Search Results (15,485)

While convolutional neural networks (CNNs) excel at image classification, their generalization across domains and robustness to nonlinear degradation remain challenges in art media classification (AMC). To address these challenges, this article presents a dual-stage analytical framework: first, an evaluation of seven discrete CNN architectures—ranging from VGG16 to ConvNeXt—subjected to domain shift using the New Spain (Mexico) Art Media Dataset; and second, a formal robustness analysis using an artistic corruption benchmark (Art-C). This benchmark simulates nonlinear degradations, including cracking, oxidized varnish, and pictorial abstraction. Our results demonstrate that while deep convolutional representations maintain acceptable transferability (accuracy $>70\%$), significant variability exists in architectural stability (mean 0.0607) under progressive stochastic degradation. Notably, Xception exhibited the highest robustness (Art-mCE = 0.8039), whereas VGG16 showed the greatest relative performance decay. Severity analysis further indicates that structural perturbations induce higher error rates than chromatic shifts, suggesting that CNNs are more sensitive to topological features (depth and residual connections) than color-space distributions. We provide quantitative evidence characterizing the relationship between architectural topology and empirical stability in non-natural image domains. Full article

The unchecked expansion of tea plantations onto steep, forest-adjacent slopes in subtropical mountains engenders a conflict between agricultural productivity and ecosystem integrity, particularly by exacerbating habitat fragmentation and soil erosion. While precise monitoring is essential to navigate this trade-off for sustainable management, accurate inventorying remains a challenge due to the plantations’ strong phenological variability, heterogeneous canopy structures, and high spectral confusion with surrounding vegetation. This study proposes a feature-optimized deep learning framework for mapping and characterizing tea plantations in complex landscapes, using Xinyang City, China, as a study area. The framework integrates multi-temporal Sentinel-1/2 observations with a sequential Jeffries-Matusita (JM)-Pearson feature filtering strategy. This approach effectively condenses a 132-variable high-dimensional pool (including optical spectra, vegetation indices, textures, and SAR polarimetry) into a compact 28-feature subset (a 78.8% reduction), preserving critical phenological and structural cues while minimizing redundancy. These optimized predictors drive a hybrid VGG16–UNet++ segmentation network, which couples transfer-learning-based semantic encoding with detail-preserving dense skip fusion. Extensive experiments across 18 model–feature configurations demonstrate that the optimal setting achieves an Overall Accuracy of 97.82%, an F1-score of 0.9093, and a mean IoU of 0.7968. Notably, the method significantly reduces misclassification in rugged, cloud-prone terrain, yielding a User’s Accuracy of 91.14% for tea. Based on the generated wall-to-wall map, we derived two decision-support indicators: multi-threshold steep-slope exposure and a normalized tea–forest interface density. This framework provides actionable, high-precision spatial products to support slope-based zoning, ecological restoration, and sustainable management in fragile mountain agroforestry systems. Full article

Drepanosira Bonet is a small genus of Entomobryidae mostly found in Asiatic high-elevation habitats. Drepanosira gisini Nosek was described from a mountainous region of Tajikistan, but its identity is currently delimited by generic features, especially color pattern. Here, we study the detailed morphology and systematics of the species to test the hypothesis that it belongs to Entomobryinae and is closely related to Willowsia. To test the phylogenetic placement of D. gisini, we assembled for the first time its mitogenome and used 30 more sequences of Entomobryidae species and two Orchesellidae taxa as outgroups. We performed both maximum likelihood and Bayesian inference phylogenetic analyses. Our data support that D. gisini belongs to Entomobryinae and is closely related to Willowsia species bearing scales of “the long basal rib type”. The dorsal chaetotaxy of D. gisini is remarkably complex, initially suggesting a more basal position of the species within Entomobryoidea. Even so, our phylogenetic analyses and other morphological features, like the presence of lanceolate ribbed scales, tergal sens and ms formulae, and tenaculum chaetotaxy, support the species placement among Entomobryinae in a more derived position within the subfamily phylogeny. Full article

The accessibility of flying drones (unmanned aerial vehicles) presents reproducible and cost-effective methods to monitor submerged aquatic vegetation. In particular, drone-borne topobathymetric LiDAR provides high-resolution (cm-scale), three-dimensional information about the geometry and structure of surveyed areas, allowing for quantification of vegetation volume in addition to bathymetry. For seagrasses, this information can advance research regarding the structure of canopies in relation to blue carbon storage and biodiversity. Here, we demonstrate how drone-borne LiDAR can be used to estimate the habitat volume of eelgrass (Zostera marina) within a sheltered bay in Norway. After classifying LiDAR points using a Random Forest model, we created a Digital Terrain Model of the sea floor and a Digital Surface Model of the eelgrass canopy. From these models, we showed that eelgrass canopy volume can be estimated (between 862 and 1099 m³ across the small study area) and the above-ground carbon stock in living tissue can be quantified (between 96 and 122 kg C). To our knowledge, this is the first study to utilise drone-borne LiDAR to quantify the habitat volume and carbon-storage potential of a marine habitat-forming species like eelgrass, demonstrating a novel methodology for providing reproducible and high-resolution data of submerged aquatic habitats. Full article

Responding to rapid urbanization, this study examines the trade-offs and synergies of ecosystem services (ESs) at the county scale in the Zhengzhou metropolitan area and constructs an ecological security pattern. Using the InVEST model, we quantified carbon storage (CS), soil conservation (SC), habitat quality (HQ), water yield (WY), and food production (FP). We then analyzed their trade-offs and synergies using the geographically weighted regression model, identified driving factors with an optimal parameter-based geographical detector model, detected ecosystem service bundles via a Self-organizing map model, and constructed an ecological security pattern based on circuit theory. The results showed that: (1) From 2003 to 2023, ES spatial distribution remained stable overall, with weak trade-offs and synergies. Locally, WY and HQ declined, while SC and FP increased. (2) Slope and DEM enhanced SC, whereas urban expansion consistently weakened CS, HQ, and FP. Moreover, slope played an increasingly prominent role in regulating WY. (3) Key synergistic bundles with stable spatiotemporal distribution were identified as ecological sources, leading to the construction of ecological security pattern characterized by “four districts, one corridor, and one belt.” This provides a framework for integrating ecological space protection and restoration into urban development. Full article

Global land use is changing rapidly, particularly in the tropics, where human populations have had relatively high growth rates in recent decades. This has resulted in wildlife increasingly living in or using anthropogenic environments, which often have different thermal properties in comparison to natural habitats. For example, materials used for buildings, such as concrete and brick, typically absorb, retain and radiate more heat than vegetated surfaces. The mosaic of man-made and natural areas formed when anthropogenic environments expand is therefore likely to generate microhabitats with different thermal properties. Here, we investigated the association between microhabitats and the body surface temperature of wild banded mongooses (Mungos mungo), a social mammal living in equatorial Uganda. After controlling for the significant effects of air temperature, humidity, time of day and body contact, we found that mongooses had the highest body surface temperatures when present on anthropogenic substrates, such as discarded roofing straw and refuse, while mongooses present on building materials, dead vegetation and bare soil had intermediate body surface temperatures. In contrast, mongooses had the lowest body surface temperatures when present in more natural, vegetated habitats. Although our study is relatively small scale and limited in scope, our results indicate that anthropogenic modifications to natural environments may result in hotter microhabitats, which may in turn impact space use, movement and thermoregulation in wildlife. We hope that our study encourages further research into this understudied but emerging topic. Full article

Small-scale inland fisheries in the Amazon are critical for food security, yet their sustainability is increasingly threatened by overexploitation and environmental degradation. In data-limited contexts such as the northern Ecuadorian Amazon, the absence of continuous monitoring constrains the development of adaptive management strategies. This study develops an integrated socio-ecological baseline to support the establishment of fisheries agreements in five Indigenous communities of the Napo and Aguarico rivers. Through a participatory monitoring approach, we generated reproductive parameters (gonadosomatic index, fecundity, size at first maturity), population structure metrics, and length–weight relationships for key subsistence species across three hydrological phases. Reproductive investment exhibited marked seasonality, with peak gonadosomatic indices during rising waters in most species, identifying a critical period for protection. Life-history strategies ranged from high-fecundity periodic strategists to low-fecundity equilibrium species, implying differentiated vulnerability to harvesting. Community perceptions prioritized large migratory catfish and floodplain habitats, aligning with biological indicators of vulnerability. High performance in technical training demonstrated the feasibility of long-term local monitoring systems. By linking biological indicators with local ecological knowledge, this study proposes a pathway from baseline assessment to adaptive co-management. The framework presented here provides a transferable model for strengthening sustainability, governance, and food security in tropical small-scale fisheries facing persistent data limitations. Full article

Cladocora caespitosa is an endemic hermatypic scleractinian in the Mediterranean Sea, currently threatened by both environmental and anthropogenic pressures, whereas Oculina patagonica is a cryptogenic hermatypic scleractinian that is expanding across the basin. This study provides the first assessment of co-occurring natural populations of these shallow-water taxa, examining their population structures, habitat preferences, and responses to environmental stressors based on SCUBA surveys conducted in the summers and autumns of 2022 and 2023. Both species were dominated by medium- to large-sized colonies, indicating relatively stable population structures, with C. caespitosa exhibiting significantly higher densities than O. patagonica. Both scleractinians showed a preference for sub-vertical and vertical rocky substrates, although O. patagonica appeared more tolerant of horizontal surfaces. Disease events were more frequent and severe in C. caespitosa, particularly affecting larger colonies during autumn 2022, whereas O. patagonica showed lower incidence and greater resilience overall. Temporal comparisons suggest that O. patagonica may act as a strong competitor to C. caespitosa; however, both species demonstrate a considerable capacity for recovery, likely due to adaptation to high-stress environments. These findings highlight key differences in ecological strategies and vulnerability to environmental stressors, emphasizing the need for targeted conservation approaches to preserve Mediterranean shallow-water coral communities under accelerating climate change. Full article

Urbanization threatens amphibians through habitat loss and fragmentation. The critically endangered Hynobius yangi, endemic to Korea, faces severe habitat destruction from urban development. No previous study has simultaneously assessed physicochemical habitat quality and larval feeding ecology across restored and alternative wetlands for this species using fecal DNA metabarcoding. We compared 25 H. yangi spawning sites in Sasong New Town through long-term monitoring (April 2021–September 2024; 364 surveys) and fecal DNA metabarcoding (18S V9, COI313, and blocking primers) from 60 larvae. Egg sac abundance showed negative associations with habitat area (r = −0.21), pH (r = −0.23), and conductivity (r = −0.21); however, none retained significance after Bonferroni correction, and each explained only 4–5% of variance, indicating exploratory associations. Associated conditions included area 115.5 ± 16.2 m² (mean ± SE), circularity 44.2 ± 2.4%, pH 7.55 ± 0.10, and conductivity 53.0 ± 2.7 μS/cm. Dietary analysis identified 17 prey taxa. Larvae in alternative areas showed generalist feeding favoring Perlidae and Tubificidae, while restored-area larvae showed specialist patterns dominated by Chironomidae, Nematocera, and Psychodidae. Both habitat types supported H. yangi populations. These preliminary findings suggest that appropriately designed alternative areas may complement traditional restoration, pending multi-site validation. Full article

Morphological traits, as core components of functional traits, are fundamental in determining environmental adaptability. However, under climate warming, the adaptive morphological changes and associated ecological risks of locust populations migrating to higher altitudes remain poorly understood. Here, we investigated Calliptamus italicus, the dominant locust species in the desert steppes of the Ili River Basin, to explore the response patterns of its morphological functional traits along an altitudinal gradient and their relationships with environmental factors. Morphological measurements revealed that forewing area, width, and length, as well as hindwing width, exhibited highly significant positive correlations with altitude (p < 0.01); in contrast, body length, head width, head height, pronotum length, pronotum width, hind femur length, and hind tibia length displayed significant negative correlations with altitude (p < 0.05). All morphological indicators presented highly significant sexual dimorphism (p < 0.001). Ratio analysis showed that the pronotum width-to-head width ratio (M/C), pronotum height-to-head width ratio (H/C), and forewing length-to-hind tibia length ratio (E/F) were significantly positively correlated with the altitudinal gradient (p < 0.05), with all ratios exhibiting significant sexual differences (p < 0.05). Random Forest analysis showed that PC1 (75.5% of variation) reflected traits for feeding, jumping, and reproduction, whereas PC2 (5.6%) represented flight-related traits, with significant sexual dimorphism. This study demonstrates that trait variation in C. italicus along an altitudinal gradient is closely linked to environmental factors. Our findings provide critical data for predicting habitat adaptation responses in locust populations, thereby enhancing the precision and efficacy of locust plague management and contributing to the conservation and restoration of desert steppe ecosystems. Full article

This study reconceptualises marginality in China’s inter-provincial border regions as a dynamic, scale-sensitive spatial relationship rather than a static condition of underdevelopment. Using the Hubei–Henan–Anhui border area as a case study, we quantitatively assess marginality across three dimensions—production, livelihood, and ecology—based on panel data from 61 counties for 2000, 2010, and 2021. The entropy-weighted TOPSIS method is used to calculate comprehensive development indices, and geographic detector models identify key driving factors. The results show that production marginality is persistently shaped by economic level and industrial structure. Livelihood marginality exhibits a clear temporal shift: dominant drivers move from healthcare security to cultural amenities and finally to transport accessibility. Ecological marginality remains primarily determined by natural endowments such as habitat quality and ecosystem services. Theoretically, the study advances marginality analysis by integrating spatial, temporal and dimensional perspectives. Practically, it offers a diagnostic framework to support differentiated, cross-administrative governance strategies that can transform peripheral border regions into cooperative hubs. Full article

Identifying the heterogeneous characteristics of habitat quality (HQ) trajectories is a key prerequisite for refined ecological spatial management. We used kernel Normalized Difference Vegetation Index (kNDVI) to correct the highly sensitive parameters, validated the correction results based on their consistency with the prior study findings, developed a framework for the evolution of HQ using Sen+MK and Pettitt’s tests, and utilized XGBoost and partial correlation analysis to identify the primary drivers of dynamic changes in HQ from both spatiotemporal perspectives. Our findings include the following: (1) between 2000 and 2023, the average annual rate of change in the HQ index was 0.0037 per year, indicating a continuous improvement in HQ. Compared with the period from 2011 to 2023 (0.0026 per year), the rate of improvement in HQ was faster during 2000–2011 (0.0047 per year). (2) Mutational improvement and progressive improvement were the main evolutionary trajectories, accounting for over 50.33% of the total. (3) Precipitation, land-use intensity (LUI), temperature, and elevation show a strong correlation with HQ distribution. The magnitude of HQ variation is related to HQ status, LUI, precipitation, and elevation. This study establishes a scientific foundation for developing differentiated regulatory strategies for YRB. Full article

A first study analyzed the effect of the presence of a highly frequented tourist trail on the size and reproductive capacity of Globularia alypum, a Mediterranean shrub of conservation interest. In Sardinia, this species is a typical example of a plant with Extremely Small Populations (PSESPs), restricted to a natural area embedded within an urban matrix, which makes it particularly vulnerable to ecological pressures. In this second contribution, the investigation expands to the entire population of the species distributed across different habitats. The possible correlations between vegetative and reproductive traits of the plant are examined, along with the influence exerted by both habitat type and varying levels of human disturbance. To evaluate potential drivers of its persistence, morphological (H, diameter and plant volume) and reproductive traits (number of flowers, number of fruits and number of seed per plant) were recorded at the individual level. Additionally, to assess human disturbance (consisting mainly of trampling), the presence of trails was used as a proxy and, accordingly, each plant was categorized following its relative position to the nearest path according to three categories: Near Trail (NT), Mid-Trail Distance (MTD), or Far from Trail (FT). A total of 114 individuals distributed across four habitat types were measured. Statistical analyses revealed only marginal associations between habitat type and vegetative or reproductive traits. While trail proximity did not influence flower and fruit production, plant volume tended to be greater in individuals located farther from trails, suggesting a potential, albeit limited, effect of reduced human pressure on plant growth. These findings highlight the importance of understanding subtle ecological interactions that shape the persistence of PSESPs in urban close to nature area and provide valuable insights for developing targeted conservation and management strategies. Full article

This study examines the evolution of the scientific literature on mining and heavy metals, with a particular focus on biosanitary risks associated with childhood exposure. The research integrates a systematic literature review following the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) methodology, combined with a bibliometric analysis of Scopus-indexed publications, international epidemiological data, and an evaluation of the socio-environmental context in Ecuadorian mining regions. The PRISMA-based screening process was applied to identify, filter, and select relevant peer-reviewed studies, enabling the delimitation of a focused corpus of literature, with particular attention given to scientific contributions produced by Latin American researchers and institutions. The results reveal a significant concentration of knowledge production among a limited number of countries and institutions, the dominance of English as the main language of scientific communication, and the centrality of journals in environmental sciences and toxicology. While notable progress has been made in identifying contaminants and exposure pathways, governance structures, territorial disparities, and policy implementation processes remain insufficiently explored. In Ecuador, the rapid growth of mining concessions in ecologically sensitive zones presents potential threats to children’s neurocognitive development, highlighting the urgent need for ongoing surveillance, biomonitoring programs, and preventive public health measures. The study emphasizes the importance of strengthening regional research capacity and fostering more equitable international scientific collaborations to ensure that knowledge production is responsive to local contexts and effectively safeguards vulnerable populations. Full article

The primary aim of this study is to validate the utility of Social Media Data (SMD) as a scientifically grounded tool for quantifying the spatial mismatch between objective ecological supply and subjective social demand. Assessing the spatial coupling and mismatch between Habitat Quality (HQ)—representing objective ecological supply—and Ecological Perception (EP)—representing subjective social demand—is essential for developing targeted urban management and development strategies. Focusing on the core urban area of Hangzhou, this study quantified ecological supply using the InVEST HQ model. To reflect social demand, 4958 geolocated Weibo posts were processed using contextual sentiment analysis. A Coupling Coordination Degree model served as a diagnostic tool to evaluate the synergy between these two dimensions. Additionally, a Geodetector model was employed to investigate the factors driving spatial differentiation in this coupling. The findings indicate that: (1) The regional average HQ is 0.56, reflecting a moderate overall level of degradation, while EP shows a preference for natural environments and exhibits a distinct “strip-like” spatial distribution. (2) The overall CCD value is 0.384; high-coupling areas are primarily concentrated in regions with superior natural conditions and dense vegetation, whereas low-coupling areas correspond to zones with intensive urban functions. (3) Driving factor analysis reveals that land-use type exerts the most significant influence on the overall degree of coupling. This study demonstrates that the HQ-EP coupling framework provides a reliable spatial diagnostic tool for urban planners to identify socio-ecological vulnerabilities. The results suggest that an appropriate integration of natural elements enhances coupling outcomes, with the highest synergy observed in environments characterized by high HQ and minimal anthropogenic disturbance. Full article