Using species distribution models to predict new occurrences for rare plants

Population isolation in the Plains spadefoot toad: causes and conservation implications

Range disjunctions appear to be common in nature, although they may be caused by various factors. They may simply be an artefact of inadequate sampling. If real, they may be the result of colonization events or habitat change. With natural habitats showing increasing fragmentation because of human activity, understanding the cause of a disjunction can have important conservation implications. We investigate the geographical range of the Plains spadefoot toad, Spea bombifrons, a widely distributed species in the midwestern and southwestern United States, with a putative disjunct population in southern Texas. We combine GIS mapping, species distribution modeling, and population genetic analysis to investigate this putative disjunction. We establish that this southern Texas population is truly geographically disjunct and genetically distinct. Further, using climate projections we show that this unique population is at high risk of local extinction.

Predicting the Current and Future Distribution of Monolepta signata (Coleoptera: Chrysomelidae) Based on the Maximum Entropy Model

Monolepta signata is a polyphagous and highly destructive agricultural pest, currently only distributed in Asia. In its place of origin, it poses a serious threat to important economic crops, for instance, maize (Zea mays L.) and cotton (Gossypium hirsutum L.). Based on morphological and molecular data research, it has been found that M. quadriguttata (Motschulsky), M. hieroglyphica (Motschulsky), and M. signata are actually the same species. This discovery means that the range of this pest will expand, and it also increases the risk of it spreading to non-native areas worldwide. It is crucial for global agricultural production to understand which countries and regions are susceptible to invasion by M. signata and to formulate corresponding prevention, control, and monitoring strategies. This study uses the maximum entropy model, combined with bioclimatic variables and elevation, to predict the potentially suitable areas and diffusion patterns of M. signata worldwide. The results indicate that in its suitable area, M. signata is mainly affected by three key climatic factors: Precipitation of Wettest Month (bio13), Mean Temperature of Warmest Quarter (bio10), and Temperature Seasonality (bio4). Under the current status, the total suitable region of M. signata is 252,276.71 × 104 km2. In addition to its native Asia, this pest has potentially suitable areas in Oceania, South America, North America, and Africa. In the future, with climate change, the suitable area of M. signata will expand to high-latitude areas and inland areas. This study found that by the 2070s, under the SSP5-8.5 climate scenario, the change in the potentially suitable area of this insect is the largest. By identifying the potentially suitable areas and key climatic factors of M. signata, we can provide theoretical and technical support to the government, enabling them to more effectively formulate strategies to deal with the spread, outbreak, and invasion of M. signata.

Geographical patterns and determinants of insect biodiversity in China

Insects play important roles in the maintenance of ecosystem functioning and the provision of livelihoods for millions of people. However, compared with terrestrial vertebrates and angiosperms, such as the giant panda, crested ibis, and the metasequoia, insect conservation has not attracted enough attention, and a basic understanding of the geographical biodiversity patterns for major components of insects in China is lacking. Herein, we investigated the geographical distribution of insect biodiversity across multiple dimensions (taxonomic, genetic, and phylogenetic diversity) based on the spatial distribution and molecular DNA sequencing data of insects. Our analysis included 18 orders, 360 families, 5,275 genera, and 14,115 species of insects. The results revealed that Southwestern and Southeastern China harbored higher insect biodiversity and numerous older lineages, representing a museum, whereas regions located in Northwestern China harbored lower insect biodiversity and younger lineages, serving as an evolutionary cradle. We also observed that mean annual temperature and precipitation had significantly positive effects, whereas altitude had significantly negative effects on insect biodiversity in most cases. Moreover, cultivated vegetation harbored the highest insect taxonomic and phylogenetic diversity, and needleleaf and broadleaf mixed forests harbored the highest insect genetic diversity. These results indicated that human activities may positively contribute to insect spatial diversity on a regional scale. Our study fills a knowledge gap in insect spatial diversity in China. These findings could help guide national-level conservation plans and the post-2020 biodiversity conservation framework.

Spatiotemporal variation in ecophysiological traits align with high resolution niche modelling in the short-range banded ironstone endemic Aluta quadrata

Defining plant ecophysiological responses across natural distributions enables a greater understanding of the niche that plants occupy. Much of the foundational knowledge of species' ecology and responses to environmental change across their distribution is often lacking, particularly for rare and threatened species, exacerbating management and conservation challenges. Combining high-resolution species distribution models (SDMs) with ecophysiological monitoring characterized the spatiotemporal variation in both plant traits and their interactions with their surrounding environment for the range-restricted Aluta quadrata Rye & Trudgen, and a common, co-occurring generalist, Eremophila latrobei subsp. glabra (L.S.Sm.) Chinnock., from the semi-arid Pilbara and Gascoyne region in northwest Western Australia. The plants reflected differences in gas exchange, plant health and plant water relations at sites with contrasting suitability from the SDM, with higher performance measured in the SDM-predicted high-suitability site. Seasonal differences demonstrated the highest variation across ecophysiological traits in both species, with higher performance in the austral wet season across all levels of habitat suitability. The results of this study allow us to effectively describe how plant performance in A. quadrata is distributed across the landscape in contrast to a common, widespread co-occurring species and demonstrate a level of confidence in the habitat suitability modelling derived from the SDM in predicting plant function determined through intensive ecophysiology monitoring programmes. In addition, the findings also provide a baseline approach for future conservation actions, as well as to explore the mechanisms underpinning the short-range endemism arid zone systems.

A novel hybrid model for species distribution prediction using neural networks and Grey Wolf Optimizer algorithm

Neural networks are frequently employed to model species distribution through backpropagation methods, known as backpropagation neural networks (BPNN). However, the complex structure of BPNN introduces parameter settings challenges, such as the determination of connection weights, which can affect the accuracy of model simulation. In this paper, we integrated the Grey Wolf Optimizer (GWO) algorithm, renowned for its excellent global search capacity and rapid convergence, to enhance the performance of BPNN. Then we obtained a novel hybrid algorithm, the Grey Wolf Optimizer algorithm optimized backpropagation neural networks algorithm (GNNA), designed for predicting species' potential distribution. We also compared the GNNA with four prevalent species distribution models (SDMs), namely the generalized boosting model (GBM), generalized linear model (GLM), maximum entropy (MaxEnt), and random forest (RF). These models were evaluated using three evaluation metrics: the area under the receiver operating characteristic curve, Cohen's kappa, and the true skill statistic, across 23 varied species. Additionally, we examined the predictive accuracy concerning spatial distribution. The results showed that the predictive performance of GNNA was significantly improved compared to BPNN, was significantly better than that of GLM and GBM, and was even comparable to that of MaxEnt and RF in predicting species distributions with small sample sizes. Furthermore, the GNNA demonstrates exceptional powers in forecasting the potential non-native distribution of invasive plant species.

Examining the rationality of Giant Panda National Park's zoning designations and management measures for habitat conservation: Insights from interpretable machine learning methods

Examining the rationality of zoning designations and management measures in the initial establishment of national parks in China is of great significance for supporting decision-making regarding habitat conservation. There exists a research gap in exploring the threshold effects of both environmental and human-related factors on habitat distribution in the context of national parks. However, it may be a challenge because of the limited species distribution data. Our study aims to put forward an analytical framework that integrates species distribution models (SDMs) with interpretable machine learning methods. A case study was performed in the Sichuan region of the Giant Panda National Park (GPNP). We constructed a SDM based on the Random Forest algorithm and made use of accessible remote sensing and big data to predict the distribution of giant panda habitat (GPH) in 2020. Interpretable machine learning methods, namely Partial dependence plots (PDPs) and SHapley Additive exPlanations (SHAP), were utilized to uncover the underlying mechanisms of environmental and anthropogenic variables influencing the GPH distribution. Through GIS overlay analysis, areas where conflicts between human settlements, transportation infrastructure, and GPH exist were identified. Our findings indicated a potential 28.44 % decrease in GPH from 2014 to 2020. Environmental factors such as temperature, topography, and vegetation type, as well as anthropogenic factors including distance to built-up areas and transportation infrastructure, notably distance to national roads, provincial roads and city arterial roads, influenced the GPH distribution with threshold effects significantly. The overlay analysis revealed escalated conflicts between human settlements, transportation infrastructure, and GPH in 2020 compared to 2014. Currently, the Sichuan region of the GPNP implements two zones: a core protection zone and a general control zone, covering 63.71 % of the GPH, while 36.29 % remains outside the management scope. Drawing from the analysis above, this study provided suggestions for the adjustment of zoning designations and management measures in the GPNP.

Unravelling the impact of climate change on honey bees: An ensemble modelling approach to predict shifts in habitat suitability in Queensland, Australia

Honey bees play a vital role in providing essential ecosystem services and contributing to global agriculture. However, the potential effect of climate change on honey bee distribution is still not well understood. This study aims to identify the most influential bioclimatic and environmental variables, assess their impact on honey bee distribution, and predict future distribution. An ensemble modelling approach using the biomod2 package in R was employed to develop three models: a climate-only model, an environment-only model, and a combined climate and environment model. By utilising bioclimatic data (radiation of the wettest and driest quarters and temperature seasonality) from 1990 to 2009, combined with observed honey bee presence and pseudo absence data, this model predicted suitable locations for honey bee apiaries for two future time spans: 2020-2039 and 2060-2079. The climate-only model exhibited a true skill statistic (TSS) value of 0.85, underscoring the pivotal role of radiation and temperature seasonality in shaping honey bee distribution. The environment-only model, incorporating proximity to floral resources, foliage projective cover, and elevation, demonstrated strong predictive performance, with a TSS of 0.88, emphasising the significance of environmental variables in determining habitat suitability for honey bees. The combined model had a higher TSS of 0.96, indicating that the combination of climate and environmental variables enhances the model's performance. By the 2020-2039 period, approximately 88% of highly suitable habitats for honey bees are projected to transition from their current state to become moderate (14.84%) to marginally suitable (13.46%) areas. Predictions for the 2060-2079 period reveal a concerning trend: 100% of highly suitable land transitions into moderately (0.54%), marginally (17.56%), or not suitable areas (81.9%) for honey bees. These results emphasise the critical need for targeted conservation efforts and the implementation of policies aimed at safeguarding honey bees and the vital apiary industry.

Global Trends in Climate Suitability of Bees: Ups and Downs in a Warming World

Bees represent vital natural assets contributing significantly to global food production and the maintenance of ecosystems. While studies on climate change effects impacting major pollinators like honeybees and bumblebees raise concerns about global diversity and crop productivity, comprehensive global-scale analyses remain limited. This study explores the repercussions of global warming on 1365 bees across seven families of bees worldwide. To compile a robust global bee occurrence dataset, we utilized the innovative 'BeeBDC' R package that amalgamated over 18.3 million bee occurrence records sourced from various repositories. Through species distribution models under the SSP585 scenario in the year 2070, we assessed how climate change influences the climate suitability of bees on a global scale, examining the impacts across continents. Our findings suggested that approximately 65% of bees are likely to witness a decrease in their distribution, with reductions averaging between 28% in Australia and 56% in Europe. Moreover, our analysis indicated that climate change's impact on bees is projected to be more severe in Africa and Europe, while North America is expected to witness a higher number (336) of bees expanding their distribution. Climate change's anticipated effects on bee distributions could potentially disrupt existing pollinator-plant networks, posing ecological challenges that emphasize the importance of pollinator diversity, synchrony between plants and bees, and the necessity for focused conservation efforts.

Potential Global Distribution of Paracoccus marginatus, under Climate Change Conditions, Using MaxEnt

The papaya mealybug, Paracoccus marginatus, is an invasive pest species found all over the world. It is native to Mexico and Central America, but is now present in more than 50 countries and regions, seriously threatening the economic viability of the agricultural and forestry industry. In the current study, the global potential distribution of P. marginatus was predicted under current and future climatic conditions using MaxEnt. The results of the model assessment indicated that the area under the curve of the receiver operating characteristic ( ROC-AUC) was 0.949, while the TSS value was 0.820. The results also showed that the three variables with the greatest impact on the model were min temperature of coldest month (bio6), precipitation of wettest month (bio13), and precipitation of coldest quarter (bio19), with corresponding contributions of 46.8%, 31.1%, and 13.1%, respectively. The results indicated that the highly suitable areas were mainly located in tropical and subtropical regions, including South America, southern North America, Central America, Central Africa, Australia, the Indian subcontinent, and Southeast Asia. Under four climate scenarios in the 2050s and 2070s, the area of suitability will change very little. Moreover, the results showed that the area of suitable areas in 2070s increased under all four climate scenarios compared to the current climate. In contrast, the area of suitable habitat increases from the current to the 2050s under the SSP370 and SSP585 climate scenarios. The current study could provide a reference framework for the future control and management of papaya mealybug and other invasive species.

A field-validated ensemble species distribution model of Eriogonum pelinophilum, an endangered subshrub in Colorado, USA

Understanding the suitable habitat of endangered species is crucial for agencies such as the Bureau of Land Management to plan management and conservation. However, few species distribution models are directly validated, potentially limiting their application in management. In preparation for a Species Status Assessment of clay-loving wild buckwheat (Eriogonum pelinophilum), an endangered subshrub found in southwest Colorado, we ran a series of species distribution models to estimate the species' potential occupied habitat and validated these models in the field. A 1-meter resolution digital elevation model derived from LiDAR and a high-resolution geology mapping helped identify biologically relevant characteristics of the species' habitat. We employed a weighted ensemble model based on two Random Forest and one Boosted Regression Tree model, and discrimination performance of the ensemble model was high (AUC-PR = 0.793). We then conducted a systematic field survey of model habitat suitability predictions, during which we discovered 55 new subpopulations of the species and demonstrated that new species observations were strongly associated with model predictions (p < .0001, Cliff's delta = 0.575). We further refined our original models by incorporating the additional species occurrences collected in the field survey, a new explanatory variable, and a more diverse set of models. These iterative changes marginally improved performance of the ensemble model (AUC-PR = 0.825). Direct validation of species distribution models is extremely rare, and our field survey provides strong validation of our model results. This helps increase confidence to utilize predictions in planning. The final model predictions greatly improve the Bureau of Land Management's understanding of the species' habitat and increase our ability to consider potential habitat in planning land use activities such as road development and travel management.

Potentially suitable distribution areas of Populus euphratica and Tamarix chinensis by MaxEnt and random forest model in the lower reaches of the Heihe River, China

Populus euphratica and Tamarix chinensis play a vital role in windbreak and sand fixation, maintaining species diversity and ensuring community stability. Managing and protecting the P. euphratica and T. chinensis forests in the Heihe River's lower reaches is an urgent issue to maintain the desert region's ecological balance. In this study, based on the distribution points of P. euphratica and T. chinensis species and environmental data, MaxEnt and random forest (RF) models were used to characterize the potential distribution areas of P. euphratica and T. chinensis in the lower reaches of the Heihe River. The results showed that the accuracy of the RF model was much higher than that of the MaxEnt model. Both the RF and MaxEnt models showed that the distance to the river greatly influenced the distribution of P. euphratica and T. chinensis. Furthermore, the RF model predicted significantly larger highly suitable areas for both P. euphratica and T. chinensis than the MaxEnt model. Our study enhances the understanding of the species' spatial distribution, offering valuable insights for practical management and conservation strategies.

Distribution and habitat assessments of the Slender racer, Orientocoluber spinalis, for the registration of nationally endangered species in the Republic of Korea

Conservation assessments are essential for preserving biodiversity. However, many reptile species have not been evaluated owing to data deficiencies. The Slender racer (Orientocoluber spinalis) is threatened in four out of six inhabiting countries. However, despite its apparent rarity and data deficiency, the International Union for Conservation of Nature (IUCN) has classified it as a Least Concern. In this study, we combined field surveys, habitat analysis, and ecological niche models (ENMs) to identify the critical habitat characteristics of O. spinalis, evaluate its distribution status in the Republic of Korea, and register it as a nationally endangered species. Across the country, we found a few small populations on the mainland but large populations on the islands. Orientocoluber spinalis is mainly found in low-altitude ecotone habitats between grasslands and forests. Based on previous genetic and climatic studies, we propose designating it as an endangered species to conserve this species in protected areas such as national parks, and its non-isolated mainland populations can be preserved as source populations.

Global Protected Areas as refuges for amphibians and reptiles under climate change

Protected Areas (PAs) are the cornerstone of biodiversity conservation. Here, we collated distributional data for >14,000 (~70% of) species of amphibians and reptiles (herpetofauna) to perform a global assessment of the conservation effectiveness of PAs using species distribution models. Our analyses reveal that >91% of herpetofauna species are currently distributed in PAs, and that this proportion will remain unaltered under future climate change. Indeed, loss of species' distributional ranges will be lower inside PAs than outside them. Therefore, the proportion of effectively protected species is predicted to increase. However, over 7.8% of species currently occur outside PAs, and large spatial conservation gaps remain, mainly across tropical and subtropical moist broadleaf forests, and across non-high-income countries. We also predict that more than 300 amphibian and 500 reptile species may go extinct under climate change over the course of the ongoing century. Our study highlights the importance of PAs in providing herpetofauna with refuge from climate change, and suggests ways to optimize PAs to better conserve biodiversity worldwide.

Multiscale ecological niche modeling exhibits varying climate change impacts on habitat suitability of Madrean Pine-Oak trees

Anthropogenic climate change and increasing greenhouse gas emissions are expected to globally impact the biological function, community structure, and spatial distribution of biodiversity. Many existing studies explore the effect of climate change on biodiversity, generally at a single spatial scale. This study explores the potential effects of climate change on the habitat suitability of seven tree species at two distinct spatial scales: the Coronado National Forest (CNF), a local management area, and the Sierra Madre Occidental (SMO), an ecoregional extent. Habitat suitability was determined by extrapolating Ecological Niche Models (ENMs) based on citizen-science tree occurrence records into future climatic conditions using projected 30-year normals for two anthropogenic emissions scenarios through the end of the century. These ENMs, examined at a spatial resolution of 1 km2, are constructed using a mean average ensemble of three commonly used machine learning algorithms. The results show that habitat suitability is expected to decrease for all seven tree species at varying degrees. Results also show that climate-forcing scenario choice appears to be far less important for understanding changes in species habitat suitability than the spatial scale of modeling extent. Additionally, we observed non-linear changes in tree species habitat suitability within the SMO and CNF dependent on forest community type, latitude, and elevational gradient. The paper concludes with a discussion of the necessary steps to verify the estimated alters of these tree species under climate change. Most importantly, provides a framework for characterizing habitat suitability across spatial scales.

Predicting suitable habitats of Melia azedarach L. in China using data mining

Melia azedarach L. is an important economic tree widely distributed in tropical and subtropical regions of China and some other countries. However, it is unclear how the species’ suitable habitat will respond to future climate changes. We aimed to select the most accurate one among seven data mining models to predict the current and future suitable habitats for M. azedarach in China. These models include: maximum entropy (MaxEnt), support vector machine (SVM), generalized linear model (GLM), random forest (RF), naive bayesian model (NBM), extreme gradient boosting (XGBoost), and gradient boosting machine (GBM). A total of 906 M. azedarach locations were identified, and sixteen climate predictors were used for model building. The models’ validity was assessed using three measures (Area Under the Curves (AUC), kappa, and overall accuracy (OA)). We found that the RF provided the most outstanding performance in prediction power and generalization capacity. The top climate factors affecting the species’ suitable habitats were mean coldest month temperature (MCMT), followed by the number of frost-free days (NFFD), degree-days above 18 °C (DD > 18), temperature difference between MWMT and MCMT, or continentality (TD), mean annual precipitation (MAP), and degree-days below 18 °C (DD < 18). We projected that future suitable habitat of this species would increase under both the RCP4.5 and RCP8.5 scenarios for the 2011–2040 (2020s), 2041–2070 (2050s), and 2071–2100 (2080s). Our findings are expected to assist in better understanding the impact of climate change on the species and provide scientific basis for its planting and conservation.

The Paths of the Galls: Differences in the Ecology and Distribution of Two European Oak Gall Wasps Andricus dentimitratus and Andricus pictus

Andricus dentimitratus (Rejtõ, 1887) and Andricus pictus (Hartig, 1856) are two European gall wasps (Hymenoptera, Cynipidae) that induce galls on species of Quercus. The distribution and ecological niches of these species have not been studied in detail, though they are known to have a different distribution pattern in the Iberian Peninsula in Europe. To investigate this difference and its potential relationship with climate and host species distribution, we analysed the potential distribution of both species in the Iberian Peninsula using six algorithms and a consensus model based on 600 iterations for each species. We compared the models obtained for each species with the distribution of their host Quercus species. The results show that A. dentimitratus and A. pictus have a complementary distribution delimited by the Ebro valley, with A. dentimitratus occurring northeast of the valley and A. pictus southwest. The observed distribution patterns might be due to differences in the climatic requirements of each species or to the distribution of their host species given that A. dentimitratus is specific to Q. humilis and Q. cerris (except in the northeastern Iberian Peninsula) and A. pictus, to marcescent Mediterranean oaks (Q. faginea and Q. pyrenaica) and Q. suber. We propose two hypotheses to explain the nonoverlapping distribution of the two gall wasp species in the Iberian Peninsula: in the first scenario, A. dentimitratus arrived to the to the Iberian Peninsula from the eastern Palearctic by way of Europe and A. pictus, from the north coast of Africa; in the second, their distribution is a result of their speciation in different glacial refugia: A. dentimitratus in the Italian Peninsula and A. pictus in the Iberian Peninsula.

New Distributional Records and Characterization of the Climatic Niche of Lepturges (Lepturges) limpidus Bates, 1872 (Coleoptera, Cerambycidae): Sink or Source Population?

A growing number of cases of the spread and establishment of non-native species outside their previously known ranges has been reported in recent years. Here we report new distributional records of Lepturges (Lepturges) limpidus Bates, 1872 (Cerambycidae) from Argentina and investigate whether these records could represent established populations. We constructed ellipsoid envelope models to characterize climatic niches of L. limpidus, identified areas of climatic suitability, investigated the status of new records as climatic outliers, and evaluated its dependency on its known hostplant as a limiting factor for the beetle distribution. Results indicate widespread climatic suitability in the Neotropical Region, and new records are not outliers with regard to the climatic profile of L. limpidus. Association with its known hostplant is non-dependent, indicating that the species might utilize different hosts plants. New records likely represent established populations, but targeted surveys should be carried out to detect new arrivals and enable the installation of mitigation and control measures.

Mapping edaphic soils' conditions to identify conservation targets for pine barren and sandplain ecosystems in New York State

Small habitat patches can be important reservoirs for biodiversity, capable of hosting unique species that are largely absent from the surrounding landscape. In cases where such patches owe their existence to the presence of particular soil types or hydrologic conditions, local-scale edaphic variables may be more effective components for models that identify patch location than regional-scale macroclimatic variables often used in habitat and species distribution models. We modeled the edaphic soil conditions that support pine barren, sandplain, and related ecosystems in New York State with the purpose of identifying potential locations for biodiversity conservation. We quantified soil percent sand and soil depth of 156 known high-quality remnant pine barren and sandplain ecosystems to calculate threshold soil characteristics. We then mapped all soils in the state that were at least as sandy and deep as the threshold values we calculated. The total area of our map of suitable soil conditions was over 9500 km2, made up of forested (57%), urban (26%), agricultural (13%), and open (4%) land covers. Our analysis nearly doubled the recognized area of barren, shrubland, and grassland habitat on deep, sandy soils in New York State. Extensive forested and even agricultural cover on these soils could also be the subject of restoration to further support the biodiversity of these unique ecosystems. The presence of extensive soils in coastal and interior New York that, with the appropriate disturbance regime, have the potential to host pine barren and sandplain ecosystems offers a new perspective on these ecosystems' distribution in the past-and about how to better align conservation and restoration to preserve the future.

Assessing the Effectiveness of Correlative Ecological Niche Model Temporal Projection through Floristic Data

Simple Summary

Climate change is the main threat for conservation in the 21st century. Reliable methodologies and tools for the evaluation of its impact are urgently needed. Correlative ecological niche models (ENMs) are effective tools for predicting the future distribution of species under climate change scenarios. Despite this, many alternative different methods have been proposed, and objective reasons for a proper selection are unclear. Therefore, a comparative study to evaluate the consistency of predictions of the main ENM algorithms was performed. To test the effectiveness of correlative ENM temporal projection, we compared predictions generated using historical data and projected to the modern climate with predictions generated using modern distribution and climate data. In total, 600 case studies were generated, by using 25 Italian endemic plant species, 12 algorithms and 2 alternative sets of environmental variables. As a result, we highlighted the similarity of eight algorithms and the poor performance of four.

Abstract

Correlative ecological niche modelling (ENM) is a method widely used to study the geographic distribution of species. In recent decades, it has become a leading approach for evaluating the most likely impacts of changing climate. When used to predict future distributions, ENM applications involve transferring models calibrated with modern environmental data to future conditions, usually derived from Global Climate Models (GCMs). The number of algorithms and software packages available to estimate distributions is quite high. To experimentally assess the effectiveness of correlative ENM temporal projection, we evaluated the transferability of models produced using 12 different algorithms on historical and modern data. In particular, we compared predictions generated using historical data and projected to the modern climate (simulating a “future” condition) with predictions generated using modern distribution and climate data. The models produced with the 12 ENM algorithms were evaluated in geographic (range size and coherence of predictions) and environmental space (Schoener’s D index). None of the algorithms shows an overall superior capability to correctly predict future distributions. On the contrary, a few algorithms revealed an inadequate predictive ability. Finally, we provide hints that can be used as guideline to plan further studies based on the adopted general workflow, useful for all studies involving future projections.

Assisted migration and the rare endemic plant species: the case of two endangered Mexican spruces

Background

In the projected climate change scenarios, assisted migration might play an important role in the ex situ conservation of the threatened plant species, by translocate them to similar suitable habitats outside their native distributions. However, it is unclear if such habitats will be available for the Rare Endemic Plant Species (REPS), because of their very restricted habitats. The aims of this study were to perform a population size assessment for the REPS Picea martinezii Patterson and Picea mexicana Martínez, and to evaluate the potential species distributions and their possibilities for assisted migration inside México and worldwide.

Methods

We performed demographic censuses, field surveys in search for new stands, and developed distribution models for Last Glacial Maximum (22,000 years ago), Middle Holocene (6,000 years ago), current (1961-1990) and future (2050 and 2070) periods, for the whole Mexican territory (considering climatic, soil, geologic and topographic variables) and for all global land areas (based only on climate).

Results

Our censuses showed populations of 89,266 and 39,059 individuals for P. martinezii and P. mexicana, respectively, including known populations and new stands. Projections for México indicated somewhat larger suitable areas in the past, now restricted to the known populations and new stands, where they will disappear by 2050 in a pessimistic climatic scenario, and scarce marginal areas (p = 0.5-0.79) remaining only for P. martinezii by 2070. Worldwide projections (based only on climate variables) revealed few marginal areas in 2050 only in México for P. martinezii, and several large areas (p ≥ 0.5) for P. mexicana around the world (all outside México), especially on the Himalayas in India and the Chungyang mountains in Taiwan with highly suitable (p ≥ 0.8) climate habitats in current and future (2050) conditions. However, those suitable areas are currently inhabited by other endemic spruces: Picea smithiana (Wall.) Boiss and Picea morrisonicola Hayata, respectively.

Conclusions

Assisted migration would only be an option for P. martinezii on scarce marginal sites in México, and the possibilities for P. mexicana would be continental and transcontinental translocations. This rises two possible issues for future ex situ conservation programs: the first is related to whether or not consider assisted migration to marginal sites which do not cover the main habitat requirements for the species; the second is related to which species (the local or the foreign) should be prioritized for conservation when suitable habitat is found elsewhere but is inhabited by other endemic species. This highlights the necessity to discuss new policies, guidelines and mechanisms of international cooperation to deal with the expected high species extinction rates, linked to projected climate change.

Deep Species Distribution Modeling From Sentinel-2 Image Time-Series: A Global Scale Analysis on the Orchid Family

Species distribution models (SDMs) are widely used numerical tools that rely on correlations between geolocated presences (and possibly absences) and environmental predictors to model the ecological preferences of species. Recently, SDMs exploiting deep learning and remote sensing images have emerged and have demonstrated high predictive performance. In particular, it has been shown that one of the key advantages of these models (called deep-SDMs) is their ability to capture the spatial structure of the landscape, unlike prior models. In this paper, we examine whether the temporal dimension of remote sensing images can also be exploited by deep-SDMs. Indeed, satellites such as Sentinel-2 are now providing data with a high temporal revisit, and it is likely that the resulting time-series of images contain relevant information about the seasonal variations of the environment and vegetation. To confirm this hypothesis, we built a substantial and original dataset (called DeepOrchidSeries) aimed at modeling the distribution of orchids on a global scale based on Sentinel-2 image time series. It includes around 1 million occurrences of orchids worldwide, each being paired with a 12-month-long time series of high-resolution images (640 x 640 m RGB+IR patches centered on the geolocated observations). This ambitious dataset enabled us to train several deep-SDMs based on convolutional neural networks (CNNs) whose input was extended to include the temporal dimension. To quantify the contribution of the temporal dimension, we designed a novel interpretability methodology based on temporal permutation tests, temporal sampling, and temporal averaging. We show that the predictive performance of the model is greatly increased by the seasonality information contained in the temporal series. In particular, occurrence-poor species and diversity-rich regions are the ones that benefit the most from this improvement, revealing the importance of habitat's temporal dynamics to characterize species distribution.

Small but visible: Predicting rare bryophyte distribution and richness patterns using remote sensing-based ensembles of small models

In Canadian boreal forests, bryophytes represent an essential component of biodiversity and play a significant role in ecosystem functioning. Despite their ecological importance and sensitivity to disturbances, bryophytes are overlooked in conservation strategies due to knowledge gaps on their distribution, which is known as the Wallacean shortfall. Rare species deserve priority attention in conservation as they are at a high risk of extinction. This study aims to elaborate predictive models of rare bryophyte species in Canadian boreal forests using remote sensing-derived predictors in an Ensemble of Small Models (ESMs) framework. We hypothesize that high ESMs-based prediction accuracy can be achieved for rare bryophyte species despite their low number of occurrences. We also assess if there is a spatial correspondence between rare and overall bryophyte richness patterns. The study area is located in western Quebec and covers 72,292 km2. We selected 52 bryophyte species with <30 occurrences from a presence-only database (214 species, 389 plots in total). ESMs were built from Random Forest and Maxent techniques using remote sensing-derived predictors related to topography and vegetation. Lee's L statistic was used to assess and map the spatial relationship between rare and overall bryophyte richness patterns. ESMs yielded poor to excellent prediction accuracy (AUC > 0.5) for 73% of the modeled species, with AUC values > 0.8 for 19 species, which confirmed our hypothesis. In fact, ESMs provided better predictions for the rarest bryophytes. Likewise, our study revealed a spatial concordance between rare and overall bryophyte richness patterns in different regions of the study area, which have important implications for conservation planning. This study demonstrates the potential of remote sensing for assessing and making predictions on inconspicuous and rare species across the landscape and lays the basis for the eventual inclusion of bryophytes into sustainable development planning.

Study on habitat suitability and environmental variable thresholds of rare waterbirds

The conservation level of rare waterbirds reflects the quality of the regional ecological environment and wetlands, and suitable habitat patches and good environmental conditions are bases to support the activities of rare species in habitats. Establishing these conditions is also an important goal of habitat landscape and functional restoration. However, lack of these conditions limits population protection and habitat restoration of rare species. Based on the random forest (RF) algorithm and threshold indicator taxa analysis (TITAN), this paper performed habitat suitability assessment and environmental variable threshold analysis of rare waterbird species in Yancheng coastal wetlands. The results showed that the suitable area proportion of three waterbird species at different habitat sites was less than 20%. The unsuitable area proportions of red-crowned cranes and oriental storks at the CA habitat site were the highest, reaching 86.73% and 85.17%, respectively. In addition, analysis of the importance of environmental variables showed that the main influencing variables affecting the suitable habitat distribution of the three rare waterbirds were habitat type (T_hab), habitat area (A_hab), vegetation coverage (P_fvc), distance to farmland (D_far), distance to reeds (D_ree), ponds density (Ponds), distance to water surface (D_wat) and distance to main roads or seawalls (D_swa). These variables covered the type, area, coverage and distance indicators. With the exception of D_far, Ponds and D_swa, rare waterbirds had response thresholds to each environmental indicator, and these results supported the restoration of landscape structure and function of each habitat site. This study emphasized the importance of foods, water resources and hidden conditions for habitat selection in rare waterbirds. Finally, we proposed the maintenance and restoration patterns of the landscape structure and function of rare waterbird habitats, which are available for other coastal tidal wetlands.

Continental-scale distribution and diversity of Ceratobasidium orchid mycorrhizal fungi in Australia

BACKGROUND AND AIMS

Mycorrhizal fungi are a critical component of the ecological niche of most plants and can potentially constrain their geographical range. Unlike other types of mycorrhizal fungi, the distributions of orchid mycorrhizal fungi (OMF) at large spatial scales are not well understood. Here, we investigate the distribution and diversity of Ceratobasidium OMF in orchids and soils across the Australian continent.

METHODS

We sampled 217 Ceratobasidium isolates from 111 orchid species across southern Australia and combined these with 311 Ceratobasidium sequences from GenBank. To estimate the taxonomic diversity of Ceratobasidium associating with orchids, phylogenetic analysis of the ITS sequence locus was undertaken. Sequence data from the continent-wide Australian Microbiome Initiative were used to determine the geographical range of operational taxonomic units (OTUs) detected in orchids, with the distribution and climatic correlates of the two most frequently detected OTUs modelled using MaxEnt.

KEY RESULTS

We identified 23 Ceratobasidium OTUs associating with Australian orchids, primarily from the orchid genera Pterostylis, Prasophyllum, Rhizanthella and Sarcochilus. OTUs isolated from orchids were closely related to, but distinct from, known pathogenic fungi. Data from soils and orchids revealed that ten of these OTUs occur on both east and west sides of the continent, while 13 OTUs were recorded at three locations or fewer. MaxEnt models suggested that the distributions of two widespread OTUs are correlated with temperature and soil moisture of the wettest quarter and far exceeded the distributions of their host orchid species.

CONCLUSIONS

Ceratobasidium OMF with cross-continental distributions are common in Australian soils and frequently have geographical ranges that exceed that of their host orchid species, suggesting these fungi are not limiting the distributions of their host orchids at large spatial scales. Most OTUs were distributed within southern Australia, although several OTUs had distributions extending into central and northern parts of the continent, illustrating their tolerance of an extraordinarily wide range of environmental conditions.

Potential Distribution of Amphibians with Different Habitat Characteristics in Response to Climate Change in South Korea

Simple Summary

Amphibian species are one of one of the groups most vulnerable to climate change according to the International Union for Conservation of Nature (IUCN). Limited research has been conducted investigating the effects of climate change on amphibian species in South Korea. In our study, we aimed to predict the impacts of climate change on the distribution of 16 of the 18 species of amphibians currently reported in South Korea. Altogether, 30,281 occurrence points, six bioclimatic variables, and one environmental variable (altitude) were used in modeling. Moreover, we classified 16 Korean amphibians into three groups based on their habitat characteristics: wetland amphibians (Group 1), migrating amphibians (Group 2), and forest-dwelling amphibians (Group 3). Altitude has been predicted to be a major factor in present amphibian distributions in South Korea. In general, our results show that the seven species in Group 1 should be the most resistant to climate change. The five migrating amphibians (Group 2) should decline with preferred habitat reductions. The forest-dwelling amphibian species (Group 3) are the most vulnerable to climate change and their protection requires the immediate implementation of conservation strategies. We will continue to refine our model as it evolves into a useful tool for our endeavor to preserve South Korea’s amphibians as climate change progresses.

Abstract

Amphibian species are highly vulnerable to climate change with significant species decline and extinction predicted worldwide. However, there are very limited studies on amphibians in South Korea. Here, we assessed the potential impacts of climate change on different habitat groups (wetland amphibians, Group 1; migrating amphibians, Group 2; and forest-dwelling amphibians, Group 3) under future climate change and land cover change in South Korea using a maximum entropy modelling approach. Our study revealed that all amphibians would suffer substantial loss of suitable habitats in the future, except Lithobates catesbeianus, Kaloula borealis, and Karsenia koreana. Similarly, species richness for Groups 2 and 3 will decline by 2030, 2050, and 2080. Currently, amphibian species are widely distributed across the country; however, in future, suitable habitats for amphibians would be concentrated along the Baekdudaegan Mountain Range and the southeastern region. Among the three groups, Group 3 amphibians are predicted to be the most vulnerable to climate change; therefore, immediate conservation action is needed to protect them. We expect this study could provide crucial baseline information required for the government to design climate change mitigation strategies for indigenous amphibians.

Genetic Distinctiveness but Low Diversity Characterizes Rear-Edge Thuja standishii (Gordon) Carr. (Cupressaceae) Populations in Southwest Japan

Rear-edge populations are of significant scientific interest because they can contain allelic variation not found in core-range populations. However, such populations can differ in their level of genetic diversity and divergence reflecting variation in life-history traits, demographic histories and human impacts. Using 13 EST-microsatellites, we investigated the genetic diversity and differentiation of rear-edge populations of the Japanese endemic conifer Thuja standishii (Gordon) Carr. in southwest Japan from the core-range in northeast Japan. Range-wide genetic differentiation was moderate (Fst = 0.087), with northeast populations weakly differentiated (Fst = 0.047), but harboring high genetic diversity (average population-level Ar = 4.76 and Ho = 0.59). In contrast, rear-edge populations were genetically diverged (Fst = 0.168), but contained few unique alleles with lower genetic diversity (Ar = 3.73, Ho = 0.49). The divergence between rear-edge populations exceeding levels observed in the core-range and results from ABC analysis and species distribution modelling suggest that these populations are most likely relicts of the Last Glacial Maximum. However, despite long term persistence, low effective population size, low migration between populations and genetic drift have worked to promote the genetic differentiation of southwest Japan populations of T. standishii without the accumulation of unique alleles.

Convolutional neural networks improve species distribution modelling by capturing the spatial structure of the environment

Convolutional Neural Networks (CNNs) are statistical models suited for learning complex visual patterns. In the context of Species Distribution Models (SDM) and in line with predictions of landscape ecology and island biogeography, CNN could grasp how local landscape structure affects prediction of species occurrence in SDMs. The prediction can thus reflect the signatures of entangled ecological processes. Although previous machine-learning based SDMs can learn complex influences of environmental predictors, they cannot acknowledge the influence of environmental structure in local landscapes (hence denoted "punctual models"). In this study, we applied CNNs to a large dataset of plant occurrences in France (GBIF), on a large taxonomical scale, to predict ranked relative probability of species (by joint learning) to any geographical position. We examined the way local environmental landscapes improve prediction by performing alternative CNN models deprived of information on landscape heterogeneity and structure ("ablation experiments"). We found that the landscape structure around location crucially contributed to improve predictive performance of CNN-SDMs. CNN models can classify the predicted distributions of many species, as other joint modelling approaches, but they further prove efficient in identifying the influence of local environmental landscapes. CNN can then represent signatures of spatially structured environmental drivers. The prediction gain is noticeable for rare species, which open promising perspectives for biodiversity monitoring and conservation strategies. Therefore, the approach is of both theoretical and practical interest. We discuss the way to test hypotheses on the patterns learnt by CNN, which should be essential for further interpretation of the ecological processes at play.

Prediction for Global Peste des Petits Ruminants Outbreaks Based on a Combination of Random Forest Algorithms and Meteorological Data

Peste des Petits Ruminants (PPR) is an acute and highly contagious transboundary disease caused by the PPR virus (PPRV). The virus infects goats, sheep and some wild relatives of small domestic ruminants, such as antelopes. PPR is listed by the World Organization for Animal Health as an animal disease that must be reported promptly. In this paper, PPR outbreak data combined with WorldClim database meteorological data were used to build a PPR prediction model. Using feature selection methods, eight sets of features were selected: bio3, bio10, bio15, bio18, prec7, prec8, prec12, and alt for modeling. Then different machine learning algorithms were used to build models, among which the random forest (RF) algorithm was found to have the best modeling effect. The ACC value of prediction accuracy for the model on the training set can reach 99.10%, while the ACC on the test sets was 99.10%. Therefore, RF algorithms and eight features were finally selected to build the model in order to build the online prediction system. In addition, we adopt single-factor modeling and correlation analysis of modeling variables to explore the impact of each variable on modeling results. It was found that bio18 (the warmest quarterly precipitation), prec7 (the precipitation in July), and prec8 (the precipitation in August) contributed significantly to the model, and the outbreak of the epidemic may have an important relationship with precipitation. Eventually, we used the final qualitative prediction model to establish a global online prediction system for the PPR epidemic.

Tapping Diversity From the Wild: From Sampling to Implementation

The diversity observed among crop wild relatives (CWRs) and their ability to flourish in unfavorable and harsh environments have drawn the attention of plant scientists and breeders for many decades. However, it is also recognized that the benefit gained from using CWRs in breeding is a potential rose between thorns of detrimental genetic variation that is linked to the trait of interest. Despite the increased interest in CWRs, little attention was given so far to the statistical, analytical, and technical considerations that should guide the sampling design, the germplasm characterization, and later its implementation in breeding. Here, we review the entire process of sampling and identifying beneficial genetic variation in CWRs and the challenge of using it in breeding. The ability to detect beneficial genetic variation in CWRs is strongly affected by the sampling design which should be adjusted to the spatial and temporal variation of the target species, the trait of interest, and the analytical approach used. Moreover, linkage disequilibrium is a key factor that constrains the resolution of searching for beneficial alleles along the genome, and later, the ability to deplete linked deleterious genetic variation as a consequence of genetic drag. We also discuss how technological advances in genomics, phenomics, biotechnology, and data science can improve the ability to identify beneficial genetic variation in CWRs and to exploit it in strive for higher-yielding and sustainable crops.

The Relict Ecosystem of Maytenus senegalensis subsp. europaea in an Agricultural Landscape: Past, Present and Future Scenarios

Maytenus senegalensis subsp. europaea is a shrub belonging to the Celastraceae family, whose only European populations are distributed discontinuously along the south-eastern coast of the Iberian Peninsula, forming plant communities with great ecological value, unique in Europe. As it is an endangered species that makes up plant communities with great palaeoecological significance, the development of species distribution models is of major interest under different climatic scenarios, past, present and future, based on the fact that the climate could play a relevant role in the distribution of this species, as well as in the conformation of the communities in which it is integrated. Palaeoecological models were generated for the Maximum Interglacial, Last Maximum Glacial and Middle Holocene periods. The results obtained showed that the widest distribution of this species, and the maximum suitability of its habitat, occurred during the Last Glacial Maximum, when the temperatures of the peninsular southeast were not as contrasting as those of the rest of the European continent and were favored by higher rainfall. Under these conditions, large territories could act as shelters during the glacial period, a hypothesis reflected in the model’s results for this period, which exhibit a further expansion of M. europaea’s ecological niche. The future projection of models in around 2070, for four Representative Concentration Pathways according to the fifth report of the Intergovernmental Panel on Climate Change, showed that the most favorable areas for this species would be Campo de Dalías (southern portion of Almería province) as it presents the bioclimatic characteristics of greater adjustment to M. europaea’s ecological niche model. Currently, some of the largest specimens of the species survive in the agricultural landscapes in the southern Spain. These areas are almost totally destroyed and heavily altered by intensive agriculture greenhouses, also causing a severe fragmentation of the habitat, which implies a prospective extinction scenario in the near future.

Ensemble Random Forests as a tool for modeling rare occurrences

Relative to target species, priority conservation species occur rarely in fishery interactions, resulting in imbalanced, overdispersed data. We present Ensemble Random Forests (ERFs) as an intuitive extension of the Random Forest algorithm to handle rare event bias. Each Random Forest receives individual stratified randomly sampled training/test sets, then down-samples the majority class for each decision tree. Results are averaged across Random Forests to generate an ensemble prediction. Through simulation, we show that ERFs outperform Random Forest with and without down-sampling, as well as with the synthetic minority over-sampling technique, for highly class imbalanced to balanced datasets. Spatial covariance greatly impacts ERFs’ perceived performance, as shown through simulation and case studies. In case studies from the Hawaii deep-set longline fishery, giant manta ray Mobula birostris syn. Manta birostris and scalloped hammerhead Sphyrna lewini presence had high spatial covariance and high model test performance, while false killer whale Pseudorca crassidens had low spatial covariance and low model test performance. Overall, we find ERFs have 4 advantages: (1) reduced successive partitioning effects; (2) prediction uncertainty propagation; (3) better accounting for interacting covariates through balancing; and (4) minimization of false positives, as the majority of Random Forests within the ensemble vote correctly. As ERFs can readily mitigate rare event bias without requiring large presence sample sizes or imparting considerable balancing bias, they are likely to be a valuable tool in bycatch and species distribution modeling, as well as spatial conservation planning, especially for protected species where presence can be rare.

Toward reliable habitat suitability and accessibility models in an era of multiple environmental stressors

Global biodiversity declines, largely driven by climate and land-use changes, urge the development of transparent guidelines for effective conservation strategies. Species distribution modeling (SDM) is a widely used approach for predicting potential shifts in species distributions, which can in turn support ecological conservation where environmental change is expected to impact population and community dynamics. Improvements in SDM accuracy through incorporating intra- and interspecific processes have boosted the SDM field forward, but simultaneously urge harmonizing the vast array of SDM approaches into an overarching, widely adoptable, and scientifically justified SDM framework. In this review, we first discuss how climate warming and land-use change interact to govern population dynamics and species' distributions, depending on species' dispersal and evolutionary abilities. We particularly emphasize that both land-use and climate change can reduce the accessibility to suitable habitat for many species, rendering the ability of species to colonize new habitat and to exchange genetic variation a crucial yet poorly implemented component of SDM. We then unite existing methodological SDM practices that aim to increase model accuracy through accounting for multiple global change stressors, dispersal, or evolution, while shifting our focus to model feasibility. We finally propose a roadmap harmonizing model accuracy and feasibility, applicable to both common and rare species, particularly those with poor dispersal abilities. This roadmap (a) paves the way for an overarching SDM framework allowing comparison and synthesis of different SDM studies and (b) could advance SDM to a level that allows systematic integration of SDM outcomes into effective conservation plans.