Microclimate species distribution models estimate lower levels of climate-related habitat loss for salamanders

Species distribution models (SDMs) largely rely on free-air temperatures at coarse spatial resolutions to predict habitat suitability, potentially overlooking important microhabitat. Integrating microclimate data into SDMs may improve predictions of organismal responses to climate change and support targeting of conservation assets at biologically relevant scales, especially for small, dispersal-limited species vulnerable to climate-change-induced range loss. We integrated microclimate data that account for the buffering effects of forest vegetation into SDMs at a very high spatial resolution (3 m²) for three plethodontid salamander species in Great Smoky Mountains National Park (North Carolina and Tennessee). Microclimate SDMs were used to characterize potential changes to future plethodontid habitat, including habitat suitability and habitat spatial patterns. Additionally, we evaluated spatial discrepancies between predictions of habitat suitability developed with microclimate and coarse-resolution, free-air climate data. Microclimate SDMs indicated substantial losses to plethodontid ranges and highly suitable habitat by mid-century, but at much more conservative levels than coarse-resolution models. Coarse-resolution SDMs generally estimated higher mid-century losses to plethodontid habitat compared to microclimate models and consistently undervalued areas containing highly suitable microhabitat. Furthermore, microclimate SDMs revealed potential areas of future gain in highly suitable habitat within current species’ ranges, which may serve as climatic microrefugia. Taken together, this study highlights the need to develop microclimate SDMs that account for vegetation and its biophysical effects on near-surface temperatures. As microclimate datasets become increasingly available across the world, their integration into correlative and mechanistic SDMs will be imperative for accurately estimating organismal responses to climate change and helping environmental managers tasked with spatially prioritizing conservation assets.     

Poor Transferability of Species Distribution Models for a Pelagic Predator,the Grey Petrel,Indicates Contrasting Habitat Preferences across Ocean Basins

Species distribution models (SDMs) are increasingly applied in conservation management to predict suitable habitat for poorly known populations. High predictive performance of SDMs is evident in validations performed within the model calibration area (interpolation), but few studies have assessed SDM transferability to novel areas (extrapolation), particularly across large spatial scales or pelagic ecosystems. We performed rigorous SDM validation tests on distribution data from three populations of a long-ranging marine predator, the grey petrel Procellaria cinerea, to assess model transferability across the Southern Hemisphere (25-65°S). Oceanographic data were combined with tracks of grey petrels from two remote sub-Antarctic islands (Antipodes and Kerguelen) using boosted regression trees to generate three SDMs: one for each island population, and a combined model. The predictive performance of these models was assessed using withheld tracking data from within the model calibration areas (interpolation), and from a third population, Marion Island (extrapolation). Predictive performance was assessed using k-fold cross validation and point biserial correlation. The two population-specific SDMs included the same predictor variables and suggested birds responded to the same broad-scale oceanographic influences. However, all model validation tests, including of the combined model, determined strong interpolation but weak extrapolation capabilities. These results indicate that habitat use reflects both its availability and bird preferences, such that the realized distribution patterns differ for each population. The spatial predictions by the three SDMs were compared with tracking data and fishing effort to demonstrate the conservation pitfalls of extrapolating SDMs outside calibration regions. This exercise revealed that SDM predictions would have led to an underestimate of overlap with fishing effort and potentially misinformed bycatch mitigation efforts. Although SDMs can elucidate potential distribution patterns relative to large-scale climatic and oceanographic conditions, knowledge of local habitat availability and preferences is necessary to understand and successfully predict region-specific realized distribution patterns.     

Identifying the relevant spatial and temporal scales in plant species occurrence models: The case of arable weeds in landscape mosaic of crops

Species distribution models (SDMs) represent potential valuable tools to explore factors underlying species occurrence over a large range of spatial scales. However, a recurrent problem with this approach is identifying the appropriate spatial and temporal scales for modeling. This problem is reinforced in plant populations for which it is often difficult to evaluate the limits of habitat patches. In this study, we aimed at developing SDMs for 13 arable weeds in highly dynamic small agricultural region. Although weed dynamic is widely thought to result from local processes, we explored the spatial and temporal scales that would best explain species occurrence over the area. Models were developed using weed occurrence data in 58 fields over four consecutive years (2008–2011) and spatial organization of management practices over the landscape for eight consecutive years (2004–2011). We used a model selection approach based on the minimum AIC criteria to select the best SDMs. Results showed that SDMs can successfully be applied to model weed occurrence over a small region. The appropriate temporal scale to consider in weed SDMs should encompass several years to reflect the effect of management history while the relevant spatial scale should extend beyond the crop field itself and include the field border and neighboring fields. This study illustrates that adopting a multiple scale approach is successful to model plant occurrence over a highly dynamic landscape.     

Modeling plant species distributions under future climates: how fine scale do climate projections need to be?

Recent studies suggest that species distribution models (SDMs) based on fine‐scale climate data may provide markedly different estimates of climate‐change impacts than coarse‐scale models. However, these studies disagree in their conclusions of how scale influences projected species distributions. In rugged terrain, coarse‐scale climate grids may not capture topographically controlled climate variation at the scale that constitutes microhabitat or refugia for some species. Although finer scale data are therefore considered to better reflect climatic conditions experienced by species, there have been few formal analyses of how modeled distributions differ with scale. We modeled distributions for 52 plant species endemic to the California Floristic Province of different life forms and range sizes under recent and future climate across a 2000‐fold range of spatial scales (0.008–16 km²). We produced unique current and future climate datasets by separately downscaling 4 km climate models to three finer resolutions based on 800, 270, and 90 m digital elevation models and deriving bioclimatic predictors from them. As climate‐data resolution became coarser, SDMs predicted larger habitat area with diminishing spatial congruence between fine‐ and coarse‐scale predictions. These trends were most pronounced at the coarsest resolutions and depended on climate scenario and species' range size. On average, SDMs projected onto 4 km climate data predicted 42% more stable habitat (the amount of spatial overlap between predicted current and future climatically suitable habitat) compared with 800 m data. We found only modest agreement between areas predicted to be stable by 90 m models generalized to 4 km grids compared with areas classified as stable based on 4 km models, suggesting that some climate refugia captured at finer scales may be missed using coarser scale data. These differences in projected locations of habitat change may have more serious implications than net habitat area when predictive maps form the basis of conservation decision making.     

Spatial modelling of ecological indicator values improves predictions of plant distributions in complex landscapes

Ecologically meaningful predictors are often neglected in plant distribution studies, resulting in incomplete niche quantification and low predictive power of species distribution models (SDMs). Because environmental data are rare and expensive to collect, and because their relationship with local climatic and topographic conditions are complex, mapping them over large geographic extents and at high spatial resolution remains a major challenge. Here, we propose to derive environmental data layers by mapping ecological indicator values in space. We combined ~6 million plant occurrences with expert-based plant ecological indicator values (EIVs) of 3600 species in Switzerland. EIVs representing local soil properties (pH, moisture, moisture variability, aeration, humus and nutrients) and climatic conditions (continentality, light) were modelled at 93 m spatial resolution with the Random Forest algorithm and 16 predictors representing meso-climate, land use, topography and geology. Models were evaluated and predictions of EIVs were compared with soil inventory data. We mapped each EIV separately and evaluated EIV importance in explaining the distribution of 500 plant species using SDMs with a set of 30 environmental predictors. Finally, we tested how they improve an ensemble of SDMs compared to a standard set of predictors for ca 60 plant species. All EIV models showed excellent performance (|r| > 0.9) and predictions were correlated reasonably (|r| > 0.4) to soil properties measured in the field. Resulting EIV maps were among the most important predictors in SDMs. Also, in ensemble SDMs overall predictive performance increased, mainly through improved model specificity reducing species range overestimation. Combining large citizen science databases to expert-based EIVs is a powerful and cost–effective approach for generalizing local edaphic and climatic conditions over large areas. Producing ecologically meaningful predictors is a first step for generating better predictions of species distribution which is of main importance for decision makers in conservation and environmental management projects.     

Behavioural context of multi-scale species distribution models assessed by radio-tracking

Incorporating ecological processes and animal behaviour into Species Distribution Models (SDMs) is difficult. In species with a central resting or breeding place, there can be conflict between the environmental requirements of the ‘central place’ and foraging habitat. We apply a multi-scale SDM to examine habitat trade-offs between the central place, roost sites, and foraging habitat in Myotis nattereri. We validate these derived associations using habitat selection from behavioural observations of radio-tracked bats. A Generalised Linear Model (GLM) of roost occurrence using land cover variables with mixed spatial scales indicated roost occurrence was positively associated with woodland on a fine scale and pasture on a broad scale. Habitat selection of radio-tracked bats mirrored the SDM with bats selecting for woodland in the immediate vicinity of individual roosts but avoiding this habitat in foraging areas, whilst pasture was significantly positively selected for in foraging areas. Using habitat selection derived from radio-tracking enables a multi-scale SDM to be interpreted in a behavioural context. We suggest that the multi-scale SDM of M. nattereri describes a trade-off between the central place and foraging habitat. Multi-scale methods provide a greater understanding of the ecological processes which determine where species occur and allow integration of behavioural processes into SDMs. The findings have implications when assessing the resource use of a species at a single point in time. Doing so could lead to misinterpretation of habitat requirements as these can change within a short time period depending on specific behaviour, particularly if detectability changes depending on behaviour.     

Ensemble modelling of species distribution: the effects of geographical and environmental ranges

The aim of this study was to analyse the effects of species geographical and environmental ranges on the predictive performances of species distribution models (SDMs). We explored the usefulness of ensemble modelling approaches and tested whether species attributes influenced the outcomes of such approaches. Eight SDMs were used to model the current distribution of 35 fish species at 1110 stream sections in France. We first quantified the consensus among the resulting set of predictions for each fish species. Next, we created an average model by taking the average of the individual model predictions and tested whether the average model improved the predictive performances of single SDMs. Lastly, we described the ranges of fish species along four gradients: latitudinal, thermal, stream gradient (i.e. upstream‐downstream) and elevation. After accounting for the effects of phylogenetic relatedness and species prevalence, these four species attributes were related to the observed variations in both consensus among SDMs and predictive performances by using generalized estimation equations. Our results highlight the usefulness of ensemble approaches for identifying geographical areas of agreement among predictions. Although the geographical extent of species had no effect on the performances of SDMs, we demonstrated that more consensual and accurate predictions were obtained for species with low thermal and elevation ranges, validating the hypothesis that specialist species yield models with higher accuracy than generalist ones. We emphasized that significant improvements in the accuracy of SDMs can be achieved by using an average model. Furthermore, these improvements were higher for species with smaller ranges along the four gradients studied. The geographical extent and ranges of species along environmental gradients provide promising insights into our understanding of uncertainties in species distribution modelling.     

Presence-absence versus presence-only modelling methods for predicting bird habitat suitability

Habitat suitability models can be generated using methods requiring information on species presence or species presence and absence. Knowledge of the predictive performance of such methods becomes a critical issue to establish their optimal scope of application for mapping current species distributions under different constraints. Here, we use breeding bird atlas data in Catalonia as a working example and attempt to analyse the relative performance of two methods: the Ecological Niche factor Analysis (ENFA) using presence data only and Generalised Linear Models (GLM) using presence/absence data. Models were run on a set of forest species with similar habitat requirements, but with varying occurrence rates (prevalence) and niche positions (marginality). Our results support the idea that GLM predictions are more accurate than those obtained with ENFA. This was particularly true when species were using available habitats proportionally to their suitability, making absence data reliable and useful to enhance model calibration. Species marginality in niche space was also correlated to predictive accuracy, i.e. species with less restricted ecological requirements were modelled less accurately than species with more restricted requirements. This pattern was irrespective of the method employed. Models for wide‐ranging and tolerant species were more sensitive to absence data, suggesting that presence/absence methods may be particularly important for predicting distributions of this type of species. We conclude that modellers should consider that species ecological characteristics are critical in determining the accuracy of models and that it is difficult to predict generalist species distributions accurately and this is independent of the method used. Being based on distinct approaches regarding adjustment to data and data quality, habitat distribution modelling methods cover different application areas, making it difficult to identify one that should be universally applicable. Our results suggest however, that if absence data is available, methods using this information should be preferably used in most situations.     

A Statistical Comparison between Less and Common Applied Models to Estimate Geographical Distribution of Endangered Species (<Emphasis Type="Italic">Felis margarita</Emphasis>) in Central Iran

Species distribution in space is important in habitat conservation and biodiversity protection, so gaining knowledge about species range would be worthwhile to rescue endangered species and plan conservation policy. This study evaluates and compares the performance of an array of Species Distribution Models (SDMs), namely RF, SVM, MaxEnt, GLMNET, and MARS, in predicting rare sand cat distribution across a large unprotected sand dune area in central Iran. Due to absence of reliable data and difficulties in recording the species itself, the SDMs were challenged by limited data including 55 absence (background) and 40 presence points as well as nine climatic and geological parameters that influence on species distribution, including humidity, maximum, minimum and mean temperature, precipitation, amount of sunshine, ground water level, aspect, and DEM. Moreover, each model was replicated 20 times and the statistics including TSS, AUC, COR and Deviance were computed. Then, based on computed statistics, the model performances were evaluated by TUKEY and ANOVA. Finally, ensemble map was obtained by weighted approach using AUC. The results of this study showed that complex machine learning methods, like SVM, RF, and MaxEnt are more outperformed to predict the distribution of rare species.     

Niche variability and its consequences for species distribution modeling

When species distribution models (SDMs) are used to predict how a species will respond to environmental change, an important assumption is that the environmental niche of the species is conserved over evolutionary time-scales. Empirical studies conducted at ecological time-scales, however, demonstrate that the niche of some species can vary in response to environmental change. We use habitat and locality data of five species of stream fishes collected across seasons to examine the effects of niche variability on the accuracy of projections from Maxent, a popular SDM. We then compare these predictions to those from an alternate method of creating SDM projections in which a transformation of the environmental data to similar scales is applied. The niche of each species varied to some degree in response to seasonal variation in environmental variables, with most species shifting habitat use in response to changes in canopy cover or flow rate. SDMs constructed from the original environmental data accurately predicted the occurrences of one species across all seasons and a subset of seasons for two other species. A similar result was found for SDMs constructed from the transformed environmental data. However, the transformed SDMs produced better models in ten of the 14 total SDMs, as judged by ratios of mean probability values at known presences to mean probability values at all other locations. Niche variability should be an important consideration when using SDMs to predict future distributions of species because of its prevalence among natural populations. The framework we present here may potentially improve these predictions by accounting for such variability.     

Exploring the spatiotemporal dynamics of habitat suitability to improve conservation management of a vulnerable plant species

Ongoing declines in biodiversity caused by global environmental changes call for adaptive conservation management, including the assessment of habitat suitability spatiotemporal dynamics potentially affecting species persistence. Remote sensing (RS) provides a wide-range of satellite-based environmental variables that can be fed into species distribution models (SDMs) to investigate species-environment relations and forecast responses to change. We address the spatiotemporal dynamics of species’ habitat suitability at the landscape level by combining multi-temporal RS data with SDMs for analysing inter-annual habitat suitability dynamics. We implemented this framework with a vulnerable plant species (Veronica micrantha), by combining SDMs with a time-series of RS-based metrics of vegetation functioning related to primary productivity, seasonality, phenology and actual evapotranspiration. Besides RS variables, predictors related to landscape structure, soils and wildfires were ranked and combined through multi-model inference (MMI). To assess recent dynamics, a habitat suitability time-series was generated through model hindcasting. MMI highlighted the strong predictive ability of RS variables related to primary productivity and water availability for explaining the test-species distribution, along with soil, wildfire regime and landscape composition. The habitat suitability time-series revealed the effects of short-term land cover changes and inter-annual variability in climatic conditions. Multi-temporal SDMs further improved predictions, benefiting from RS time-series. Overall, results emphasize the integration of landscape attributes related to function, composition and spatial configuration for improving the explanation of ecological patterns. Moreover, coupling SDMs with RS functional metrics may provide early-warnings of future environmental changes potentially impacting habitat suitability. Applications discussed include the improvement of biodiversity monitoring and conservation strategies.     

Using species distribution models to predict new occurrences for rare plants

Aim  To evaluate a suite of species distribution models for their utility as predictors of suitable habitat and as tools for new population discovery of six rare plant species that have both narrow geographical ranges and specialized habitat requirements.
Location  The Rattlesnake Creek Terrane (RCT) of the Shasta-Trinity National Forest in the northern California Coast Range of the United States.
Methods  We used occurrence records from 25 years of US Forest Service botanical surveys, environmental and remotely sensed climate data to model the distributions of the target species across the RCT. The models included generalized linear models (GLM), artificial neural networks (ANN), random forests (RF) and maximum entropy (ME). From the results we generated predictive maps that were used to identify areas of high probability occurrence. We made field visits to the top-ranked sites to search for new populations of the target species.
Results  Random forests gave the best results according to area under the curve and Kappa statistics, although ME was in close agreement. While GLM and ANN also gave good results, they were less restrictive and more varied than RF and ME. Cross-model correlations were the highest for species with the most records and declined with record numbers. Model assessment using a separate dataset confirmed that RF provided the best predictions of appropriate habitat. Use of RF output to prioritize search areas resulted in the discovery of 16 new populations of the target species.
Main conclusions  Species distribution models, such as RF and ME, which use presence data and information about the background matrix where species do not occur, may be an effective tool for new population discovery of rare plant species, but there does appear to be a lower threshold in the number of occurrences required to build a good model.     

Why georeferencing matters: Introducing a practical protocol to prepare species occurrence records for spatial analysis

Species Distribution Models (SDMs) are widely used to understand environmental controls on species’ ranges and to forecast species range shifts in response to climatic changes. The quality of input data is crucial determinant of the model's accuracy. While museum records can be useful sources of presence data for many species, they do not always include accurate geographic coordinates. Therefore, actual locations must be verified through the process of georeferencing. We present a practical, standardized manual georeferencing method (the Spatial Analysis Georeferencing Accuracy (SAGA) protocol) to classify the spatial resolution of museum records specifically for building improved SDMs. We used the high‐elevation plant Saxifraga austromontana Wiegand (Saxifragaceae) as a case study to test the effect of using this protocol when developing an SDM. In MAXENT, we generated and compared SDMs using a comprehensive occurrence dataset that had undergone three different levels of georeferencing: (1) trained using all publicly available herbarium records of the species, minus outliers (2) trained using herbarium records claimed to be previously georeferenced, and (3) trained using herbarium records that we have manually georeferenced to a ≤ 1‐km resolution using the SAGA protocol. Model predictions of suitable habitat for S. austromontana differed greatly depending on georeferencing level. The SDMs fitted with presence locations georeferenced using SAGA outperformed all others. Differences among models were exacerbated for future distribution predictions. Under rapid climate change, accurately forecasting the response of species becomes increasingly important. Failure to georeference location data and cull inaccurate samples leads to erroneous model output, limiting the utility of spatial analyses. We present a simple, standardized georeferencing method to be adopted by curators, ecologists, and modelers to improve the geographic accuracy of museum records and SDM predictions.     

Incorporating uncertainty in predictive species distribution modelling

Motivated by the need to solve ecological problems (climate change, habitat fragmentation and biological invasions), there has been increasing interest in species distribution models (SDMs). Predictions from these models inform conservation policy, invasive species management and disease-control measures. However, predictions are subject to uncertainty, the degree and source of which is often unrecognized. Here, we review the SDM literature in the context of uncertainty, focusing on three main classes of SDM: niche-based models, demographic models and process-based models. We identify sources of uncertainty for each class and discuss how uncertainty can be minimized or included in the modelling process to give realistic measures of confidence around predictions. Because this has typically not been performed, we conclude that uncertainty in SDMs has often been underestimated and a false precision assigned to predictions of geographical distribution. We identify areas where development of new statistical tools will improve predictions from distribution models, notably the development of hierarchical models that link different types of distribution model and their attendant uncertainties across spatial scales. Finally, we discuss the need to develop more defensible methods for assessing predictive performance, quantifying model goodness-of-fit and for assessing the significance of model covariates.     

From topography to hydrology—The modifiable area unit problem impacts freshwater species distribution models

Species distribution models (SDMs) are statistical tools to identify potentially suitable habitats for species. For SDMs in river ecosystems, species occurrences and predictor data are often aggregated across subcatchments that serve as modeling units. The level of aggregation (i.e., model resolution) influences the statistical relationships between species occurrences and environmental predictors—a phenomenon known as the modifiable area unit problem (MAUP), making model outputs directly contingent on the model resolution. Here, we test how model performance, predictor importance, and the spatial congruence of species predictions depend on the model resolution (i.e., average subcatchment size) of SDMs. We modeled the potential habitat suitability of 50 native fish species in the upper Danube catchment at 10 different model resolutions. Model resolutions were derived using a 90‐m digital‐elevation model by using the GRASS‐GIS module r.watershed. Here, we decreased the average subcatchment size gradually from 632 to 2 km². We then ran ensemble SDMs based on five algorithms using topographical, climatic, hydrological, and land‐use predictors for each species and resolution. Model evaluation scores were consistently high, as sensitivity and True Skill Statistic values ranged from 86.1–93.2 and 0.61–0.73, respectively. The most contributing predictor changed from topography at coarse, to hydrology at fine resolutions. Climate predictors played an intermediate role for all resolutions, while land use was of little importance. Regarding the predicted habitat suitability, we identified a spatial filtering from coarse to intermediate resolutions. The predicted habitat suitability within a coarse resolution was not ported to all smaller, nested subcatchments, but only to a fraction that held the suitable environmental conditions. Across finer resolutions, the mapped predictions were spatially congruent without such filter effect. We show that freshwater SDM predictions can have consistently high evaluation scores while mapped predictions differ significantly and are highly contingent on the underlying subcatchment size. We encourage building freshwater SDMs across multiple catchment sizes, to assess model variability and uncertainties in model outcomes emerging from the MAUP.     

A comparison of absolute performance of different correlative and mechanistic species distribution models in an independent area

To investigate the comparative abilities of six different bioclimatic models in an independent area, utilizing the distribution of eight different species available at a global scale and in Australia. Global scale and Australia. We tested a variety of bioclimatic models for eight different plant species employing five discriminatory correlative species distribution models (SDMs) including Generalized Linear Model (GLM), MaxEnt, Random Forest (RF), Boosted Regression Tree (BRT), Bioclim, together with CLIMEX (CL) as a mechanistic niche model. These models were fitted using a training dataset of available global data, but with the exclusion of Australian locations. The capabilities of these techniques in projecting suitable climate, based on independent records for these species in Australia, were compared. Thus, Australia is not used to calibrate the models and therefore it is as an independent area regarding geographic locations. To assess and compare performance, we utilized the area under the receiver operating characteristic (ROC) curves (AUC), true skill statistic (TSS), and fractional predicted areas for all SDMs. In addition, we assessed satisfactory agreements between the outputs of the six different bioclimatic models, for all eight species in Australia. The modeling method impacted on potential distribution predictions under current climate. However, the utilization of sensitivity and the fractional predicted areas showed that GLM, MaxEnt, Bioclim, and CL had the highest sensitivity for Australian climate conditions. Bioclim calculated the highest fractional predicted area of an independent area, while RF and BRT were poor. For many applications, it is difficult to decide which bioclimatic model to use. This research shows that variable results are obtained using different SDMs in an independent area. This research also shows that the SDMs produce different results for different species; for example, Bioclim may not be good for one species but works better for other species. Also, when projecting a “large” number of species into novel environments or in an independent area, the selection of the “best” model/technique is often less reliable than an ensemble modeling approach. In addition, it is vital to understand the accuracy of SDMs' predictions. Further, while TSS, together with fractional predicted areas, are appropriate tools for the measurement of accuracy between model results, particularly when undertaking projections on an independent area, AUC has been proved not to be. Our study highlights that each one of these models (CL, Bioclim, GLM, MaxEnt, BRT, and RF) provides slightly different results on projections and that it may be safer to use an ensemble of models.     

A spatially explicit method for evaluating accuracy of species distribution models

Aim Models predicting the spatial distribution of animals are increasingly used in wildlife management and conservation planning. There is growing recognition that common methods of evaluating species distribution model (SDM) accuracy, as a global overall value of predictive ability, could be enhanced by spatially evaluating the model thereby identifying local areas of relative predictive strength and weakness. Current methods of spatial SDM model assessment focus on applying local measures of spatial autocorrelation to SDM residuals, which require quantitative model outputs. However, SDM outputs are often probabilistic (relative probability of species occurrence) or categorical (species present or absent). The goal of this paper was to develop a new method, using a conditional randomization technique, which can be applied to directly spatially evaluate probabilistic and categorical SDMs. Location Eastern slopes, Rocky Mountains, Alberta, Canada. Methods We used predictions from seasonal grizzly bear (Ursus arctos) resource selection functions (RSF) models to demonstrate our spatial evaluation technique. Local test statistics computed from bear telemetry locations were used to identify areas where bears were located more frequently than predicted. We evaluated the spatial pattern of model inaccuracies using a measure of spatial autocorrelation, local Moran’s I. Results We found the model to have non‐stationary patterns in accuracy, with clusters of inaccuracies located in central habitat areas. Model inaccuracies varied seasonally, with the summer model performing the best and the least error in areas with high RSF values. The landscape characteristics associated with model inaccuracies were examined, and possible factors contributing to RSF error were identified. Main conclusions The presented method complements existing spatial approaches to model error assessment as it can be used with probabilistic and categorical model output, which is typical for SDMs. We recommend that SDM accuracy assessments be done spatially and resulting accuracy maps included in model metadata.     

Transferable species distribution modelling: Comparative performance of Generalised Functional Response models

Predictive species distribution models (SDMs) are becoming increasingly important in ecology, in the light of rapid environmental change. However, the predictions of most current SDMs are specific to the habitat composition of the environments in which they were fitted. This may limit SDM predictive power because species may respond differently to a given habitat depending on the availability of all habitats in their environment, a phenomenon known as a functional response in resource selection. The Generalised Functional Response (GFR) framework captures this dependence by formulating the SDM coefficients as functions of habitat availability. The original GFR implementation used global polynomial functions of habitat availability to describe the functional responses. In this study, we develop several refinements of this approach and compare their predictive performance using two simulated and two real datasets. We first use local radial basis functions (RBF), a more flexible approach than global polynomials, to represent the habitat selection coefficients, and balance bias with precision via regularization to prevent overfitting. Second, we use the RBF-GFR and GFR models in combination with the classification and regression tree CART, which has more flexibility and better predictive powers for non-linear modelling. As further extensions, we use random forests (RFs) and extreme gradient boosting (XGBoost), ensemble approaches that consistently lead to variance reduction in generalization error. We find that the different methods are ranked consistently across the datasets for out-of-data prediction. The traditional stationary approach to SDMs and the GFR model consistently perform at the bottom of the ranking (simple SDMs underfit, and polynomial GFRs overfit the data). The best methods in our list provide non-negligible improvements in predictive performance, in some cases taking the out-of-sample R2 from 0.3 up to 0.7 across datasets. At times of rapid environmental change and spatial non-stationarity ignoring the effects of functional responses on SDMs, results in two different types of prediction bias (under-prediction or mis-positioning of distribution hotspots). However, not all functional response models perform equally well. The more volatile polynomial GFR models can generate biases through over-prediction. Our results indicate that there are consistently robust GFR approaches that achieve impressive gains in transferability across very different datasets.     

Wrong,but useful: regional species distribution models may not be improved by range‐wide data under biased sampling

Species distribution modeling (SDM) is an essential method in ecology and conservation. SDMs are often calibrated within one country's borders, typically along a limited environmental gradient with biased and incomplete data, making the quality of these models questionable. In this study, we evaluated how adequate are national presence‐only data for calibrating regional SDMs. We trained SDMs for Egyptian bat species at two different scales: only within Egypt and at a species‐specific global extent. We used two modeling algorithms: Maxent and elastic net, both under the point‐process modeling framework. For each modeling algorithm, we measured the congruence of the predictions of global and regional models for Egypt, assuming that the lower the congruence, the lower the appropriateness of the Egyptian dataset to describe the species' niche. We inspected the effect of incorporating predictions from global models as additional predictor (“prior”) to regional models, and quantified the improvement in terms of AUC and the congruence between regional models run with and without priors. Moreover, we analyzed predictive performance improvements after correction for sampling bias at both scales. On average, predictions from global and regional models in Egypt only weakly concur. Collectively, the use of priors did not lead to much improvement: similar AUC and high congruence between regional models calibrated with and without priors. Correction for sampling bias led to higher model performance, whatever prior used, making the use of priors less pronounced. Under biased and incomplete sampling, the use of global bats data did not improve regional model performance. Without enough bias‐free regional data, we cannot objectively identify the actual improvement of regional models after incorporating information from the global niche. However, we still believe in great potential for global model predictions to guide future surveys and improve regional sampling in data‐poor regions.     

Incorporating intraspecific variation into species distribution models improves distribution predictions,but cannot predict species traits for a wide-spread plant species

The most common approach to predicting how species ranges and ecological functions will shift with climate change is to construct correlative species distribution models (SDMs). These models use a species’ climatic distribution to determine currently suitable areas for the species and project its potential distribution under future climate scenarios. A core, rarely tested, assumption of SDMs is that all populations will respond equivalently to climate. Few studies have examined this assumption, and those that have rarely dissect the reasons for intraspecific differences. Focusing on the arctic-alpine cushion plant Silene acaulis, we compared predictive accuracy from SDMs constructed using the species’ full global distribution with composite predictions from separate SDMs constructed using subpopulations defined either by genetic or habitat differences. This is one of the first studies to compare multiple ways of constructing intraspecific-level SDMs with a species-level SDM. We also examine the contested relationship between relative probability of occurrence and species performance or ecological function, testing if SDM output can predict individual performance (plant size) and biotic interactions (facilitation). We found that both genetic- and habitat-informed SDMs are considerably more accurate than a species-level SDM, and that the genetic model substantially differs from and outperforms the habitat model. While SDMs have been used to infer population performance and possibly even biotic interactions, in our system these relationships were extremely weak. Our results indicate that individual subpopulations may respond differently to climate, although we discuss and explore several alternative explanations for the superior performance of intraspecific-level SDMs. We emphasize the need to carefully examine how to best define intraspecific-level SDMs as well as how potential genetic, environmental, or sampling variation within species ranges can critically affect SDM predictions. We urge caution in inferring population performance or biotic interactions from SDM predictions, as these often-assumed relationships are not supported in our study.