and with the power model being the most likely SAR model. Although we found that four variables (area, survey effort, and total human disturbance, and mean tree height) independently contributed greater than 10% of the variation in lemur species richness, only area was included in the most likely model. We suggest that the power model was the most likely SAR model and our inability to detect a “small island effect” are the result of Microcebus spp. being edge tolerant and capable of dispersing through matrix, scale issues in the study design, and low γ‐diversity in the landscape. However, more study is needed to determine what role human disturbance plays in influencing species richness in lemurs.