Search Results (251)

Multi-site water quality sequences are jointly affected by seasonal periodicity, meteorological disturbances, and inter-site differences in the Jianghuai Watershed region. Conventional quality prediction models struggle to simultaneously achieve multi-scale feature extraction, spatial heterogeneity characterization, and prediction uncertainty expression. This study used daily-scale monitoring data on dissolved oxygen (DO), pH, and ammonia nitrogen (NH3N) from 32 monitoring stations within the region in 2025 and proposed the FT-TransONet (Fourier-enhanced Temporal Transformer Operator Network) multi-site probabilistic water quality prediction model. Within a Transformer framework, the model employed a FourierTime learnable frequency-domain filtering module, a GeoBias (Geographic Bias) attention bias mechanism, and a multi-residual ensemble strategy composed of a multilayer perceptron (MLP), a gated recurrent unit (GRU), and a temporal convolutional network (TCN) combined with a mass conservation constraint, thereby achieving both point and interval prediction of key water quality indicators. The results showed that FT-TransONet achieved the lowest Macro_RMSE among all compared methods on the multi-site water quality prediction task. At a prediction horizon of three days, its Macro_RMSE reached 0.2255, which was 21.89% lower than that of the long short-term memory network and 5.57% lower than that of the strongest baseline MC-Dropout. For the three individual indicators, the model attained coefficients of determination of 0.9135, 0.9338, and 0.8660 for dissolved oxygen, pH, and ammonia nitrogen, with corresponding root-mean-square errors of 0.5145, 0.1098, and 0.0523, confirming its potential to characterize the temporal variation in the main water quality indicators. Under multi-step prediction, the error grew gently, with the Macro_RMSE rising only from 0.2255 to 0.2384 as the horizon extended from three to seven days, and the ablation experiments, together with the probabilistic prediction results, further supported the effectiveness of the proposed structural design. Validated on 32 water quality monitoring stations in the Jianghuai Watershed, the method improved multi-site prediction accuracy while accounting for stability and uncertainty quantification, providing a preliminary reference for regional water quality early warning and management. Full article

Accurately depicting the spatiotemporal evolution patterns and driving mechanisms of soil drought is of great significance for regional agricultural drought warning and adaptive management of water resources. There are still shortcomings in the existing research in terms of indicator applicability, mutation detection and trend persistence collaborative diagnosis, as well as the quantification of multi-scale meteorological driving factors. In response to the above issues, this study constructs the Standardized Soil Moisture Index (SSMI) based on the principle of soil moisture supply and demand balance, and comprehensively uses BFAST structure mutation detection, autocorrelation correction Mann–Kendall (MMK) trend test, Hurst persistence analysis, and cross-wavelet transform methods to systematically analyze soil drought in the Haihe River Basin (HRB) from 2000 to 2022. Using the FLDAS reanalysis dataset and multi-source meteorological observation data, this study revealed the stage changes, seasonal evolution characteristics, and dominant meteorological driving factors of soil drought in the watershed. Key findings include: (1) the most significant structural breakpoint occurred in May 2005 (confidence interval: March–November 2005); (2) spring exhibited the strongest drying trend (mean Z_s = −0.51), while autumn showed the strongest anti-persistence (mean Hurst = 0.41), making it the most vulnerable season for future soil moisture state shifts; (3) evapotranspiration was the dominant meteorological driver, with the highest significant coherence area percentage (SCAP), followed by air humidity, soil moisture, soil temperature, air temperature, and precipitation in descending order of influence. Full article

Background: Extreme drought and flood events continuously threaten the stability of forest and crop production. Long-term hydrological records derived from tree-ring anatomical proxies provide critical evidence for revealing historical drought hazard differentiation. Methods: Cell wall thickness chronologies of Betula platyphylla (northern forest) and Picea koraiensis (southern agro-pastoral zone) were developed to reconstruct nearly 300-year annual runoff sequences. Pearson correlation, quadratic regression, wavelet transform and superposed epoch analysis (SEA) were applied to quantify hydrological evolution, periodic signals, large-scale climate forcing and statistical coupling between dry/wet extremes and historical yield reduction records. Results: The northern watershed showed stronger interannual runoff oscillation. Both regions entered persistent low-flow phases post-1950. Pacific Decadal Oscillation (PDO) acted as the dominant driver, while solar radiation exerted weak secondary regulation. Severe drought events corresponded closely to historical forest and grain yield losses, with far higher agricultural vulnerability in the southern agro-pastoral ecotone. Conclusions: This study reconstructed the long-term historical runoff of the Greater Khingan Range from the thickness of the cell wall, analyzed the different impacts of PDO on it, and clarified the differentiated effects of drought and flood on agricultural and forestry production losses and the interrelated impact of land use on hydrology and the value of agricultural output. Full article

Accurate runoff prediction is an essential foundation for water resource management, flood prevention, and drought warning. Despite the superior performance of deep learning models in runoff prediction, the high-dimensional hyperparameter optimization limits their widespread application. To address this challenge, this study proposed a hyperparameter optimization strategy that integrated Uniform Design (UD) and Meta-Learning (ML) within the Transformer framework (UD-ML-Transformer) for daily runoff prediction. Performance of the proposed model was systematically evaluated against five benchmark models, including the UD-Transformer, Particle Swarm Optimization (PSO)-Transformer, and three Receptance Weighted Key Value (RWKV)-based models (PSO-RWKV, UD-RWKV, and UD-ML-RWKV), using hydroclimatic data spanning 1980 to 2014 from the Rio Pueblo de Taos watershed in USA. Results showed that the UD-ML-Transformer model performed the best in both prediction accuracy and peak flow, with the highest Nash-Sutcliffe Efficiency (NSE) of 0.906, and the lowest Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE) of 0.004, 0.062, and 0.034, respectively. The UD-Transformer ranked second in performance, followed by the PSO-Transformer. The integrated UD-ML hyperparameter optimization strategy also improved the performance of RWKV-based models. Compared with the PSO-RWKV and UD-RWKV models, the UD-ML-RWKV model exhibited an NSE improvement of 0.45–7.65% and an RMSE reduction of 1.47–21.18%, respectively. Moreover, cross-watershed validation conducted in the Ford River watershed, USA, also demonstrated the satisfactory performance of the proposed UD-ML-Transformer model, with the highest NSE of 0.890, and the lowest MSE, RMSE, and MAE of 0.088, 0.296, and 0.141, respectively. These findings highlight the superiority of integrating UD and ML for hyperparameter optimization in runoff forecasting. Full article

Under rapid urbanization and watershed-scale spatial restructuring, urban green-space systems are often treated as residual indicators after construction land has been allocated, which limits the capacity of blue–green networks to act as leading frameworks for spatial structure and development sequencing. Taking the Sanjiangkou New Town Master Plan in Lishui, Zhejiang Province, China, as a case, this study develops the concepts of landscape-flow transformation and locality in urban green-space networks and examines their generative, planning, and participatory mechanisms through planning-document interpretation, visual evidence-chain analysis, sequential scenario construction, and an exploratory public-participation questionnaire survey. The paper proposes an integrated Perception–Cognition–Interaction (PCI) and Ecology–Construction–Program (ECP) framework. The ECP framework clarifies how locality-based landscape ecology constrains network formation, how frontloaded green networks shape urban zoning and mobility structures, and how long-term construction, use, and feedback refine master-planning schemes. The PCI framework explains how the public enters planning communication through embodied locality perception, structural understanding, and interactive feedback. Based on 400 valid questionnaires, the results reveal significant differences between local and non-local respondents in locality perception and planning understanding. The PCI pathway provides exploratory evidence that perception, cognition, and interaction are closely associated in scenario-based planning communication. The study argues that green-space networks should be introduced as an ecological substrate, structural constraint, and dynamic feedback system rather than as post hoc environmental land-use allocation. Its contribution is to reposition locality from a visual character label to a mechanism of pattern generation, phasing, and participatory negotiation. Full article

Deep learning methods have exemplified performance in various dental image segmentation tasks. However, their interpretability inadequacy remains a hindrance to clinical adoption. This study introduces a quantitative explainability-driven evaluation framework to systematically assess and compare convolutional and transformer-based segmentation models in dental imaging. Specifically, we evaluate a convolutional Watershed Encoder–Decoder Neural Network (WEDN) and the hybrid Vision Transformer U-Net (ViTUNet) model using both qualitative and quantitative explainability metrics. The qualitative analysis employs Grad-CAM, occlusion sensitivity, and attribution-based visualization techniques to assess model decision patterns. Quantitatively, we define and apply explainability metrics, including Dice coefficient, boundary Dice, sparsity, and faithfulness metric scores, to independently evaluate segmentation performance and explanation quality. The experimental results show that ViTUNet achieves superior spatial localization, with higher Dice ($0.765$) and boundary Dice ($0.421$), compared to the WEDN model ($0.664$ and $0.221$), indicating improved lesion delineation in dental images. Moreover, the ViTUNet model exhibits higher sparsity scores in attribution maps, indicating more concentrated and structured interpretability regions, while the WEDN model demonstrates higher faithfulness scores under perturbation-based evaluations, thus reflecting stronger dependence on localized feature representations. These findings highlight a key distinction between convolutional and transformer-based architectures with predictive behavior and explanation characteristics. Notably, the results further indicate that gradient-based explanation methods are more stable for transformer-based models, while perturbation-based methods better capture the decision logic of convolutional networks. In general, this study establishes an integrated framework for collectively evaluating segmentation performance and explainability, allowing more transparent and clinically reliable deployment of deep learning models in dental imaging. Full article

The aim of this paper is to reflect on the changing relationship between Catholic education and the State in the eighty years that have elapsed since the passing of the 1944 ‘Butler’ Education Act. The 1944 Education Act proved to be a transformational landmark in the development of Catholic education in this country. Whilst in many other countries in the world Catholic education is provided by independent fee-paying schools, in England it has benefited from support and funding provided by the government. The legislation consolidated the relationship between Church and State that had been established with the introduction of compulsory education in 1870. However, integrated within the national educational system, Catholic schools are also subject to political currents that can pose challenges. When I began teaching in a Catholic secondary school in the mid-1970s, compulsory education was framed within the legislation set out in the 1944 Education Act. However, the post-war consensus that informed that legislation was swept away in the wake of the passing of the 1988 Education Reform Act (ERA). This latter development marked a watershed in schooling in England and Wales. Whilst extending greater autonomy to schools through Local Management of Schools (LMS) and Grant Maintained (GM) status, central government designed and regulated education for all maintained schools through a National Curriculum and it intervened more rigorously in their management by scrutinising their performance through the establishment of regular Ofsted inspections. Arguably, the introduction of Grant Maintained schools contributed to ‘a survival of the fittest approach’, which challenged concerns for the common good. Moreover, with the passing of the 2010 Academies Act, it became possible for all maintained schools in England and Wales to convert to academies and multi-academy trusts (MATs) by direct agreement with the Secretary of State for Education. Within the Catholic sector, where the bishop has traditionally been primarily responsible for the regulation of education provided by Catholic schools across his diocese, the question of academisation has provoked divisions of opinion about the governance of Catholic schools. Drawing on a reflection on my own experience as a teacher and leader in Catholic secondary education, the paper examines opportunities and challenges that have faced Catholic education in this country over the past eighty years and considers implications for its future. Autobiographical narrative is a method of research located within the qualitative field of enquiry. Whilst its subjective and introspective nature has been open to question, it provides a researcher with the opportunity to examine personal experience to provide illuminative insight. Full article

Water systems often change more rapidly than traditional monitoring frameworks can detect. Historically, water-quality assessment relied on intermittent sampling and delayed laboratory analysis. It has since evolved toward continuous sensing, satellite observations, and autonomous monitoring platforms that generate vast, high-frequency datasets. Yet, interpreting these heterogeneous data streams remains a challenge. Artificial Intelligence (AI) now provides the analytical framework needed to transform raw observations into actionable environmental intelligence, revealing patterns, transitions, and anomalies that conventional methods overlook. From predicting nocturnal hypoxia to reconstructing storm-driven nutrient pulses and forecasting harmful algal blooms, AI can expose the dynamic processes that govern aquatic ecosystem behavior. This review synthesizes recent advances in AI across physical, chemical, biological, and watershed domains and demonstrates their practical relevance to proactive watershed management using a narrative case study. It further examines governance and ethical considerations and outlines a roadmap for developing environmental intelligence that can support equitable, transparent, and climate-resilient water management systems. Full article

Remote sensing imagery provides a primary data source for large-scale surface water body monitoring, which is crucial for quantifying climate-related hydrological impacts, supporting flood control, and sustaining integrated water resource management. However, remote sensing images generally face the trade-off between spatial resolution and temporal coverage. To address this issue, the Real-ESRGAN super-resolution algorithm is employed to reconstruct temporally continuous, wide-coverage medium-resolution imagery to a 2.5 m resolution, effectively improving its capability to identify sub-pixel river boundaries. Water body segmentation (WBS) is an effective method for fine-detail surface water extraction. Nonetheless, when applied in complex hydrological environments, it still faces several limitations, such as ambiguous delineation of land–water boundaries and the difficulty in capturing multiscale water body characteristics. To address these issues, a Dynamic Weight Fusion SegFormer (DWFSeg) network is constructed, integrating a MixVision Transformer (MVT) encoder with a multiscale decoding architecture. Specifically, a Dynamic Multiscale Feature Fusion (DMFF) mechanism is proposed, which adaptively assigns semantic-guided fusion weights to multiscale feature water bodies. Furthermore, the Dual Attention-Enhanced (DAE) module strengthens discriminative essential features and suppresses background noise in both channel and spatial dimensions. Evaluated on a self-constructed super-resolution imagery dataset (SID) and the public GID, DWFSeg achieves overall accuracies of 98.08% and 96.14%, respectively. It outperforms representative benchmark models across multiple quantitative metrics, while maintaining competitive inference efficiency and favorable segmentation stability. Ablation studies verify the effectiveness and necessity of each proposed component. The presented network provides a reliable technical solution and supports refined water resource evaluation and sustainable watershed management. Full article

Background: Malaria is a life-threatening disease caused by Plasmodium species, which is endemic in tropical and subtropical regions worldwide. In clinical settings, experienced parasitologists perform microscopic examinations of thick/thin blood slides. This method is labour-intensive and is adversely affected by inter- and intra-observer variability among the microscopists. The present study aimed to develop a malaria screening algorithm using computer vision to identify and classify malaria parasite-infected red blood cells (RBC) from microscopic blood slide images. Methods: The proposed classification methodology first employs digital image processing techniques, the watershed transform, to preprocess the raw images, followed by connected component labelling to accurately segment and isolate individual RBCs from the background. To classify these segmented cells as either normal or infected, convolutional neural networks (CNNs) were utilized, leveraging their ability to automatically extract relevant features through deep, hidden layers, thus eliminating the need for manual feature engineering. Results: To compare and determine the most effective classification engine, the study developed and evaluated five distinct models: four well-established transfer learning architectures (VGG16, VGG19, DenseNet121, and InceptionV3), alongside a newly proposed custom CNN model. A total of 2422 segmented RBC images were used for the training, and 692 different images were used for testing, with the VGG model showing the best accuracy at 99.57%. The proposed CNN architecture also showed competitive results with 99.14% accuracy. Conclusions: Transfer learning models demonstrated remarkable accuracy for malaria parasite classification from blood smear slides, with VGG19 (99.57%) achieving the highest accuracy on diverged datasets for the test images. The analysis demonstrates the potential of this approach as a computational aid for future image-based malaria screening in conjunction with existing diagnostic tests. Full article

Agricultural karst watersheds are highly vulnerable to nutrient loss because strong surface water–groundwater (SW–GW) connectivity can rapidly transfer nitrogen and sulfur species from soils, agricultural activities, and human settlements into aquatic systems. However, the coupled behavior and contrasting controls of nitrate (NO₃⁻) and sulfate (SO₄²⁻) in such agroecosystems remain insufficiently understood, limiting effective nutrient and groundwater-quality management. In this study, a typical karst agricultural watershed in Southwest China was selected to investigate the sources, transformation processes, and transport pathways of NO₃⁻ and SO₄²⁻ under strong SW–GW interactions. During the rainy season, 44 groundwater and 40 surface water samples were collected for major hydrochemical and nitrate–sulfate stable isotope analyses. An integrated framework combining hydrochemical analysis, self-organizing maps (SOM), positive matrix factorization (PMF), and MixSIAR were used to identify dominant sources, quantify source contributions, and clarify controlling processes. The results showed that groundwater was mainly characterized by carbonate-controlled Ca-HCO₃ facies, whereas surface water exhibited higher mineralization and a shift toward Ca-SO₄ facies, indicating stronger external inputs and rapid hydrological responses. Nitrate was primarily controlled by external nitrogen inputs, with manure and sewage and soil nitrogen contributing 39–62% and 16–33%, respectively. Nitrate was also regulated by nitrification under oxic conditions, while denitrification was negligible. In contrast, sulfate was predominantly governed by geogenic processes, with sulfide oxidation contributing 63–83%, while other sources were minor. These contrasting controls resulted in distinct spatial and process behaviors: nitrate showed source-driven variability associated with agricultural and domestic inputs, whereas sulfate displayed process-driven accumulation mainly controlled by water–rock interactions. Strong SW–GW connectivity enhanced the transfer of anthropogenic nutrient signals, while subsurface mixing and buffering regulated their expression in groundwater and surface water. These findings demonstrate a clear decoupling between nitrate and sulfate controls in agricultural karst systems and provide a scientific basis for nutrient pollution control, groundwater protection, and sustainable agricultural water management in vulnerable karst regions. Full article

Beat-level synchrony among cardiomyocyte clusters is a critical indicator of cardiac electromechanical function. Traditional invasive approaches have substantial limitations, and conventional computer vision methods are poorly suited for resolving densely packed, adherent clusters. To address these challenges, we developed an analysis framework to characterize the beating characteristics of cardiomyocyte clusters from microscopic imaging data. Specifically, we propose CardioSegNet, a multi-task deep learning model that combines attention mechanisms with three prediction heads (semantic segmentation, contour detection, and distance transform), followed by a watershed algorithm to achieve high-accuracy cluster-level segmentation of cardiomyocyte clusters. The Pixel-Difference method is applied to extract time-series beating signals from each segmented cluster and compute several dynamic parameters, including beating amplitude, period, frequency, and the Beat Rate Irregularity (BRI). We further introduce PeriodAwareNAPTD_ij to quantify the beating synchrony among different clusters. Our experimental results show that CardioSegNet achieves a Dice coefficient of 0.8868 and an HD95 of 93.02 µm on an independent test set, demonstrating strong segmentation performance. The cardiomyocyte populations are not uniformly globally synchronized; rather, they consist of multiple local subgroups with high internal synchrony, and the degree of synchronization between clusters is positively correlated with their physical distance. This label-free analytical pipeline provides an efficient tool for myocardial function evaluation and cardiotoxicity screening in vitro. Full article

This study examines whether and through what channels ecological compensation efficiency affects urban economic resilience from a watershed-scale perspective. Using panel data for 108 prefecture-level cities in China’s Yangtze River Economic Belt from 2011 to 2023, ecological compensation efficiency is first measured with a super-efficiency SBM model incorporating undesirable outputs. A two-way fixed effects model, a mechanism-testing framework, robustness checks, and a spatial Durbin model are then employed to investigate its direct effect, transmission mechanisms, and spatial spillovers. The results show that (1) ecological compensation efficiency significantly enhances urban economic resilience, and this finding remains robust under alternative indicator measurements and model specifications; (2) mechanism analysis indicates that ecological compensation efficiency strengthens urban economic resilience by promoting green technological innovation and facilitating digital–real economy integration; and (3) spatial analysis further reveals significant positive spillover effects on neighboring cities. These findings suggest that improving ecological compensation efficiency can enhance both local and regional economic resilience. This study enriches the literature on ecological compensation and resilient urban development and provides policy implications for efficiency improvement, green and digital transformation, and cross-regional collaborative governance. Full article

Understanding the coordinated development of production, living, and ecological (P–L–E) functions is critical for sustainable watershed governance in rapidly transforming regions. Using the Chaohu Lake Basin, China, as a case study, this study developed a process–pattern–potential–driver framework for watershed-scale P–L–E coordination analysis from 2000 to 2020. Unlike previous studies that mainly assess coordination levels or map spatial patterns, this framework further identifies subsystem constraints, quantifies coordinated development potential, and determines key factors driving spatial differences. The results show that production and ecological functions remained weakly coordinated, indicating persistent tension between economic growth and ecological protection. In contrast, the relationships between production and living functions and between living and ecological functions improved from strong imbalance to moderate coordination. Spatially, higher coordination levels were concentrated in the southwestern basin. Decoupling analysis further reveals that production activities, especially the energy-intensive secondary industry, were the main constraint on ecological function. In addition, 88.2% of the basin showed an increasing trend in coordinated development potential. Land-use patterns, socioeconomic conditions, and eco-environmental quality were identified as direct drivers, whereas climate change mainly acted indirectly. By linking diagnostic results with spatially differentiated management needs, this study provides a basis for more targeted watershed governance. Full article

For microbiological diagnostics, accurately counting and segmenting microbial colonies is extremely important. However, manual methods are labor-intensive and yield inconsistent results. We develop a hybrid model using swarm intelligence, combining a convolutional transformer with nested skip connections and global context with channel and spatial attention. Parameter tuning is supported by a variety of swarm optimization algorithms (e.g., Particle Swarm Optimization, Quantum-behaved Particle Swarm Optimization, and Differential Evolution Particle Swarm Optimization). Morphological refinement, including a further watershed transform, an attention graph, and post-processing, enhances colony boundaries by separating them. Grad-CAM++, Integrated Gradients, and temperature scaling provide a transparent and trustworthy model through explainability and post hoc calibration. The proposed model was extensively tested on the Microbial Colony Recognition and Circular Bacterial Colony Datasets, achieving a Dice score of 94.2%, an Intersection over the Union of 88.6%, and a mean absolute counting error of 2.7 colonies. These results significantly outperform several baseline models, including U-Net (88.1%), U-Net++ (89.7%), Attention U-Net (90.6%), and Swin-Unet (91.4%). Statistically significant improvements were confirmed (p < 0.01). A cross-dataset analysis demonstrates the framework’s robustness and cross-domain applicability, and positions it as a trustworthy, explainable automated model for assessing microbial colonies in laboratory and clinical settings. Full article