Explore the vast range of titles available.

[This corrects the article DOI: 10.3389/fpls.2026.1748030.].

Species distribution modeling (SDM) is widely used in ecology and conservation. Currently, the most available data for SDM are species presence-only records (available through digital databases). There have been many studies comparing the performance of alternative algorithms for modeling presence-only data. Among these, a 2006 paper from Elith and colleagues has been particularly influential in the field, partly because they used several novel methods (at the time) on a global data set that included independent presence–absence records for model evaluation. Since its publication, some of the algorithms have been further developed and new ones have emerged. In this paper, we explore patterns in predictive performance across methods, by reanalyzing the same data set (225 species from six different regions) using updated modeling knowledge and practices. We apply well-established methods such as generalized additive models and MaxEnt, alongside others that have received attention more recently, including regularized regressions, point-process weighted regressions, random forests, XGBoost, support vector machines, and the ensemble modeling framework biomod. All the methods we use include background samples (a sample of environments in the landscape) for model fitting. We explore impacts of using weights on the presence and background points in model fitting. We introduce new ways of evaluating models fitted to these data, using the area under the precision-recall gain curve, and focusing on the rank of results. We find that the way models are fitted matters. The top method was an ensemble of tuned individual models. In contrast, ensembles built using the biomod framework with default parameters performed no better than single moderate performing models. Similarly, the second top performing method was a random forest parameterized to deal with many background samples (contrasted to relatively few presence records), which substantially outperformed other random forest implementations. We find that, in general, nonparametric techniques with the capability of controlling for model complexity outperformed traditional regression methods, with MaxEnt and boosted regression trees still among the top performing models. All the data and code with working examples are provided to make this study fully reproducible.

Emerging infectious diseases can present serious threats to wildlife, even to the point of causing extinction. Whitenose fungus (Pseudogymnoascus destructans) is causing an epizootic in bats that is expanding rapidly, both geographically and taxonomically. Little is known of the ecology and distributional potential of this intercontinental pathogen. We address this gap via ecological niche models that characterise coarse resolution niche differences between fungus populations on different continents, identifying areas potentially vulnerable to infection in South America. Here we explore a novel approach to identifying areas of potential distribution across novel geographic regions that avoids perilious extrapolation into novel environments. European and North American fungus populations show differential use of environmental space, but rather than niche differentiation, we find that changes are best attributed to climatic differences between the two continents. Suitable areas for spread of the pathogen were identified across southern South America; however caution should be taken to avoid underestimating the potential for spread of this pathogen in South America.

Climate warming extends insect distribution areas, increases voltinism and makes pest prevention and control more difficult. The MaxEnt ecological niche modeling software was used to simulate Batocera lineolata distribution and predict potential range changes under climate change scenarios. Future B. lineolata distribution was modeled for three climate scenarios (RCP2.6, RCP4.5 and RCP8.5) to predict suitable regions in the 2050s and 2070s. A receiver operating characteristic curve was used to estimate model precision and a jackknife test was used to screen the dominant environmental variables. The results show that the area under the curve of the B. lineolata distribution model could reach an ‘Excellent’ standard. Under current climate conditions, the most suitable region for B. lineolata is 25.5–40.5°N, 102–120°E, distributed discontinuously from south to north and covering an area of 47.17 × 104 km2. For predicted future distribution, except for a decrease in moderately suitable regions under RCP2.6, RCP4.5 and RCP8.5 in the 2050s and RCP2.6 and RCP4.5 in the 2070s, other suitable regions are likely to extend; highly suitable regions would increase continuously. This research provides a theoretical basis to improve pest management strategies regarding B. lineolata to face the challenge of climate change.

Mixture distributions arise in many parametric and non-parametric settings—for example, in Gaussian mixture models and in non-parametric estimation. It is often necessary to compute the entropy of a mixture, but, in most cases, this quantity has no closed-form expression, making some form of approximation necessary. We propose a family of estimators based on a pairwise distance function between mixture components, and show that this estimator class has many attractive properties. For many distributions of interest, the proposed estimators are efficient to compute, differentiable in the mixture parameters, and become exact when the mixture components are clustered. We prove this family includes lower and upper bounds on the mixture entropy. The Chernoff α -divergence gives a lower bound when chosen as the distance function, with the Bhattacharyaa distance providing the tightest lower bound for components that are symmetric and members of a location family. The Kullback–Leibler divergence gives an upper bound when used as the distance function. We provide closed-form expressions of these bounds for mixtures of Gaussians, and discuss their applications to the estimation of mutual information. We then demonstrate that our bounds are significantly tighter than well-known existing bounds using numeric simulations. This estimator class is very useful in optimization problems involving maximization/minimization of entropy and mutual information, such as MaxEnt and rate distortion problems.

Hucks, K.D. and Leberg, P.L., 2024. Evaluation of maximum entropy models for assessing coastal bird distributions under restoration scenarios. Journal of Coastal Research, 40(5), 901–918. Charlotte (North Carolina), ISSN 0749-0208. Coastal systems are facing many challenges, including climate change, sea-level rise, storm surge, and erosion, all of which contribute to land loss. In Louisiana, this has led to the development of a coastal master plan supported by habitat suitability index (HSI) models to predict wildlife responses under various management scenarios. However, HSI models were not originally intended for this purpose, and their functionality at large spatial scales is unclear. The goal was to use maximum entropy modeling to predict how various bird distributions might change with coastal restoration and management and to compare those results to HSI model predictions. Using field surveys and sources of bird locations, as well as environmental projections from the Comprehensive Master Plan habitat and hydrology models, the authors predicted the probability of occurrence for each target species for current conditions and projected the distributions into the future at 25 and 50 years using sea-level rise and coastal change scenarios. Predictive models for each species under current conditions show good agreement with field observations. Future models generally show reductions in areas of potentially high habitat use, with a few notable exceptions in the Brown Pelican habitat. Both MaxEnt and HSI modeling approaches had advantages and disadvantages; neither was clearly superior for predicting wildlife habitat. Increasing the resolution and quality of environmental data used in coastal monitoring efforts, as well as additional field validation of model predictions, will improve estimates of suitable habitat, habitat use, and restoration outcomes for wildlife.

Aim: To synthesize the species distribution modelling (SDM) literature to inform which variables have been used in MaxEnt models for different taxa and to quantify how frequently they have been important for species' distributions. Location: Global. Methods: We conducted a quantitative synthesis analysing the contribution of over 400 distinct environmental variables to 2040 MaxEnt SDMs for nearly 1900 species representing over 300 families. Environmental variables were grouped into 24 related factors and results were analysed by examining the frequency with which variables were found to be most important, the mean contribution of each variable (at various taxonomic levels), and using TrueSkill™, a Bayesian skill rating system. Results: Precipitation, temperature, bathymetry, distance to water and habitat patch characteristics were the most important variables overall. Precipitation and temperature were analysed most frequently and one of these variables was often the most important predictor in the model (nearly 80% of models, when tested). Notably, distance to water was the most important variable in the highest proportion of models in which it was tested (42% of 225 models). For terrestrial species, precipitation, temperature and distance to water had the highest overall contributions, whereas for aquatic species, bathymetry, precipitation and temperature were most important. Main conclusions: Over all MaxEnt models published, the ability to discriminate occurrence from reference sites was high (average AUC = 0.92). Much of this discriminatory ability was due to temperature and precipitation variables. Further, variability (temperature) and extremes (minimum precipitation) were the most predictive. More generally, the most commonly tested variables were not always the most predictive, with, for instance, 'distance to water' infrequently tested, but found to be very important when it was. Thus, the results from this study summarize the MaxEnt SDM literature, and can aid in variable selection by identifying underutilized, but potentially important variables, which could be incorporated in future modelling efforts.

Aim: Species distribution modelling, a family of statistical methods that predicts species distributions from a set of occurrences and environmental predictors, is now routinely applied in many macroecological studies. However, the reliability of evaluation metrics usually employed to validate these models remains questioned. Moreover, the emergence of online databases of environmental variables with global coverage, especially climatic, has favoured the use of the same set of standard predictors. Unfortunately, the selection of variables is too rarely based on a careful examination of the species' ecology. In this context, our aim was to highlight the importance of selecting ad hoc variables in species distribution models, and to assess the ability of classical evaluation statistics to identify models with no biological realism. Innovation: First, we reviewed the current practices in the field of species distribution modelling in terms of variable selection and model evaluation. Then, we computed distribution models of 509 European species using pseudo-predictors derived from paintings or using a real set of climatic and topographic predictors. We calculated model performance based on the area under the receiver operating curve (AUC) and true skill statistics (TSS), partitioning occurrences into training and test data with different levels of spatial independence. Most models computed from pseudo-predictors were classified as good and sometimes were even better evaluated than models computed using real environmental variables. However, on average they were better discriminated when the partitioning of occurrences allowed testing for model transferability. Main conclusions: These findings confirm the crucial importance of variable selection and the inability of current evaluation metrics to assess the biological significance of distribution models. We recommend that researchers carefully select variables according to the species' ecology and evaluate models only according to their capacity to be transfered in distant areas. Nevertheless, statistics of model evaluations must still be interpreted with great caution.

Aim Accounting for sampling bias is the greatest challenge facing presence‐only and presence‐background species distribution models; no matter what type of model is chosen, using biased data will mask the true relationship between occurrences and environmental predictors. To address this issue, we review four established bias correction techniques, using empirical occurrences with known sampling effort, and virtual species with known distributions. Innovation Occurrence data come from a national recording scheme of hoverflies (Syrphidae) in Great Britain, spanning 1983–2002. Target‐group backgrounds, distance‐restricted backgrounds, travel time to cities and human population density were used to account for sampling bias in 58 species of hoverfly. Distributions generated by bias correction techniques were compared in geographical space to the distribution produced accounting for known sampling effort, using Schoener's distance, centroid shifts and range size changes. To validate our results, we performed the same comparisons using 50 randomly generated virtual species. We used sampling effort from the hoverfly recording scheme to structure our biased sampling regime, emulating complex real‐life sampling bias. Main conclusions Models made without any correction typically produced distributions that mapped sampling effort rather than the underlying habitat suitability. Target‐group backgrounds performed the best at emulating sampling effort and unbiased virtual occurrences, but also showed signs of overcompensation in places. Other methods performed better than no‐correction, but often differences were difficult to visually detect. In line with previous studies, when sampling effort is unknown, target‐group backgrounds provide a useful tool for reducing the effect of sampling bias. Models should be visually inspected for biological realism to identify any areas of potential overcompensation. Given the disparity between corrected and un‐corrected models, sampling bias constitutes a major source of error in species distribution modelling, and more research is needed to confidently address the issue.