Search Results (1,939)

Remote sensing building change detection (RSBCD) is critical for land surface monitoring and understanding interactions between human activities and the ecological environment. However, existing deep learning-based RSBCD methods often result in mis-detected pixels concentrated around object boundaries, mainly due to ambiguous object shapes and complex spatial distributions. To address this problem, we propose a new Multiscale Edge-Aware change detection Network (MEANet) that accurately locates edge pixels of changed objects and enhances the separability between changed and unchanged pixels. Specifically, a high-resolution feature fusion network is adopted to preserve spatial details while integrating deep semantic information, and a multi-scale supervised contrastive loss (MSCL) is designed to jointly optimize pixel-level discrimination and embedding space separability. To further improve the handling of difficult samples, hard negative sampling is adopted in the contrastive learning process. We conduct comparative experiments on three benchmark datasets. Both Visual and quantitative results demonstrate that our new MEANet significantly reduces misclassified pixels at object boundaries and achieve superior detection accuracy compared to existing methods. Especially on the GZ-CD dataset, MEANet improves F1-Score and mIoU by more than 2% compared with ChangeFormer, demonstrating strong robustness in complex scenarios. It is worth noting that the performance of MEANet may still be affected by extremely complex edge textures or highly blurred boundaries. Future work will focus on further improving robustness under such challenges and extending the method to broader RSBCD scenarios. Full article

Water functional zoning plays a crucial role in water resource allocation, pollution prevention, and ecological protection. With the increasing intensity of human activities, there is a significant mismatch between current water functional zoning and the economic, social development needs and ecological protection goals. Existing water functional zoning methods mainly rely on expert experience for qualitative judgment, which is highly subjective and inefficient. In response, this paper presents a transferable quantitative feature system and introduces a machine learning-based progressive zoning framework for water functions, validated through a case study of the Yangtze River Basin. The results show that the overall accuracy of the framework is 0.78, which is 4–7% higher compared to traditional single models. In terms of spatial distribution, the transformation of protection and reserved zones in 2020 mainly occurred in the middle and lower reaches, where human activities are frequent, particularly in Sichuan and Jiangxi provinces. The development zones are highly concentrated in the downstream areas, with some regions transitioning into protection or reserved zones, mainly in Hubei and Chongqing provinces. Adjustments to buffer zones are primarily concentrated along inter-provincial boundary areas, such as the junction between Hubei and Anhui provinces. This framework helps managers quickly identify key areas for optimizing water functional zones, providing valuable reference for the precise management of water resources and the formulation of ecological protection strategies in the basin. Full article

Aquaculture faces environmental challenges from sediment contamination by potentially toxic elements. This study investigated how aquaculture patterns and seasons jointly affect the distribution and ecological risks of these potentially toxic elements in sediments. By analyzing and comparing sediment samples from different aquaculture systems across seasons, we found that Mn (mean = 435.42 mg/kg) was the most abundant, followed by Zn (mean = 172.69 mg/kg), Cr (mean = 106.79 mg/kg), and Cu (mean = 63.44 mg/kg). Aquaculture patterns were the primary factor determining the composition of potentially toxic elements, followed by season. Fish farming tended to promote their accumulation in sediments, whereas the rice–crayfish co-culture model effectively reduced the enrichment of potentially toxic elements and their associated ecological risks. Therefore, optimizing aquaculture practices proves more effective in controlling these risks than managing seasonal variations. Moreover, total phosphorus was identified as a key driver of potentially toxic element accumulation in sediments. The results from the rice–crayfish co-culture system indicate that enhanced phosphorus management is crucial for mitigating such risks. Accordingly, it is necessary to develop systematic monitoring and integrated remediation strategies focused on priority metals and their main drivers. Full article

As a distal factor influencing adolescents’ psychological development and behavioral adaptation, the question of whether and how childhood unpredictability is associated with smartphone addiction remains unclear. To address this gap, this study examined the mediating roles of self-concept clarity and self-control, as well as the moderating role of psychological resilience, in the relationship between childhood unpredictability and smartphone addiction. Using a random cluster sampling method, 2262 high school students (51.59% girls; M_age = 17.83, SD = 0.77) were recruited to complete relevant questionnaires. Correlation analyses revealed that childhood unpredictability was negatively correlated with self-concept clarity, self-control, and psychological resilience, and positively correlated with smartphone addiction. Mediation model results indicated that childhood unpredictability contributes to higher smartphone addiction both directly and indirectly through the independent mediating roles of self-concept clarity and self-control and a chained mediation pathway from self-concept clarity to self-control. Moreover, the link between childhood unpredictability and self-concept clarity was moderated by psychological resilience. These findings highlight the critical role and underlying mechanisms of childhood unpredictability in increasing adolescents’ risk of smartphone addiction and emphasize that fostering psychological resilience should be a key target for prevention and intervention efforts aimed at mitigating the adverse effects of childhood unpredictability. Full article

To strengthen the safety management and control of explosives in underwater blasting construction sites, this study proposes an improved YOLOv11-based network named CRS-Y, designed to enhance the detection accuracy of explosives in complex underwater environments and improve the recognition capability of multi-scale targets. To address the limitations of traditional object detection methods in handling complex backgrounds and low-resolution targets, a lightweight re-parameterized vision transformer was integrated into the C3K module, forming a novel CSP structure (C3K-RepViT) that enhances feature extraction under small receptive fields. In combination with the Efficient Multi-Scale Attention (EMSA) mechanism, the model’s spatial feature representation is further strengthened, enabling a more effective understanding of objects in complex scenes. Furthermore, to reduce the computational cost of the P2 feature layer, a new convolutional structure named SPD-DSConv (Space-to-Depth Depthwise Separable Convolution) is proposed, which integrates downsampling and channel expansion within depthwise separable convolution. This design achieves a balance between parameter reduction and multidimensional feature learning. Finally, the Inner-IoU loss function is introduced to dynamically adjust auxiliary bounding box scales, accelerating regression convergence for both high-IoU and low-IoU samples, thereby optimizing bounding box shapes and localization accuracy while improving overall detection performance and robustness. Experimental results demonstrate that the proposed CRS-Y model achieved superior performance on the VOC2012, URPC2020, and self-constructed underwater blasting datasets, effectively meeting the real-time detection requirements of underwater blasting construction scenarios while exhibiting strong generalization ability and practical value. Full article

Detecting surface defects in forgings is crucial for ensuring the reliability of automotive components such as steering knuckles. In fluorescent magnetic particle inspection (FDMPI) images, normal forging surfaces generally exhibit locally symmetric texture patterns, whereas cracks and other flaws appear as locally asymmetric regions. Traditional FDMPI inspection relies on manual visual judgement, which is inefficient and error-prone. This paper introduces SDDNet, a symmetry-aware deep learning model for surface defect detection in FDMPI images. A dedicated FDMPI dataset is constructed and further expanded using a denoising diffusion probabilistic model (DDPM) to improve training robustness. To better separate symmetric background textures from asymmetric defect cues, SDDNet integrates a UPerNet-based segmentation layer for background suppression and a Scale-Variant Inception Module (SVIM) within an RTMDet framework for multi-scale feature extraction. Experiments show that SDDNet effectively suppresses background noise and significantly improves detection accuracy, achieving a mean average precision (mAP) of 45.5% on the FDMPI dataset, 19% higher than the baseline, and 71.5% mAP on the NEU-DET dataset, outperforming existing methods by up to 8.1%. Full article

The Xiannüshan Fault Zone, located in the southwestern part of the Huangling Anticline within the Three Gorges Reservoir area of Hubei Province, is one of the largest and most complex faults in the region. The geological structures of its different segments vary significantly. Previous studies have primarily focused on the northern segment and often relied on single geophysical methods, which are insufficient for detailed characterization of the entire fault zone. Based on existing geological data, field reconnaissance results, and the geological characteristics of different segments of the fault zone, we employed multiple geophysical methods for a varied investigation: shallow seismic reflection in the northern segment; a combination of waterborne seismic exploration and microtremor survey in the middle segment; and high-density resistivity in the southern segment. The integrated approach revealed the spatial extent, fault geometry, and activity characteristics of each segment, confirming that the Xiannüshan Fault Zone is a pre-Quaternary structure dominated by thrusting. The findings provide a critical scientific basis for regional seismic hazard assessment and disaster mitigation planning, while also establishing a technical framework with significant practical application value for detailed fault characterization in geologically complex environments. Full article

To address the power fluctuation challenges associated with high-proportion wind power integration and enhance the source–load coordination capability of aluminum electrolysis parks, this paper proposes a multi-time scale collaborative regulation strategy. Based on the production characteristics and regulation principles of aluminum electrolysis loads, a multi-objective optimization model for regulating loads with multiple potline series is established, considering both production revenue and temperature penalties. On this basis, a multi-time scale optimal scheduling model is developed for the park, involving day-ahead commitment optimization, intraday rolling adjustment, and real-time dynamic responses. Case studies based on actual data demonstrate that the proposed strategy effectively alleviates wind power fluctuations and enhances local consumption capacity. Compared to the baseline scenario without load regulation, the integration of electrolytic aluminum load across day-ahead, intra-day, and real-time stages reduces wind curtailment by approximately 40.1%, 52.5%, and 74.6% in successive scenarios, respectively, while the total operating cost shows a decreasing trend with reductions of about 1.15%, 0.63%. This facilitates economical and high-quality operation while maintaining temperature stability for the aluminum electrolysis production process. Full article

The indiscriminate and excessive use of antimicrobial agents in livestock production is a major driver of antimicrobial resistance (AMR), thereby posing a grave threat to global public health. Although several surveillance studies have documented antimicrobial resistance patterns of swine-derived E. coli in different regions of China, comprehensive investigations integrating multilocus sequence typing (MLST), resistance determinants, and virulence gene profiles have remained scarce for central China, particularly Hubei province, since 2018. This study investigated the prevalence of antibiotic resistance, and molecular epidemiology of E. coli isolated from swine farms in Hubei province, China, while simultaneously analyzing their clonal and genetic diversity. A total of 148 E. coli isolates were collected from porcine sources in central China, revealing distinct regional variations in genetic diversity. Multilocus sequence typing (MLST) analysis identified 38 sequence types (STs) distributed across 7 clonal complexes (CCs) and several unassigned clones. ST46 emerged as the predominant sequence type (19.6% prevalence), followed by ST23 and ST10. Antimicrobial susceptibility testing demonstrated 100% resistance to lincosamides and sulfonamides, with all isolates exhibiting multidrug resistance (MDR) to antimicrobial classes. Genetic characterization detected 16 resistance determinants, with individual isolates carrying 5–7 resistance genes on average. The resistance profile included seven β-lactamase genes: blaTEM (61.5%), blaCTX-M-1G (57.4%), blaDHA (46.6%), blaSHV (39.2%), blaCTX-M-9G (24.3%), blaOXA (13.5%), and blaCMY-2 (1.4%); and eight aminoglycoside-modifying enzyme genes, including polymyxin resistance gene mcr-1 (7.4%). Virulence factor screening through PCR detected nine associated genes, with EAST1, fyuA, STa, K88, STb, Irp2, and LT-1 present in 95.3% of isolates, while K99 and 987P were absent in all specimens. This investigation documents alarmingly high antimicrobial resistance rates in swine-derived E. coli populations while elucidating their genetic diversity. The findings suggest that intensive antibiotic use in porcine production systems has driven the evolution of extensively drug-resistant bacterial isolates. These results emphasize the urgent need to implement antimicrobial stewardship programs in livestock management to mitigate AMR proliferation. Full article

Oxidative stress and chronic inflammation, driven by reactive oxygen species (ROS) and pro-inflammatory cytokines, contribute significantly to diseases like inflammatory bowel diseases (IBD), yet the therapeutic potential of phenolic compounds-rich agricultural byproducts like ramie leaves (Boehmeria nivea L.) remains underexplored for multi-target antioxidant and anti-inflammatory applications. Using response surface methodology, optimal ultrasonic extraction conditions for ramie leaf aqueous extract (RLAE) were determined as a 1:30 g/mL solid-to-liquid ratio, 43 min, and 50 °C, yielding 2.26 ± 0.16 mg/g total phenolic content. RLAE exhibited strong antioxidant activity with IC₅₀ values of 1.09 ± 0.06 mg/mL (DPPH), 0.60 ± 0.02 mg/mL (ABTS), and 0.93 ± 0.03 mg/mL (O₂⁻), a FRAP equivalent of 11.85 ± 0.47 mmol FeSO₄/g, and notable SOD-like activity. In LPS-stimulated IEC-6 cells, RLAE (0.1–0.2 mg/mL) significantly reduced pro-inflammatory cytokines (IL-1β, IL-6, TNF-α) and enhanced IL-10 expression, with low cytotoxicity up to 0.4 mg/mL. HPLC identified 21 compounds, including pyrocatechuic acid, rutin, and hyperoside, driving these effects via ROS scavenging and NF-κB modulation. RLAE’s multi-mechanistic antioxidant and anti-inflammatory properties position it as a sustainable candidate for nutraceutical development in gastrointestinal health, warranting further in vivo studies. Full article

Micro and small enterprises (MSEs) in emerging markets often face resource and capability constraints, highlighting the need to leverage digital innovation for improved performance. Although entrepreneurial orientation (EO) is widely recognized as a driver of firm performance (FP), the capability-based mechanisms linking EO to performance through digital innovation remain underexplored. To address this gap, this study develops and empirically validates a Digital Innovation Opportunity Transformation (DIOT) framework, which explains how EO enhances FP through sequential capability mechanisms—digital opportunity recognition and digital opportunity exploitation—and how IT-environmental support (ITES) strengthens these effects. Using survey data from 286 Ethiopian MSEs and structural equation modeling, the findings reveal that EO has a significant positive impact on FP (β = 0.14, p < 0.05) and generates indirect benefits through internal digital innovation capabilities. Additionally, ITES amplifies these indirect pathways, suggesting that supportive digital infrastructures enhance the outcomes of EO-driven innovation efforts. The study advances theoretical understanding by validating the DIOT framework and elucidating the internal mechanisms linking EO to FP. It also offers practical insights for managers, technology providers, and policymakers seeking to promote EO-led digital innovation in resource-constrained emerging economies. Full article

UAV-based video multi-object tracking (MOT) is a significant task in the field of remote sensing. However, current research still faces critical issues: (1) the limitations of the single architecture of DNNs inherently hinder performance improvement of object detection; and (2) current linear modeling approaches for spatiotemporal relationships fail to capture complex motion patterns in the real world. To overcome the aforementioned issues, a hybrid architecture tracker (HA-Tracker) with a spatiotemporal Mamba motion model for UAV-based video MOT is the first to be proposed, which has the following innovations and contributions: (1) a CNN–Transformer–Mamba detector (CTM detector) is proposed to enhance the capability of object detection, which is a novel synergistic fusion framework for simultaneously fusing the local details of a CNN, the global context of a Transformer, and the long-range dependency of Mamba; and (2) a spatiotemporal Mamba motion model (STM³) is proposed to improve tracking accuracy by modeling the nonlinear spatiotemporal motion relationships of object trajectories. Extensive experimental results indicate that our HA-Tracker achieved outstanding performance, with multiple object tracking accuracy (MOTA) metrics of 44.76% and 52.22% and identity F1 scores (IDF1) of 60.33% and 72.34% on the Visdrone and UAVDT datasets, respectively. These results validate the effectiveness of HA-Tracker, which outperforms the existing MOT networks. Full article

Thorough analysis of regional carbon emissions is essential, given their substantial contribution to overall carbon emissions, as it underpins the formulation of targeted low-carbon development strategies. This study investigates whether Hubei Province can achieve carbon peaking by 2030 and explores feasible emission reduction pathways. To address the limitations of existing regional carbon emission studies—particularly the direct use of decomposition factors in prediction models and the lack of logical separation between mechanism analysis and forecasting—a hybrid analytical-predictive framework is proposed. Specifically, the logarithmic mean Divisia index (LMDI) method is first employed to decompose historical carbon emissions and identify the driving forces, while the STIRPAT model combined with the Lasso regression is subsequently used to screen key influencing factors for emission prediction, thereby avoiding the direct use of decomposition factors in forecasting. Based on the selected factors, a genetic algorithm–optimized backpropagation neural network (GA-BP) is developed to predict carbon emissions in Hubei Province from 2024 to 2035. The predictive performance of the GA-BP model is validated using three statistical indicators (R², MAPE, and RMSE) and compared with Extreme Learning Machine (ELM), Support Vector Regression (SVR), and conventional BP models. Furthermore, six development scenarios are designed in accordance with provincial policy objectives to assess the feasibility of carbon peaking. The results indicate the following: (1) Based on the results of the LMDI decomposition, Lasso–STIRPAT analysis, and model sensitivity analysis, per capita GDP is identified as the primary driving factor of carbon emissions in Hubei Province. (2) The GA-BP model demonstrates superior predictive accuracy compared with benchmark models and (3) carbon peaking by 2030 can only be achieved under Scenario 6, highlighting the necessity of coordinated structural and technological interventions. Based on these findings, targeted policy recommendations for carbon emission reduction are proposed. Full article

Around 85% of all land plants have symbiotic relationships with arbuscular mycorrhizal (AM) fungi, microscopic soil fungi that build extensive filamentous network in and around the roots. These links strongly influence plant development, water uptake, mineral nutrition, and defense against abiotic stresses. In this context, the use of AMF as a biological instrument to enhance plant drought resistance and phenotypic plasticity, through the formation of mutualistic associations, seems like a novel strategy for sustainable agriculture. This review synthesizes current understanding on the mechanisms through which AMF alleviates drought stress in agriculture. We focus on how AMF help maintain nutrient and water homeostasis by modulating phytohormones and signaling molecules, and by orchestrating associated biochemical and physiological responses. Particular emphasis is placed on aquaporins (AQPs) as key water-and stress-related channels whose expression and activity are modulated by AMF to maintain ion, nutrient, and water balance. AMF-mediated host AQP responses exhibit three unique patterns under stressful conditions: either no changes, downregulation to limit water loss, or upregulation to promote water and nutrient uptake. Nevertheless, little is known about cellular and molecular underpinnings of AMF effect on host AQPs. We also summarize evidence that AMF enhance antioxidant defenses, osmotic adjustment, soil structure, and water retention, thereby jointly improving plant drought tolerance. This review concludes by outlining the potential of AMF to support sustainable agriculture, offering critical research gaps, such as mechanistic studies on fungal AQPs, hormonal crosstalk, and field-scale performance, which propose future directions for deploying AMF in drought-prone agroecosystems. Full article

Cell–cell communication (CCC) is essential for multicellular organisms, enabling different cell types to coordinate their activities in both physiological and pathological contexts, such as cell growth, proliferation, tumorigenesis, and immune responses. Metabolites represent an important class of signaling molecules, though their signaling roles were long underappreciated. Growing evidence has highlighted the critical involvement of metabolites in CCC, and the advent of single-cell RNA sequencing (scRNA-seq) has enabled high-resolution exploration of CCC events. This review summarizes existing metabolite–sensor databases and computational tools developed to identify metabolite-mediated CCC using scRNA-seq data. Nonetheless, these databases exhibit considerable variability due to lack of unified collection standards. Most computational tools were adapted from methods used for general CCC inference and often estimate metabolite abundance based on the expression of one or several related genes. Therefore, such approaches are not fully suited to capturing metabolite-mediated CCC due to the complexity of interaction mechanisms between metabolites and their sensors. To address these challenges, improved computational methods and refined databases are needed for the reliable inference of metabolite-mediated CCC. This review discusses the current limitations in database construction and method development, and highlights potential directions for future improvement, including the incorporation of spatial omics and artificial intelligence (AI) approaches. Furthermore, the systematic inference and validation of metabolite-mediated CCC will pave the way for the discovery of novel drugs and therapeutic targets. Full article