Search Results (382)

Antimicrobial resistance (AMR) in hospital wastewater is a recognized public health concern, yet the dynamics of its emergence remain poorly understood. This study aimed to characterize the quantitative and qualitative changes in the microbial community of a newly built internal medicine intensive care hospital wing following the start of patient treatment. Wastewater samples were collected regularly from eight relevant sites, including seven patient-associated locations within the intensive care ward and the central sanitary sewer where all effluent converged. Culture-based analyses targeted the “ESCAPE-SO” bacterial and fungal groups (“Enterococci”, “Staphylococci”, “Candida”, “Acinetobacter”, “Pseudomonas”, “Enterobacteriaceae”, “Stenotrophomonas”, “Others”). Comparisons were made between a 12-month pre-operation period (only flushing every 72 h to prevent contamination of the drinking water system) and the first 12 months of patient treatment. The results showed a significant increase in mean bacterial concentrations from 53 [0–349] CFU/mL before patient treatment to 8423 [3054–79,490] CFU/mL during patient treatment (p = 0.0224) with a particular focus on Pseudomonas spp. as the dominant genus. Resistance against all four main antibiotic classes of the WHO AWaRe essential “watch” list (carbapenems, third-generation cephalosporins, broad-spectrum penicillin and ciprofloxacin) emerged within the first twelve months and depended on the amount of prescribed antibiotics and the number of patients treated. These findings indicate that hospital activity drives rapid development of antimicrobial resistance in wastewater microbial communities, highlighting the critical role of clinical antibiotic use in shaping environmental resistomes. This study provides quantitative evidence that resistance can emerge within months of hospital operation, emphasizing the need for early monitoring and targeted interventions to mitigate the spread of AMR from hospital effluents into broader environmental systems. Full article

Accurate spatiotemporal forecasting underpins high-stakes decision making in smart urban systems, from traffic control and energy scheduling to environment monitoring. Yet two persistent gaps limit current models: (i) spatial modules are often biased toward low-pass smoothing and struggle to reconcile slow global trends with sharp local dynamics; and (ii) the graph structure required for forecasting is frequently latent, while learned graphs can be unstable when built from temporally derived node features alone. We propose SpeQNet, a query-enhanced spectral graph filtering framework that jointly strengthens node representations and graph construction while enabling frequency-selective spatial reasoning. SpeQNet injects global spatial context into temporal embeddings via lightweight learnable spatiotemporal queries, learns a task-oriented adaptive adjacency matrix, and refines node features with an enhanced ChebNetII-based spectral filtering block equipped with channel-wise recalibration and nonlinear refinement. Across twelve real-world benchmarks spanning traffic, electricity, solar power, and weather, SpeQNet achieves state-of-the-art performance and delivers consistent gains on large-scale graphs. Beyond accuracy, SpeQNet is interpretable and robust: the learned spectral operators exhibit a consistent band-stop-like frequency shaping behavior, and performance remains stable across a wide range of Chebyshev polynomial orders. These results suggest that query-enhanced spatiotemporal representation learning and adaptive spectral filtering form a complementary and effective foundation for effective spatiotemporal forecasting. Full article

The sustainability of resources and ecological integrity are significantly influenced by land use and land cover change (LULCC) dynamics, particularly in ecotonal semi-arid regions where biome transitions are highly sensitive to anthropogenic disturbance and climatic variability. This study aims to assess historical LULCC dynamics and spatial reconfiguration across nine classes (grassland, shrubland, wetlands, forestland, waterbodies, farmed land, built-up land, bare land, and mines/quarries) in the C5 Secondary Drainage Region of South Africa over the three periods 1990–2014, 2014–2022, and 1990–2022. Using the South African National Land Cover datasets and the TerrSet liberaGIS v20.03 Land Change Modeller, this research applied post-classification comparison, transition matrices, asymmetric gain–loss metrics, and patch-based landscape analysis to quantify the magnitude, direction, source–sink dynamics, and spatial reconfiguration of LULCC. Results showed that between 1990 and 2014, Shrubland expanded markedly (+49.1%), primarily at the expense of Grassland, Wetlands, and Bare land, indicating bush encroachment and hydrological stress. From 2014 to 2022, the trend reversed as Grassland increased substantially (+261.2%) while Shrubland declined sharply (−99.3%). Forestland also regenerated extensively (+186%) along riparian corridors, and Waterbodies expanded more than fivefold (+384.6 km²). Over the long period between 1990 and 2022, Built-up land (+30.6%), Cultivated land (+16%), Forestland (+140%), Grassland (+94.4%), and Waterbodies (+25.6%) increased, while Bare land (−58.1%), Mines and Quarries (−56.1%), Shrubland (−98.9%), and Wetlands (−82.5%) decreased. Asymmetric analysis revealed strongly directional transitions, with early Grassland-to-Shrubland conversion likely driven by grazing pressure, fire suppression, and climate variability, followed by a later Shrubland-to-Grassland reversal consistent with fire, herbivory, and ecotonal climate sensitivity. LULC dynamics in the C5 catchment show class-specific spatial reconfiguration, declining landscape diversity (SHDI 1.3 → 0.9; SIDI 0.7 → 0.43), and patch metrics indicating urban and cultivated fragmentation, shrubland loss, and grassland consolidation. Based on these quantified trajectories, we recommend targeted catchment-scale land management, shrubland restoration, and monitoring of anthropogenic hotspots to support ecosystem services, hydrological stability, and sustainable land use in ecotonal regions. Full article

Mapping coastal landforms is critical for the sustainable management of ecosystems influenced by both natural dynamics and human activity. This study investigates the application of Transformer-based semantic segmentation models for pixel-level classification of key surface types such as water, sandy shores, rocky areas, vegetation, and built structures. We utilize a diverse, multi-resolution dataset that includes NAIP (1 m), Quadrangle (6 m), Sentinel-2 (10 m), and Landsat-8 (15 m) imagery from U.S. coastlines, along with high-resolution aerial images of the Greek coastline provided by the Hellenic Land Registry. Due to the lack of labeled Greek data, models were pre-trained on U.S. datasets and fine-tuned using a manually annotated subset of Greek images. We evaluate the performance of three advanced Transformer architectures, with Mask2Former achieving the most robust results, further improved 11 through a coastal-class weighted focal loss to enhance boundary precision. The findings demonstrate that Transformer-based models offer an effective, scalable, and cost-efficient solution for automated coastal monitoring. This work highlights the potential of AI-driven remote sensing to replace or complement traditional in-situ surveys, and lays the foundation for future research in multimodal data integration and regional adaptation for environmental analysis. Full article

In the context of the digital transformation of industrial production, the need for intelligent maintenance and repair systems capable of ensuring reliable operation of machine-tool equipment without operator involvement is growing. This present study reviews the current state and future development of diagnostic and condition-monitoring systems for metalworking machine tools. A review of international standards and existing solutions from domestic and international vendors in vibration diagnostics has been conducted. Particular attention is paid to non-intrusive vibration diagnostics, digital twins, multiparametric analysis methods, and neural network approaches to failure prediction. The architecture of the developed system is presented. The concept of the system is developed in full compliance with Russian and international standards of vibration diagnostics. At its core, the comprehensive digital twin relies on machine learning methods. The proposed architecture is a predictive-maintenance system built on interconnected digital twin realizations: the dynamic machine passport of a unit, operational data, and a comprehensive digital twin of the machine-tool equipment. The potential of neuromorphic computing on a hardware platform is being considered as a promising element for local-condition classification and emergency protection. At the current development stage, the operating principle has been demonstrated along with the integration into the control loop. The system is now at the beginning of laboratory testing. It demonstrates capabilities for comprehensive assessment of the equipment’s technical condition based on multiparametric data, short-term vibration trend forecasting using a Long Short-Term Memory network, and state classification using a Multilayer Perceptron model. The results of the system’s testing on a turning machining center have been analyzed. Full article

Incremental computing is becoming increasingly important for processing large-scale datasets. In satellite imagery, spatial resolution, temporal depth, and large files pose significant computational challenges, requiring efficient architectures to manage processing time and resource usage. Accordingly, in this study, we propose a dynamic architecture, termed Multi-Cube, for optical satellite time series. The framework introduces a modular and baseline-aware approach that enables scalable subdivision, incremental growth, and consistent management of spatiotemporal data. Built on NetCDF, xarray, and Zarr, Multi-Cube automatically constructs stable multidimensional data cubes while minimizing redundant reprocessing, formalizing automated internal decisions governing cube subdivision, baseline reuse, and incremental updates to support recurrent monitoring workflows. Its performance was evaluated using more than 83,000 Sentinel-2 images (covering 2016–2024) across multiple areas of interest. The proposed approach achieved a 5.4× reduction in end-to-end runtime, decreasing execution time from 53 h to 9 h, while disk I/O requirements were reduced by more than two orders of magnitude compared with a traditional sequential reprocessing pipeline. The framework supports parallel execution and on-demand sub-cube extraction for responsive large-area monitoring while internally handling incremental updates and adaptive cube management without requiring manual intervention. The results demonstrate that the Multi-Cube architecture provides a decision-driven foundation for integrating dynamic Earth observation workflows with analytical modules. Full article

In this study, we developed a novel water quality model that integrated hydrodynamic, solute transport, and geochemical reactions processes. This model was built upon the open-source ELCIRC hydrodynamic model, the TVD-format solute transport model, and the PhreeqcRM geochemical reaction engine. The accuracy of the model was rigorously validated using a 2D chain decay analytical solution, demonstrating its capability to accurately simulate water flow, solute transport, and chemical reactions. To evaluate the practical applicability of the model, case studies involving the 2012 Huaihe River benzene leakage accident and the acetic acid leakage accident in the Gulei sea area were simulated. Findings indicate that the model effectively captures the diffusion and attenuation dynamics of the benzene contamination plume. Furthermore, it accurately depicts the reaction–diffusion interaction with seawater following acetic acid release. Notably, the versatility and flexibility of the model were further demonstrated by its ability to simulate a wide range of pollutants and their associated biochemical processes. This addresses the limitations of existing water quality models and provides a powerful tool for environmental monitoring and assessment. The results of this study offer valuable insights for improving water quality management and emergency response strategies in the face of environmental pollution incidents. Full article

Additive manufacturing (AM) has emerged as a pivotal technology in component fabrication, renowned for its capabilities in freeform fabrication, material efficiency, and integrated design-to-manufacturing processes. As a critical branch of AM, metal additive manufacturing (MAM) has garnered significant attention for producing metal parts. However, process anomalies during MAM can pose safety risks, while internal defects in as-built parts detrimentally affect their service performance. These concerns underscore the necessity for robust in-process monitoring of both the MAM process and the quality of the resulting components. This review first delineates common MAM techniques and popular in-process monitoring methods. It then elaborates on the fundamental principles of acoustic emission (AE), including the configuration of AE systems and methods for extracting characteristic AE parameters. The core of the review synthesizes applications of AE technology in MAM, categorizing them into three key aspects: (1) hardware setup, which involves a comparative analysis of sensor selection, mounting strategies, and noise suppression techniques; (2) parametric characterization, which establishes correlations between AE features and process dynamics (e.g., process parameter deviations, spattering, melting/pool stability) as well as defect formation (e.g., porosity and cracking); and (3) intelligent monitoring, which focuses on the development of classification models and the integration of feedback control systems. By providing a systematic overview, this review aims to highlight the potential of AE as a powerful tool for real-time quality assurance in MAM. Full article

Accurate monitoring of fish movement is essential for understanding behavioral patterns and group dynamics in aquaculture systems. Underwater scenes—characterized by dense populations, frequent occlusions, non-rigid body motion, and visually similar appearances—present substantial challenges for conventional multi-object tracking methods. We propose an improved CenterTrack-based framework tailored for multi-fish tracking in such environments. The framework integrates three complementary components: a multi-branch feature extractor that enhances discrimination among visually similar individuals, occlusion-aware output heads that estimate visibility states, and a three-stage cascade association module that improves trajectory continuity under abrupt motion and occlusions. To support systematic evaluation, we introduce a self-built dataset named Multi-Fish 25 (MF25), continuous video sequences of 75 individually annotated fish recorded in aquaculture tanks. The experimental results on MF25 show that the proposed method achieves an IDF1 of 82.5%, MOTA of 85.8%, and IDP of 84.7%. Although this study focuses on tracking performance rather than biological analysis, the produced high-quality trajectories form a solid basis for subsequent behavioral studies. The framework’s modular design and computational efficiency make it suitable for practical, online tracking in aquaculture scenarios. Full article

Digital Twin technology is transforming how buildings are designed, operated, and optimized, serving as a key enabler of smarter, more energy-efficient, and sustainable built environments. By creating dynamic, data-driven virtual replicas of physical assets, Digital Twins support continuous monitoring, predictive maintenance, and performance optimization across a building’s lifecycle. This paper provides a structured review of current developments and future trends in Digital Twin applications within the building sector, particularly highlighting their contribution to decarbonization, operational efficiency, and performance enhancement. The analysis identifies major challenges, including data accessibility, interoperability among heterogeneous systems, scalability limitations, and cybersecurity concerns. It emphasizes the need for standardized protocols and open data frameworks to ensure seamless integration across Building Management Systems (BMSs), Building Information Models (BIMs), and sensor networks. The paper also discusses policy and regulatory aspects, noting how harmonized standards and targeted incentives can accelerate adoption, particularly in retrofit and renovation projects. Emerging directions include Artificial Intelligence integration for autonomous optimization, alignment with circular economy principles, and coupling with smart grid infrastructures. Overall, realizing the full potential of Digital Twins requires coordinated collaboration among researchers, industry, and policymakers to enhance building performance and advance global decarbonization and urban resilience goals. Full article

Understanding the breeding ecology and trophic dynamics of the Swainson’s Hawk (Buteo swainsoni) is essential for conserving grassland raptor populations in northern Mexico. We evaluated reproductive success, nest-site characteristics, and diet of the species in the grasslands of Janos, Chihuahua, during the 2006 breeding season. Eighteen nests were monitored to estimate daily survival rates (DSRs) using the Mayfield method. Overall nest success was 44.4%. DSR declined significantly from incubation (0.99 ± 0.00079) to the nestling stage (0.98 ± 0.00087; z = 8.5, p < 0.001), resulting in cumulative survival of 79.9% and 56.2%, respectively. Successful nests tended to occur farther from towns, although this trend was not statistically significant. Most nests were built in mesquite trees at intermediate elevations and in areas with low human disturbance. Diet analyses of 56 pellets and 91 prey remains revealed a predominance of vertebrates (63.17%), mainly mammals and reptiles, with vertebrate frequency significantly exceeding that of invertebrates (χ² = 23.19, p < 0.001). These results highlight the species’ reliance on vertebrate prey and the vulnerability of the nestling stage, underscoring the importance of long-term monitoring in semi-arid grasslands. Full article

The increasing frequency and severity of urban crowd disasters underscore a critical need for intelligent surveillance systems capable of real-time crowd anomaly detection and early warning. While deep learning models such as LSTMs, ConvLSTMs, and Transformers have been applied to video-based crowd anomaly detection, they often face limitations in long-term contextual reasoning, computational efficiency, and interpretability. To address these challenges, this paper proposes HiMeLSTM, a crowd anomaly detection framework built around a hippocampal-inspired memory-enhanced LSTM backbone that integrates Long Short-Term Memory (LSTM) networks with an Episodic Memory Unit (EMU). This hybrid design enables the model to effectively capture both short-term temporal dynamics and long-term contextual patterns essential for understanding complex crowd behavior. We evaluate HiMeLSTM on two publicly available crowd-anomaly benchmark datasets (UCF-Crime and ShanghaiTech Campus) and an in-house CrowdSurge-1K dataset, demonstrating that it consistently outperforms strong baseline architectures, including Vanilla LSTM, ConvLSTM, a lightweight spatial–temporal Transformer, and recent reconstruction-based models such as MemAE and ST-AE. Across these datasets, HiMeLSTM achieves up to 93.5% accuracy, 89.6% anomaly detection rate (ADR), and a 0.89 F1-score, while maintaining computational efficiency suitable for real-time deployment on GPU-equipped edge devices. Unlike many recent approaches that rely on multimodal sensors, optical-flow volumes, or detailed digital twins of the environment, HiMeLSTM operates solely on raw CCTV video streams combined with a simple manually defined zone layout. Furthermore, the hippocampal-inspired EMU provides an interpretable memory retrieval mechanism: by inspecting the retrieved episodes and their att ention weights, operators can understand which past crowd patterns contributed to a given decision. Overall, the proposed framework represents a significant step toward practical and reliable crowd monitoring systems for enhancing public safety in urban environments. Full article

The Semipalatinsk Test Site (STS), one of the most heavily contaminated nuclear test sites globally, presents critical challenges for ecological monitoring and restoration due to long-term radioactive pollution and soil degradation. This study applied the Remote Sensing Ecological Index (RSEI) model to systematically evaluate the spatiotemporal changes in ecological quality at STS from 2003 to 2023. The RSEI model integrated multi-indicator data, including NDVI (Normalized Difference Vegetation Index), LST (Land Surface Temperature), WET (Wetness), and NDBSI (Normalized Difference Built-up and Soil Index), enabling a comprehensive assessment of ecological dynamics. Results demonstrated a significant improvement in ecological quality, with the RSEI increasing by 29.59% (from 0.345 in 2003 to 0.447 in 2023). PCA results indicated that ecological recovery was primarily influenced by surface temperature, vegetation cover, and soil moisture, with radioactive residues further hindering recovery in severely contaminated zones. The proportion of “Poor” areas declined from 14.99% to 0.61%, while “Moderate” and “Good” areas expanded to 55.76% and 8.87%, respectively. Peripheral regions showed faster recovery due to effective natural and management interventions, while core high-contamination zones (Sary-Uzen) exhibited slower recovery due to persistent radioactive residues. This study highlights the applicability of RSEI for assessing ecological recovery in nuclear test sites and emphasizes the need for targeted remediation strategies. These findings provide valuable insights for global ecological management of nuclear test sites, supporting sustainable restoration efforts. Full article

With the continuous expansion of the electric vehicle market, lithium-ion batteries have also been rapidly developed, but this has brought about concerns over the safety of lithium-ion batteries. Research on the correlation mechanism between the expansion and safety of lithium-ion batteries is a key step in the construction of a battery life cycle safety evaluation system. In this paper, the physicochemical mechanism of early safety faults in batteries was analyzed from three dimensions of electricity, heat, and force. The interactions of electrochemical side reactions, thermal runaway chain reactions, and mechanical fault mechanisms were analyzed, and the core induction of early safety risk was explored. A battery coupling model based on electrical, thermal, and mechanical dimensions was built, and the accuracy of the coupling model was verified by a variety of test conditions. Based on the coupling model, the stress distribution of the battery under different safety boundary conditions was simulated, and then the average expansion force of the battery surface was calculated through the stress distribution results. Through this process, a multi-parameter database based on the test and simulation data was obtained. According to the data of battery parameters at different times, an early safety classification method based on the battery expansion force was proposed, and a classification model between battery dimension data and safety level was proposed based on the nonlinear dynamic sparse regression method, and the classification accuracy was validated. From the perspective of fault warning, by establishing a multi-physical coupling model of electrical, thermal, and mechanical fields, the space-time evolution law of battery expansion under different working conditions can be dynamically monitored, and the fault criterion based on the expansion force can be established accordingly to provide quantitative indicators for safety risk classification warnings, and improve the battery’s reliability and durability. Full article

Artisanal and Small-scale Mining (ASM) significantly impacts the Democratic Republic of Congo’s (DRC) socio-economic landscape and environmental integrity, yet its dynamic and informal nature makes monitoring challenging. This study addresses this challenge by implementing a novel deep learning approach to map ASM sites across the DRC using satellite imagery. We tackled key obstacles including ground truth data scarcity, insufficient spatial resolution of conventional satellite sensors, and persistent cloud cover in the region. We developed a methodology to generate a pseudo-ground truth dataset by converting point-based ASM locations to segmented areas through a multi-stage process involving clustering, auxiliary dataset masking, and manual refinement. Four model configurations were evaluated: Planet-NICFI standalone, Sentinel-1 standalone, Early Fusion, and Late Fusion approaches. The Late Fusion model, which integrated high-resolution Planet-NICFI optical imagery (4.77 m resolution) with Sentinel-1 SAR data, achieved the highest performance with an average precision of 71%, recall of 75%, and F1-score of 73% for ASM detection. This superior performance demonstrated how SAR data’s textural features complemented optical data’s spectral information, particularly improving discrimination between ASM sites and water bodies—a common source of misclassification in optical-only approaches. We deployed the optimized model to map ASM extent in the Mwenga territory, achieving an overall accuracy of 88.4% when validated against high-resolution reference imagery. Despite these achievements, challenges persist in distinguishing ASM sites from built-up areas, suggesting avenues for future research through multi-class approaches. This study advances the domain of ASM mapping by offering methodologies that enhance remote sensing capabilities in ASM-impacted regions, providing valuable tools for monitoring, regulation, and environmental management. Full article