Machine learning algorithms for the evaluation of risk by tick-borne pathogens in Europe.

BACKGROUND: Tick-borne pathogens pose a major threat to human health worldwide. Understanding the epidemiology of tick-borne diseases to reduce their impact on human health requires models covering large geographic areas and considering both the abiotic traits that affect tick presence, as well as the vertebrates used as hosts, vegetation, and land use. Herein, we integrated the public information available for Europe regarding the variables that may affect habitat suitability for ticks and hosts and tested five machine learning algorithms (MLA) for predicting the distribution of four prominent tick species across Europe. MATERIALS AND METHODS: A grid of cells 20 km in diameter was prepared to cover the entire territory, containing data on vegetation, points of water, habitat fragmentation, forest density, grass extension, or imperviousness, with information on temperature and water deficit. The distribution of the hosts (162 species) was modelled and included in the dataset. We used five MLA, namely, Random Forest, Neural Networks, Naive Bayes, Gradient Boosting, and AdaBoost, trained with reliable coordinates for Ixodes ricinus, Dermacentor reticulatus, Dermacentor marginatus, and Hyalomma marginatum in Europe. RESULTS: Both Random Forest and Gradient Boosting best predicted ticks and host environmental niches. Our results demonstrate that MLA can identify trait-matching combinations of environmental niches. The inclusion of land cover and land use variables has a superior capacity for predicting areas suitable for ticks, compared to classic methods based on the use of climate data alone. CONCLUSIONS: Flexible MLA-driven models may offer several advantages over traditional models. We anticipate that these results may be extrapolated to other regions and combinations of tick-vertebrates. These results highlight the potential of MLA for inference in ecology and provide a background for the evolution of a completely automatized tool to calculate the seasonality of ticks for early warning systems aimed at preventing tick-borne diseases.

The benefits and disbenefits associated with cultural ecosystem services of urban green spaces.

Cultural ecosystem services (CES) and disservices shape landscape planning policy to a huge extent. We focus on the benefits and disbenefits associated with CES. The study aimed to explore the co-occurrence of the benefits and disbenefits associated with CES as well as the relationship between spatial and landscape characteristics and specific benefits and disbenefits. We conducted a map-based online questionnaire among visitors of two urban green spaces in Kraków, Poland (Wolski Forest and Jordan Park). Respondents were asked to map places visited and assign them benefits and disbenefits using indicator statements. We found three bundles of benefits (connection to nature, social bonding in nature and responsibility) and five to seven bundles of disbenefits (1). The experiences (e.g., strengthening social bonds) were more concentrated whereas the identities (e.g., reflection) were more blurred spatially owing to their individualistic nature (2). The relationship between benefits/disbenefits and landscape features showed a relatively weak correlation, with a more discernible pattern observed in the case of experiences and capabilities (3). Respondents perceived more human-related disbenefits (overcrowding, noise, rubbish), exhibiting a greater geographical concentration, especially in proximity to tourist attractions (4). The ecosystem-related disbenefits (insects, allergies) were less geographically concentrated (5). Furthermore, the study unveiled differences in the perception of disbenefits across seasons. Visitors of warmer months expressed concerns about overcrowding, insects, and allergies, while those exploring the study areas in winter indicated challenges associated with darkness and snow-covered paths (6). These are important implications for management to increase the comfort of visits to green spaces.

Habitat-specific conservation priorities of multidimensional diversity patterns of amphibians in China effectively contribute to the '3030' target.

Amphibia is the most threatened animal group among all land vertebrates in the context of anthropogenic global change. Filling the conservation gaps for this taxonomic group could help achieve the ambitious target of covering 30 % of the land by 2030 ('3030' target) set by the 15-th meeting of the Conference of the Parties (COP15). In this study, we compiled the most up-to-date occurrence records and corresponding species-specific traits and phylogenies of amphibians in China (particularly those newly described in the past decade) to explore the spatial distribution patterns of multidimensional diversity (including taxonomic, functional, and phylogenetic) for different species groups (including all, endemic and threatened). Additionally, a new conservation gap index (CGI) was proposed and applied to the analysis of multi-objective conservation strategies. The results showed that the spatial distribution of taxonomic, functional and phylogenetic diversity of amphibians in China is markedly geographically diverse, with common hotspots for all three concentrated in the humid mountainous regions of southern China. The CGI, which is independent of arbitrary threshold selection and grid cell size, showed that the conservation gap for amphibians in China is largest in biomes such as tropical and subtropical moist broadleaf forests and temperate broadleaf and mixed forests. The multi-objective conservation analysis revealed that the Yangtze River basin, Pearl River basin and Southeast Basin in China have pivotal roles in achieving the '3030' target due to their high taxonomic, phylogenetic and functional diversity, relatively high proportion of threatened and endemic species, and low coverage of existing nature reserves. Notably, sustainable management of less-protected habitats, including farmlands and grasslands, can reduce the area requirement of strict protection for reaching the '3030' conservation goal. This study provides practical strategies for guiding amphibian conservation by systematically integrating multidimensional biodiversity information, habitat features and the spatial distributions of the existing natural reserves.

Effects of Environmental Factors on Bird Communities in Different Urbanization Grades: An Empirical Study in Lishui, a Mountainous Area of Eastern China.

The rapid development of urbanization has changed landscape patterns and biological habitats severely and, therefore, affected biodiversity. In this study, we selected 75 townships in Lishui, a mountainous area in eastern China, to conduct bird surveys for two years. We analyzed the birds' composition characters in townships with different levels of development in order to identify the effects on bird diversity of the urban development level, land cover pattern, landscape pattern, and other factors. In total, 296 bird species from 18 orders and 67 families were recorded between December 2019 and January 2021. A total of 166 species of birds belonged to Passeriformes (56.08%). The seventy-five townships were divided into three grades by K-means cluster analysis. The average number of bird species, richness index, and diversity index were higher in G-H (highest urban development level) compared with the other grades. At the township level, landscape diversity and landscape fragmentation were the key factors that positively affected the bird species number, diversity index, and richness index. Landscape diversity had a greater effect than landscape fragmentation, particularly on the Shannon-Weiner diversity index. The diversity and heterogeneity of urban landscapes could be improved by constructing biological habitats in future urban development planning to maintain and increase biodiversity. The results obtained in this study provide a theoretical basis for urban planning in mountainous areas, and a reference for policymakers to formulate biodiversity conservation strategies, construct reasonable biodiversity patterns, and solve practical biodiversity conservation problems.

Using buffer analysis to determine urban park cooling intensity: Five estimation methods for Nanjing, China.

Urban parks are part of the blue-green infrastructure of urban ecosystems. Although the cooling effect of urban parks has been widely recognized, the understanding of park cooling intensity (PCI) and its mechanisms remains incomplete. Applicable and accurate quantification could facilitate better design and management of urban parks. We used five methods (equal area method [EAM], equal radius method [ERM], fixed radius method [FRM], turning point method-maximum perspective [TPM-M], and turning point method-accumulation perspective [TPM-A]) to estimate PCI, and established the method selection mechanism, which we evaluated in terms of PCI amplitudes, spatial heterogeneity, and interactions with park landscape features. Using Nanjing as a case study, we employed spatial and statistical analyses to further assess the autocorrelation of PCI and its relationship with park landscape features. The results indicate the following: (1) 62.38 % of Nanjing's urban parks are located above the 90 % confidence level in cold spot areas. (2) Different methods had significant effects on the estimated PCI, were positively correlated, and had similar spatial heterogeneity. (3) All methods revealed that park area (PA), water area proportion (WAP), and the normalized difference vegetation index (NDVI) of the vegetated area (NDVIveg) were the three dominant factors that influenced PCI; WAP and NDVIveg that achieved more effective cooling. (4) The quantification of PCI using the ERM and TPM is recommended over other methods. These findings are essential for landscape planners to understand the formation of PCI and design cooler parks to mitigate the urban heat island (UHI) effect more systematically.

Robust spatial estimates of biomass carbon on farms.

The drive for farm businesses to move towards net zero greenhouse gas emissions means that there is a need to develop robust methods to quantify the amount of biomass carbon (C) on farms. Direct measurements can be destructive and time-consuming and some prediction methods provide no assessment of uncertainty. This study describes the development, validation, and use of an integrated spatial approach, including the use of lidar data, and Bayesian Belief Networks (BBNs) to quantify total biomass carbon stocks (Ctotal) of i) land cover and ii) landscape features such as hedges and lone trees for five case study sites in lowland England. The results demonstrated that it was possible to develop and use a remote integrated approach to estimate biomass carbon at a farm scale. The highest achievable prediction accuracy was attained from models using the variables AGBC, BGBC, DOMC, age, height, species and land cover, derived from measured information and from literature review. The two BBN models successfully predicted the test values of the total biomass carbon with propagated error rates of 6.7 % and 4.3 % for the land cover and landscape features respectively. These error rates were lower than in other studies indicating that the seven predictors are strong determinants of biomass carbon. The lidar data also enabled the spatial presentation and calculation of the variable C stocks along the length of hedges and within woodlands.

What drives bat activity at field boundaries?

Field boundaries are important habitat for bats in agricultural landscapes, serving as commuting and foraging areas for many species. The goal of our study was to better understand the drivers of bat activity in agricultural landscapes to inform conservation policy and make specific recommendations for habitat management. We placed sixty-four full spectrum bat detectors at random recording locations, weekly, along field boundaries in North Somerset between July and October 2020. We used an automated classifier to analyse recordings and performed error rate modelling to account for and remove the majority of error in automated classifications. We used generalised additive models to explore bat response to recording location metrics, controlling for spatial-autocorrelation and temporal differences in sampling. We validated our models with k-fold cross-validation and explored the utility of our models for predicting bat activity at new sites. We found that field boundary characteristics better describe bat activity than adjacent field characteristics or measures of local landscape for the majority of species studied. Bat activity was higher along tall, wide, vegetated field boundaries containing trees; there was lower activity at arable recording locations. Still, bat activity was highly variable and predictive error was high. We found a large spatial effect driving activity patterns, meaning models are not able to predict activity beyond the extent of the study area. We recommend management strategies that give incentives to farmers for replacing fences with hedgerows, planting hedgerow trees, and maintaining tall and outgrown field boundaries.

Bees in the six: Determinants of bumblebee habitat quality in urban landscapes.

With growing urbanization, it is becoming increasingly important to design cities in a manner that sustains and enhances biodiversity and ecosystem services. Native bees are critical pollinators that have experienced substantive declines over the past several decades. These declines have captured the attention of the public, particularly urbanites, prompting a large interest in protecting pollinators and their habitats in cities across North America and Europe. Unfortunately, we currently lack research about specific features of urban environments that can enhance the fitness of pollinators. We carried out an intensive study of Bombus impatiens, the Common Eastern Bumblebee, in the city of Toronto (Canada's largest city), to better understand landscape parameters that provide high-quality habitat for this species and likely other generalist bees. We divided the city into 270 grid cells and sampled a large number of worker bees, which were then genotyped at twelve hypervariable microsatellite loci. The genetic data allowed us to quantify the effective number of colonies and foraging distance for bumblebees in our study area. We then asked how the city's landscape and human population demography and income are associated with the availability of high-quality habitat for B. impatiens. Several aspects of Toronto's landscape influenced colony density and foraging range. Urbanization had a clear effect on both colony density and foraging distance of workers. On the other hand, functional (i.e., not cosmetic) green space was often associated with higher quality habitats for bumblebees. Our study suggests several planning strategies to enhance habitat quality for bumblebees and other pollinators in cities.

Factors influencing the habitat use by ocelots in one of the last large Atlantic Forest remnants in southeastern Brazil.

Ocelots (Leopardus pardalis) are widely distributed throughout the Americas, being dependent on forested areas to survive. Although ocelot ecology is broadly studied throughout the species range distribution, studies concerning factors that may affect ocelot occupancy in the Atlantic Forest are still scarce. We used camera traps to evaluate factors influencing the probabilities of detection and occupancy of ocelots in a protected area of the Atlantic Forest, the Rio Doce State Park (RDSP), southeastern Brazil. To assess ocelot occupancy and detection probabilities, we measured the distances between sampling stations and rivers, lakes, cities, pasture, and Eucalyptus plantations. In addition, we recorded the mean rainfall levels for each sampling occasion, and native grassland areas within a 500 m-buffer around each sampling station. We found a strong and positive association between ocelot detection and the dry season, which might be due to a higher number of individuals moving through the Park during this season. Moreover, we found a strong and positive association of ocelot detection with native grassland areas around lakes, which may be related to the ocelot behavior of searching for prey in these areas. Conversely, the ocelot occupancy probability was intermediate ( Ψ ^  = 0.53, 95% CI = 0.36-0.69) and was not strongly associated with the evaluated covariates, which may be explained by the high-quality of forest habitats and water resources that are homogeneously distributed within the Park. Our study indicates that the RDSP still provides a structurally suitable forest habitat for ocelots, but because of the current worrying scenario of over fragmentation, reduction of forest cover, and weakness of the protective legislation of this biome, the long-term persistence of the species in RDSP is uncertain.

Small things are important: the value of singular point elements for birds in agricultural landscapes.

Farmland birds belong to the most endangered group of vertebrates in Europe. They are an important component of farmland biodiversity considering the numerous functions they perform (e.g. seed dispersal, improving germination, increasing gene flow, nutrient recycling, and pest control). Therefore, their decline imposes substantial risks on agricultural ecosystems. In general, farmland bird conservation includes land-use and management alterations leading to less-intensive farming and land-sparing for breeding habitats (e.g. agri-environment-climate schemes, and organic farming). However, theoretical concepts describing farmland biodiversity maintenance and applied conservation measures usually ignore the role of singular, often very small, natural or man-made elements in an agricultural landscape. These elements play a role in the populations of certain species, their biology and in the general species richness of farmland. Furthermore, the importance of these elements has never been empirically tested, which means that conservationists and practitioners are not aware of their measurable value for birds. Herein, we define and identify singular point elements in the agricultural landscape (SPELs) which are potentially important for breeding farmland birds. We also describe each SPEL and evaluate its importance for birds in farmland based on a systematic review of the available literature. Using a horizon-scanning technique, we then polled field ornithologists about their personal observations of birds in relation to SPELs and the evaluation of the potential roles of such structures for birds. We identified 17 SPELs that vary in naturalness and age: singular trees, singular shrubs, erratic boulders, puddles, electricity pylons, wind turbines, spiritual sites, hunting platforms, fence and border posts, wells, road signs, scarecrows, piles of manure, piles of brushwood/branches, piles of stones/debris, piles of lime, and haystacks. Analysis of the literature revealed knowledge gaps, because some SPELs are frequently mentioned in ecological studies (e.g. trees, shrubs, pylons), but others such as spiritual sites, stones, hunting platforms, wells, road signs, or piles of lime are ignored. Despite the fact that some authors incorporate the effects of some SPELs in their studies, little research to date has aimed to assess the impact of various SPELs on farmland bird species numbers and distribution. Horizon scanning revealed that ornithologists often observe birds on various SPELs and thus, attribute to SPELs many functions that are important for maintaining bird populations. Horizon scanning also highlighted the importance of SPELs for many declining bird species and suggested possible mitigation of negative changes in the agricultural landscape by retaining SPELs within fields. We suggest that a better understanding of the role of SPELs for farmland birds is required. We also recommend that SPELs are considered as a potential tool for the conservation of birds, and existing conservation programs such as agri-environment-climate schemes and organic farming should be updated accordingly. Finally, we suggest that SPELs are included in predictive models that evaluate habitat suitability for farmland biodiversity.