Search Results (195)

Erosion in intensively farmed landscapes threatens above- and below-ground biodiversity. While impacts on soil physical and chemical properties (which affect soil inhabiting biota) are well documented, effects on ground-associated fauna (distribution, diversity, abundance) remain less understood. A likely very strong factor is the direct transport of epigeon together with the eroded soil. We assessed how water-erosion processes shape communities of epigeic invertebrates along agricultural slopes in the Chernozem region of South Moravia (Czech Republic). Ground-dwelling invertebrates were sampled over five years (May–September) in conventionally managed maize fields using pitfall traps across 18 sloping fields. Three slope positions were compared per field (control, erosional, depositional; 54 positions in total). Community patterns were evaluated using Canonical Correspondence Analysis with covariates (month, year, slope position, site), and species responses to key drivers were analysed using Generalised Additive Models. Across the full dataset, Shannon diversity and species richness did not differ significantly among slope positions; however, total invertebrate abundance was significantly lower in erosional parts. Interannual variation was pronounced and linked to precipitation: wet conditions increased diversity and richness at depositional positions, whereas dry conditions reduced diversity downslope. Ordination and GAM results identified erosion intensity and relative precipitation/temperature anomalies as important predictors, with most dominant species showing higher abundances under low to moderate erosion. These findings indicate that epigeic invertebrate communities along slopes can serve as indicators of erosion force. Full article

Neltuma juliflora (Sw.) Raf. (syn. = Prosopis juliflora (Sw.) DC.) is among the world’s most aggressive woody invaders, yet its ecological impacts remain poorly quantified in hyper-arid environments, where soils are calcareous and ecosystems recover slowly from disturbance. In this study, we tested two hypotheses: (1) the presence of N. juliflora changes native plant diversity, as well as soil and key physicochemical properties in hyper-arid Qatar, and (2) agricultural farms act as primary sources of N. juliflora invasion. Using a comparative observational design across 62 sites (45 invaded and 17 non-invaded), we applied a generalised additive model (GAM) and a generalised linear mixed model (GLMM) to quantify invasion drivers and the impact of invasion on perennial species diversity, respectively. Additionally, we used the Wilcoxon rank-sum test to compare the soil properties in the invaded and non-invaded sites. Our results indicate that N. juliflora is positively associated with farms, with the probability of occurrence declining by ca. 20% for each kilometre farther away from agricultural farms. This pattern suggests substantial propagule pressure from agricultural farms. Perennial species richness declined from 7.5 species at 0% N. juliflora cover to 4.8 species at full cover (36% reduction). Invaded sites were characterised by higher amounts of coarse sand (16%); reduced silt–clay fractions (5%); and elevated salinity indicators, including electrical conductivity (0.744 dS m⁻¹) and total dissolved solids (476 mg L⁻¹), while major N–P–K pools remained unchanged. These findings demonstrate measurable invasion-related changes in soil conditions and native perennial diversity in hyper-arid ecosystems and highlight the role of agricultural land use as a key driver of biological invasion. From a sustainability perspective, early detection, targeted control near agricultural and grazing zones, and integration of invasive species monitoring into land-use planning frameworks are essential to prevent further ecosystem degradation, protect biodiversity, and enhance the resilience of desert landscapes under increasing climate and land-use pressures. Full article

Accurate and early prediction of crop yield at the sub-field scale is essential for precision-agriculture and food-system planning. This study evaluates a phenology-based machine learning framework for winter wheat yield prediction using Sentinel-2 satellite imagery, climate reanalysis data, and field-level yield data. Phenological metrics derived from the normalised difference vegetation index (NDVI), the normalised difference water index (NDWI), and the normalised difference red-edge index (NDRE) were combined with accumulated seasonal rainfall and seasonal potential evapotranspiration, and multiple modelling strategies were assessed using a leave-one-field-out cross-validation (LOFO CV) scheme to ensure spatial generalisation. Among the evaluated models, the Random Forest (RF) algorithm achieved the highest overall performance, explaining up to 73% of the yield variability with a root mean square error (RMSE) of 0.88 t ha⁻¹ at optimal prediction timing (day of year 160–175). Integrating phenological and climatic covariates consistently improved prediction accuracy compared to models based only on phenological variables, while the inclusion of soil properties provided limited additional benefit at the examined spatial scale. Phenological metrics based on red-edge data, particularly the maximum NDRE, were the most influential predictors, highlighting the added value of red-edge spectral information beyond traditional red–near-infrared indices. Uncertainty analysis revealed spatially heterogeneous prediction uncertainty, particularly near field boundaries and in areas of complex spatial patterns. Overall, the proposed framework enables robust, early, and interpretable yield prediction at the sub-field scale, supporting uncertainty-aware decision-making in precision agriculture and offering a scalable foundation for regional crop monitoring. Full article

Hospital readmission within 30 days remains a significant challenge in oncology practice, contributing to higher healthcare costs, treatment delays, and poorer patient outcomes. Existing predictive models for breast cancer readmission are often limited by inadequate interpretability and generalisability. This study develops and evaluates an explainable machine learning (ML) framework to predict 30-day hospital readmissions among breast cancer patients, with specific emphasis on methodological transparency and avoidance of information leakage. A retrospective dataset including demographic, clinical, and treatment-related variables such as age, comorbidity burden, ECOG performance status, baseline neutrophil count, and dosage adjustments was analysed. Multiple ML classifiers were evaluated—including Logistic Regression, Support Vector Machine, Naïve Bayes, K-Nearest Neighbours, Decision Tree, Random Forest, and XGBoost—using repeated stratified cross-validation (5 × 10 folds). Class imbalance was addressed using SMOTE applied strictly within the training folds to prevent data leakage. Out-of-fold performance metrics included ROC-AUC, PR-AUC, calibration curves, and Brier scores. Random Forest demonstrated the strongest discrimination specificity of 0.57 ± 0.33, the highest among all models, and a superior ROC-AUC of 0.68 ± 0.17, which was appropriate for the small, imbalanced dataset. For interpretability, each model was refit on the full dataset and analysed using Shapley Additive Explanations (SHAP), Partial Dependence Plots (PDP), and LIME. Comorbidity burden and ECOG performance status consistently emerged as the most influential predictors across all explainability techniques, aligning with established clinical evidence. The findings highlight the feasibility of applying explainable ML methods to small, imbalanced oncology datasets and demonstrate their potential to support early clinical risk identification in breast cancer care. Full article

High-risk Artificial Intelligence (AI) systems deployed in cybersecurity and privacy-critical contexts must satisfy not only demanding performance targets but also stringent obligations for transparency, accountability, and human oversight under the General Data Protection Regulation (GDPR) and the Artificial Intelligence Act (AI Act). Existing approaches often treat these concerns in isolation as follows: Explainable Artificial Intelligence (XAI) methods are added ad hoc to machine learning pipelines, while governance and regulatory frameworks remain largely conceptual and weakly connected to the concrete artefacts produced in practice. This article proposes XAI-Compliance-by-Design, a modular framework that integrates XAI techniques, compliance-by-design principles and trustworthy Machine Learning Operations (MLOps) practices into a unified architecture for high-risk AI systems in cybersecurity and privacy domains. The framework follows a dual-flow design that couples an upstream technical pipeline (data, model, explanation, and monitoring) with a downstream governance pipeline (policy, oversight, audit, and decision-making), orchestrated by a Compliance-by-Design Engine and a technical–regulatory correspondence matrix aligned with the GDPR, the AI Act, and ISO/IEC 42001. The framework is instantiated and evaluated through an end-to-end, Python-based proof of concept using a synthetic, intrusion detection system (IDS)-inspired anomaly detection scenario with a Random Forest (RF) classifier, Shapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME), drift indicators, and tamper-evident evidence bundles and decision dossiers. The results show that, even in a modest, toy setting, the framework systematically produces verifiable artefacts that support auditability and accountability across the model lifecycle. By linking explanation reports, drift statistics and compliance logs to concrete regulatory provisions, the approach illustrates how organisations operating high-risk AI for cybersecurity and privacy can move from model-centric optimisation to evidence-centric governance. The article discusses how the proposed framework can be generalised to real-world high-risk AI applications, contributing to the operationalisation of European digital sovereignty in AI governance. This article does not introduce a new intrusion detection algorithm; instead, it proposes an evidence-centric governance pipeline that captures decision provenance and compliance artefacts so that decisions can be audited and justified against regulatory obligations. Full article

Microclimate and built environment jointly influence outdoor activities among the elderly. However, existing studies largely focus on a single season or environmental factor, lacking a comprehensive analysis of seasonal variation and multi-factor coupling effects. This paper investigates the seasonal interaction effects of microclimate and built environment on elderly outdoor activities, with implications for elderly-friendly urban design. Using a typical residential neighbourhood in Xi’an as a case, we constructed a multi-source spatio-temporal dataset through high-density microclimate monitoring in winter and summer, fine-grained POI mapping, and computer-vision-based behavioural annotation. Generalised Additive Models (GAM) and SHAP analysis were employed for modelling and mechanism exploration. The results show that: (1) Elderly activity patterns exhibit a fundamental seasonal reversal—characterised as “sun-seeking and wind-avoiding” in winter and “shade-seeking and wind-pursuing” in summer; (2) Environmental factors exhibit marked nonlinear and threshold-dependent influences that vary by season; (3) Microclimate and built environment elements demonstrate synergistic interaction effects, especially pronounced in summer. Quantitatively, GAM and SHAP analyses indicate that the “effective service radius” of Elderly-Friendly POIs (defined as the threshold where positive influence approaches zero) contracted from approximately 45–50 m in winter to 35–40 m in summer, while their peak promotional effect occurred at 20–25 m. Positive POIs exhibited a significantly shorter influence range, and Negative POIs demonstrated negligible distance-dependent effects. This study confirms a “seasonal dynamic interaction” mechanism and proposes the adaptive design strategy of “sunlight and wind-shelter pockets—shade and ventilation corridors,” offering empirical and methodological support for climate-responsive elderly-friendly community planning. Full article

The common dolphin (Delphinus delphis) is one of the most abundant small cetaceans along the Galician coast and a definitive host for the nematode parasite Anisakis, which is transmitted to cetaceans through the food chain. This study aimed to analyse which factors, including dolphin diet, affect the parasitic load. Samples of stomach contents from stranded dolphins along the Galician coast (2004–2024) were examined. The number of parasites was counted, and the contribution of different prey species to the diet was analysed based on hard remains. Generalised Additive Models (GAMs) were used to assess the relationships between parasitic load (number of Anisakis in the stomach) and various putative explanatory variables (e.g., year, month, size, sex, latitude, body condition, cause of death and diet of the dolphins). Results showed an increase in parasitic load over the years and a seasonal pattern, with numbers peaking in the first months of the year. A significant positive relationship was found between dolphin length and Anisakis load. In addition, dolphins that died from bycatch had the lowest parasitic loads. The numbers of Atlantic mackerel (Scomber scombrus) and blue whiting (Micromesistius poutassou) in the stomach had a significant effect on parasite load: parasite abundance decreased as the numbers of these prey species in the stomach increased. This result confirms the influence of diet on Anisakis load, although it does not reveal which species contribute the most to the parasite load. The study offers insights into how diet and other ecological factors influence the parasitic load in D. delphis. Full article

The high energy consumption and cost of operation which result from substantial pressure losses during the transportation of crude oil over long-distance pipelines due to frictional drag created by turbulence are fundamental issues. In order to cope with such challenges, the current research intends to develop a simulation-based study that employs MATLAB R2016b and Minitab 21 to assess the effectiveness of drag-reducing agents (DRAs). An effective mathematical representation of the use of basic fluid mechanics with a semi-empirical correlation on the DRA performance is therefore created and its performance compared to actual pipeline data, showing good compatibility with experimental results. The findings show that DRA addition can produce a significant reduction in the pressure drop by 30–35% with an increase in the overall flow efficiency by 40–60%. Using 25 ppm DRA concentration at a Reynolds number of 323,159 enables an optimised prediction of 33.43% in drag reduction with an efficiency of 45.13%. Moreover, it is also found that there are considerable energy savings, flatter radial velocity profiles, and enhanced particle transport, which highlights the radical effect of DRAs on the hydrodynamics of flows. More importantly, it is determined that DRAs are one of the most effective and cost-efficient solutions to improve throughput and decrease the pumping power in the oil pipeline. However, further research is required to generalise the model to multiphase flows and use the newest optimisation algorithms to control the dosage dynamically. Full article

Understanding interactions among sympatric mesocarnivore populations is essential for making sound management decisions. The golden jackal has rapidly expanded in Europe, raising questions about its potential intraguild effects. Using long-term hunting bag data (1997–2024) from Hungary, we investigated spatiotemporal population trends of the European badger, red fox, and golden jackal. We examined pairwise associations in their annual growth rates. Generalised additive models and Pearson correlation analyses revealed strong species-specific temporal and spatial trends and weak to moderate positive relationships among the species’ population growth rates at the national scale and within regions of high jackal population density. We found no evidence of jackal suppression of foxes or badgers. Additionally, badgers showed the strongest positive association with fox populations. Our large-scale analyses suggest that these mesocarnivores coexist without substantial competitive interference, likely due to local spatial heterogeneity and fine-scale temporal partitioning that are not detectable in annual, broad-scale (national) data. These findings highlight the importance of integrating broad-scale population data with finer-scale behavioural studies to better understand coexistence mechanisms in expanding mesocarnivore assemblages. Full article

Background: Type 2 diabetes (T2D) increases cardiovascular disease (CVD) risk and predisposes individuals to heart failure with preserved ejection fraction. Metabolic dysfunction-associated steatotic liver disease (MASLD), prevalent in T2D, may worsen cardiac remodelling and haemodynamics. This secondary analysis of the DIASTOLIC trial examined the relationship of liver fat to cardiac remodelling in T2D at baseline and after a 12-week intervention or standard care. Methods: Adults with obesity and T2D and matched controls underwent hepatic MRI, cardiac MRI, echocardiography, and adipokine profiling as part of the DIASTOLIC study (NCT02590822). Participants with T2D were randomised to supervised exercise, a low-calorie meal-replacement plan (MRP), or routine care for 12 weeks. A baseline case–control and then pre- and post-analyses in those with T2D were performed. Associations between changes in liver fat and cardiovascular measures were assessed using correlation and adjusted generalised linear models. Results: At baseline, 81 T2D and 35 healthy controls were compared, and 76 subjects with T2D completed the trial. Participants with T2D had ~4× higher hepatic fat and adverse haemodynamics. The MRP arm achieved the greatest reductions in BMI, blood pressure, dysglycaemia, insulin resistance, and hepatic fat (−8.9%), with favourable adipokine changes. Overall, hepatic fat loss was associated with reductions in cardiac index and stroke volume and with additional reductions in end-diastolic volume in the MRP arm, independent of BMI. Conclusions: In T2D, hepatic fat is strongly linked to pathological haemodynamic profiles. Intensive caloric restriction achieves substantial hepatic fat loss and normalisation of hyperdynamic cardiovascular physiology independent of weight loss, identifying hepatic steatosis as a potential therapeutic target for early cardiovascular risk reduction. Full article

Automated anomaly detection in transportation infrastructure is essential for enhancing safety and reducing the operational costs associated with manual inspection protocols. This study presents an improved neuromorphic vision system, which extends the prior SIFT-SNN (scale-invariant feature transform–spiking neural network) proof-of-concept by incorporating temporal feature aggregation for context-aware and sequence-stable detection. Analysis of classical stitching-based pipelines exposed sensitivity to motion and lighting variations, motivating the proposed temporally smoothed neuromorphic design. SIFT keypoints are encoded into latency-based spike trains and classified using a leaky integrate-and-fire (LIF) spiking neural network implemented in PyTorch. Evaluated across three hardware configurations—an NVIDIA RTX 4060 GPU, an Intel i7 CPU, and a simulated Jetson Nano—the system achieved 92.3% accuracy and a macro F1 score of 91.0% under five-fold cross-validation. Inference latencies were measured at 9.5 ms, 26.1 ms, and ~48.3 ms per frame, respectively. Memory footprints were under 290 MB, and power consumption was estimated to be between 5 and 65 W. The classifier distinguishes between safe, partially dislodged, and fully dislodged barrier pins, which are critical failure modes for the Auckland Harbour Bridge’s Movable Concrete Barrier (MCB) system. Temporal smoothing further improves recall for ambiguous cases. By achieving a compact model size (2.9 MB), low-latency inference, and minimal power demands, the proposed framework offers a deployable, interpretable, and energy-efficient alternative to conventional CNN-based inspection tools. Future work will focus on exploring the generalisability and transferability of the work presented, additional input sources, and human–computer interaction paradigms for various deployment infrastructures and advancements. Full article

Procambarus clarkii (red swamp crayfish) exhibits physiological plasticity that enables adaptation to variable freshwater conditions, such as those in Lake Trasimeno. This study examined whether fluctuations in hydrometric level and associated physicochemical parameters affect oxidative stress responses in the hepatopancreas and abdominal muscle of male and female individuals. Superoxide dismutase, catalase, glutathione peroxidase, and metallothionein reveal tissue, sex, and season-specific differences that indicate adaptive physiological adjustments. Temporal trends were evaluated, and multivariate analyses summarised environmental and metal gradients. Generalised Additive Models (GAMs) were used to explore relationships between oxidative responses and these gradients, with sex as a categorical factor. Associations were identified with hydrometric level, temperature, conductivity, transparency, pH, dissolved oxygen, and metals of biological relevance. These results highlight the remarkable physiological plasticity of P. clarkii, which underpins its success as an invasive species in fluctuating freshwater ecosystems. Full article

The psychosocial well-being of employees is crucial to health and productivity, and it forms the basis for organisational sustainability. Unfortunately, most studies rely on narrow indicators or small samples and thus are not generalisable. The present study aims to identify psychosocial and health-related factors that distinguish employees with high and low SWB and determine whether these effects are universal or sector-specific. A total of 1628 employees with organisations in Latvia’s public administration, healthcare, pharmaceutical and energy sectors participated by completing the Multidimensional Psychosocial Well-Being Scale for Employed Persons (MPSWEP). This instrument assesses five key work environment factors: social inclusion, professional development, work intensity, health risks and autonomy. Subjective well-being (SWB) was measured as a separate outcome variable, and additional self-reported health problems were included as an independent variable in the analysis. Higher odds of high SWB were observed with greater social inclusion (OR = 5.11; p < 0.001), whereas higher work intensity (OR = 0.51; p < 0.001) and health problems (OR = 0.25; p < 0.001) were associated with lower odds of high SWB. Model accuracy was high (AUC = 0.85–0.87), with significant differences between sectors. The results suggest that some resources universally facilitate well-being across sectors, while others exert more sector-specific effects. Full article

Copepods are key components of marine food webs, linking primary producers such as microalgae to higher trophic levels, including many fish species. This study investigates long-term changes in the composition, density, and biomass of copepod communities along the Romanian coast of the Black Sea over six decades (1956–2015), based on historical records and recent monitoring from 18 sampling stations. Mean copepod density declined markedly over the study period, particularly during the cold season, decreasing from values exceeding 1000 ind/m³ in the 1960s to <300 ind/m³ after 2000, while biomass showed weaker but comparable long-term fluctuations. Seasonal variability was pronounced, with significantly higher densities and biomass during the warm season. Generalised Additive Models (GAMs) explained up to 40–55% of the variance in copepod density and biomass, depending on the season. During the warm season, phosphate exerted a positive effect on copepod abundance, consistent with bottom-up control via phytoplankton productivity, whereas during the cold season, temperature showed a positive effect and salinity a negative effect, indicating stronger physical control of copepod persistence. Species composition shifted over time, with a reduction in constant species and an increase in rare or accidental taxa in later decades. These results indicate that climate variability and anthropogenic pressures have reshaped copepod communities, with potential consequences for food-web efficiency and ecosystem resilience in the Black Sea. Full article

Background: Chest X-ray (CXR) is widely used for the assessment of thoracic diseases, yet automated multi-label interpretation remains challenging due to subtle visual patterns, overlapping anatomical structures, and frequent co-occurrence of abnormalities. While recent deep learning models have shown strong performance, limitations in interpretability, anatomical awareness, and robustness continue to hinder their clinical adoption. Methods: The proposed framework employs a hybrid ConvNeXtV2–Vision Transformer (ViT) architecture that combines convolutional feature extraction for capturing fine-grained local patterns with transformer-based global reasoning to model long-range contextual dependencies. The model is trained exclusively using image-level annotations. In addition to classification, three complementary post hoc components are integrated to enhance model trust and interpretability. A segmentation-aware Gradient-weighted class activation mapping (Grad-CAM) module leverages CheXmask lung and heart segmentations to highlight anatomically relevant regions and quantify predictive evidence inside and outside the lungs. An ontology-driven neuro-symbolic reasoning layer translates Grad-CAM activations into structured, rule-based explanations aligned with clinical concepts such as “basal effusion” and “enlarged cardiac silhouette”. Furthermore, a lightweight out-of-distribution (OOD) detection module based on confidence scores, energy scores, and Mahalanobis distance scores is employed to identify inputs that deviate from the training distribution. Results: On the VinBigData test set, the model achieved a macro-AUROC of 0.9525 and a Micro AUROC of 0.9777 when trained solely with image-level annotations. External evaluation further demonstrated strong generalisation, yielding macro-AUROC scores of 0.9106 on NIH ChestXray14 and 0.8487 on CheXpert (frontal views). Both Grad-CAM visualisations and ontology-based reasoning remained coherent on unseen data, while the OOD module successfully flagged non-thoracic images. Conclusions: Overall, the proposed approach demonstrates that hybrid convolutional neural network (CNN)–vision transformer (ViT) architectures, combined with anatomy-aware explainability and symbolic reasoning, can support automated chest X-ray diagnosis in a manner that is accurate, transparent, and safety-aware. Full article