Aim: Forecasting changes in species distribution under future scenarios is one of the most prolific areas of application for species distribution models (SDMs). However, no consensus yet exists on the reliability of such models for drawing conclusions on species’ distribution response to changing climate. In this study, we provide an overview of common modelling practices in the field and assess the reliability of model predictions using a virtual species approach.Location: Global.Methods: We first review papers published between 2015 and 2019. Then, we use a virtual species approach and three commonly applied SDM algorithms (GLM, MaxEnt and random forest) to assess the estimated and actual predictive performance of models parameterized with different modelling settings and violations of modelling assumptions.Results: Most SDM papers relied on single models (65%) and small samples (N < 50, 62%), used presence‐only data (85%), binarized models' output (74%) and used a split‐sample validation (94%). Our simulation reveals that the split‐sample validation tends to be over‐optimistic compared to the real performance, whereas spatial block validation provides a more honest estimate, except when datasets are environmentally biased. The binarization of predicted probabilities of presence reduces models’ predictive ability considerably. Sample size is one of the main predictors of the real model accuracy, but has little influence on estimated accuracy. Finally, the inclusion of ecologically irrelevant predictors and the violation of modelling assumptions increases estimated accuracy but decreases real accuracy of model projections, leading to biased estimates of range contraction and expansion.Main conclusions: Our ability to predict future species distribution is low on average, particularly when models’ predictions are binarized. A robust validation by spatially independent samples is required, but does not rule out inflation of model accuracy by assumption violation. Our findings call for caution in the application and interpretation of SDM projections under different climates.

The IUCN (International Union for Conservation of Nature) Red List categories and criteria are the most widely used framework for assessing the relative extinction risk of species. The criteria are based on quantitative thresholds relating to the size, trends, and structure of species’ distributions and populations. However, data on these parameters are sparse and uncertain for many species and unavailable for others, potentially leading to their misclassification or classification as data deficient. We devised an approach that combines data on land‐cover change, species‐specific habitat preferences, population abundance, and dispersal distance to estimate key parameters (extent of occurrence, maximum area of occupancy, population size and trend, and degree of fragmentation) and hence predict IUCN Red List categories for species. We applied our approach to nonpelagic birds and terrestrial mammals globally (∼15,000 species). The predicted categories were fairly consistent with published IUCN Red List assessments, but more optimistic overall. We predicted 4.2% of species (467 birds and 143 mammals) to be more threatened than currently assessed and 20.2% of data deficient species (10 birds and 114 mammals) to be at risk of extinction. Incorporating the habitat fragmentation subcriterion reduced these predictions 1.5–2.3% and 6.4–14.9% (depending on the quantitative definition of fragmentation) for threatened and data deficient species, respectively, highlighting the need for improved guidance for IUCN Red List assessors on the application of this aspect of the IUCN Red List criteria. Our approach complements traditional methods of estimating parameters for IUCN Red List assessments. Furthermore, it readily provides an early‐warning system to identify species potentially warranting changes in their extinction‐risk category based on periodic updates of land‐cover information. Given our method relies on optimistic assumptions about species distribution and abundance, all species predicted to be more at risk than currently evaluated should be prioritized for reassessment.

Bioclimatic envelope models are commonly used to assess the influence of climate change on species' distributions and biodiversity patterns. Understanding how methodological choices influence these models is critical for a comprehensive evaluation of the estimated impacts. Here we systematically assess the performance of bioclimatic envelope models in relation to the selection of predictors, modeling technique, and pseudo‐absences. We considered (a) five different predictor sets, (b) seven commonly used modeling techniques and an ensemble model, and (c) three sets of pseudo‐absences (1,000 pseudo‐absences, 10,000 pseudo‐absences, and the same as the number of presences). For each combination of predictor set, modeling technique, and pseudo‐absence set, we fitted bioclimatic envelope models for 300 species of mammals, amphibians, and freshwater fish, and evaluated the predictive performance of the models using the true skill statistic (TSS), based on a spatially independent test set as well as cross‐validation. On average across the species, model performance was mostly influenced by the choice of predictor set, followed by the choice of modeling technique. The number of the pseudo‐absences did not have a strong effect on the model performance. Based on spatially independent testing, ensemble models based on species‐specific nonredundant predictor sets revealed the highest predictive performance. In contrast, the Random Forest technique yielded the highest model performance in cross‐validation but had the largest decrease in model performance when transferred to a different spatial context, thus highlighting the need for spatially independent model evaluation. We recommend building bioclimatic envelope models according to an ensemble modeling approach based on a nonredundant set of bioclimatic predictors, preferably selected for each modeled species.

The global expansion of agricultural land is a leading driver of climate change and biodiversity loss. However, the spatial resolution of current global land change models is relatively coarse, which limits environmental impact assessments. To address this issue, we developed global maps representing the potential for conversion into agricultural land at a resolution of 10 arc-seconds (approximately 300 m at the equator). We created the maps using artificial neural network (ANN) models relating locations of recent past conversions (2007–2020) into one of three cropland categories (cropland only, mosaics with >50% crops, and mosaics with <50% crops) to various predictor variables reflecting topography, climate, soil, and accessibility. Cross-validation of the models indicated good performance with area under the curve (AUC) values of 0.88–0.93. Hindcasting of the models from 1992 to 2006 revealed a similar high performance (AUC of 0.83–0.91), indicating that our maps provide representative estimates of current agricultural conversion potential provided that the drivers underlying agricultural expansion patterns remain the same. Our maps can be used to downscale projections of global land change models to more fine-grained patterns of future agricultural expansion, which is an asset for global environmental assessments.

Aim: Forecasting changes in species distribution under future scenarios is one of the most prolific areas of application for species distribution models (SDMs). However, no consensus yet exists on the reliability of such models for drawing conclusions on species distribution response to changing climate. In this study we provide an overview of common modelling practices in the field and assess model predictions reliability using a virtual species approach. Location: Global Methods: We first provide an overview of common modelling practices in the field by reviewing the papers published in the last 5 years. Then, we use a virtual species approach and three commonly applied SDM algorithms (GLM, MaxEnt and Random Forest) to assess the estimated (cross-validated) and actual predictive performance of models parameterized with different modelling settings and violations of modelling assumptions. Results: Our literature review shows that most papers that model species distribution under climate change rely on single models (65%) and small samples (< 50 presence points, 62%), use presence-only data (85%), and binarize models’ output to estimate range shift, contraction or expansion (74%). Our virtual species approach reveals that the estimated predictive performance tends to be over-optimistic compared to the real predictive performance. Further, the binarization of predicted probabilities of presence reduces models’ predictive ability considerably. Sample size is one of the main predictors of real accuracy, but has little influence on estimated accuracy. Finally, the inclusion of irrelevant predictors and the violation of modelling assumptions increases estimated accuracy but decreases real accuracy of model projections, leading to biased estimates of range contraction and expansion. Main conclusions: Our study calls for extreme caution in the application and interpretation of SDMs in the context of biodiversity conservation and climate change research, especially when modelling a large number of species where species-specific model settings become impracticable.

Aim: We aimed to assess potential climate change impacts on the distribution of a cold‐adapted terrestrial amphibian that shows strong intraspecific differentiation.Location: Alps and Dinarides.Taxon: Alpine salamander (Salamandra atra).Methods: We built SDMs for each of two major intraspecific lineages (S. a. atra, which is found throughout the Northern Alps, and S. a. prenjensis, which appears sparsely along the Dinarides) and for the entire species, using occurrence points from a carefully curated database, climate data with 1 km² spatial resolution and eight modelling techniques. We projected climatically suitable areas to 2070 under two climate scenarios (RCP2.6 and RCP8.5), using 24 general circulation models.Results: For S. a. atra, under RCP2.6 scenario, we detected a 3% increase in the extent of climatically suitable areas in the Alps (although with low model agreement), yet a 6% decrease under the RCP8.5 scenario. For S. a. prenjensis, we detected a decrease in the extent of climatically suitable areas in the Dinarides between 7% and 45% (RCP2.6 and RCP8.5, respectively). The SDM predictions for the entire species were most in line with those of the S. a. atra model. Although climate variables were not equally strong in predicting the climatic suitability for both lineages, the minimum temperature of the coldest month revealed an important predictor for the entire species, with clear decreases in suitability towards higher temperature.Main Conclusions: All models reveal a considerable decrease in climate suitability throughout most of the range of S. atra, which is particularly visible in the Dinarides. We highlight the importance of considering intraspecific variation when modelling climate change impacts on geographically differentiated species whose populations vary in their climatic niche. We provide our study results (occurrence data and maps) via a web application that can be useful for guiding conservation efforts.