Search Results (22,521)

Although Graph Neural Networks (GNNs) are widely regarded as an ideal tool for capturing spatial dependencies in river basins, their effectiveness in hydrological forecasting is severely challenged by a topology paradox: under a purely data-driven paradigm, GNNs fail to spontaneously learn physical laws, generating predictions that lack physical interpretability and frequently violate mass conservation. To address this fundamental problem, this paper proposes a physics-informed graph learning framework integrated with an explicit, differentiable water balance constraint (WB-GNN). By reconstructing the continuity equation into a differentiable loss function, we directly embed physical conservation as a strong inductive bias into the neural network’s training objective. We comprehensively evaluated the model on two large-sample datasets (LamaH-CE and CAMELS) against state-of-the-art baselines, including EA-LSTM and unconstrained Pure-GNN. Quantitative results demonstrate that the proposed physical constraint successfully awakens the potential of river network topology. On the LamaH-CE dataset, WB-GNN achieved a Nash-Sutcliffe Efficiency (NSE) of 0.86 and a Root Mean Square Error (RMSE) of 9.2 ${\mathrm{m}}^3/\mathrm{s}$, outperforming both the domain-specific EA-LSTM (NSE: 0.83) and the unconstrained Pure-GNN (NSE: 0.74). Crucially, the introduction of the differentiable constraint reduced the Physical Inconsistency Ratio (PIR) by an order of magnitude-from 39.8% in the unconstrained model to just 4.3%. Similar robust improvements were validated across the highly heterogeneous CAMELS dataset. These quantifiable results confirm that the proposed method not only achieves superior forecasting accuracy but also fundamentally guarantees physical trustworthiness, making it highly robust for critical decision-making in extreme flood events. Full article

Lunar optical and synthetic aperture radar (SAR) imagery provide complementary information for characterizing the lunar surface. However, their joint use remains challenging because of substantial cross-modality differences and severe illumination constraints, particularly in polar regions. To address this challenge, we propose LS2ODiff (Lunar SAR-to-Optical Diffusion), a diffusion-based framework designed for SAR-to-optical image translation in lunar environments. LS2ODiff uses SAR observations as conditional guidance in the diffusion process and incorporates a partial-convolution strategy into the U-Net backbone to handle irregular invalid regions. In addition, self-attention modules are incorporated into the downsampling stages of the U-Net to model long-range spatial dependencies and enhance global structural consistency in complex lunar terrain. We further construct a dedicated paired dataset of the lunar south polar region by registering Chandrayaan-II DFSAR data with Lunar Reconnaissance Orbiter (LRO) Narrow-Angle Camera (NAC) imagery. Comparative experiments against Pix2Pix, CycleGAN, SynDiff, and ConDiff demonstrate that LS2ODiff achieves better visual fidelity and quantitative performance in terms of peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), Fréchet inception distance (FID), and learned perceptual image patch similarity (LPIPS). These results demonstrate the potential of diffusion models for high-fidelity lunar image translation, offering new opportunities for polar terrain interpretation and future exploration missions. Full article

Alzheimer’s disease (AD) is characterized by progressive neurodegeneration and prominent neuroimmune remodeling, but the contribution of macrophage and myeloid states across disease severity remains incompletely defined. We integrated bulk transcriptomic, single-cell RNA sequencing (RNA-seq), and spatial transcriptomic datasets to characterize AD-associated myeloid immune changes across Braak stage and disease status. Across datasets, M2-like macrophage and myeloid signatures showed progressive enrichment with increasing neuropathological severity and were accompanied by pathway changes related to macrophage proliferation, TGF-β signaling, and myeloid homeostasis. Immune-feature-based classifiers identified macrophage-related variables among the informative features distinguishing AD from controls. CellChat analyses further inferred that M2-like myeloid populations occupied communication-enriched positions in single-cell and spatial interaction networks, including apolipoprotein E (ApoE), CX3C chemokine signaling, and fibronectin 1 (FN1)-associated signaling contexts. Collectively, these findings indicate that M2-like myeloid programs are consistently associated with AD severity and neuroimmune network remodeling. Rather than establishing a causal disease driver, this study highlights M2-like myeloid signatures as candidate neuroimmune components that warrant experimental validation in human-relevant systems. Full article

Change detection in open-pit mining areas from remote sensing imagery is of great importance for mining supervision, ecological monitoring, and restoration planning. Nevertheless, mining-related changes usually exhibit multi-scale patterns, irregular boundaries, and fragmented spatial distributions, which make accurate detection difficult. Existing CNN- and Transformer-based methods often cannot effectively balance global context perception and local detail preservation, resulting in incomplete boundary extraction and insufficient sensitivity to subtle changes. To overcome these limitations, we propose GLMECD-Net, a Global–Local Multi-scale Cross-fusion Enhanced Change Detection Network for remote sensing image change detection in open-pit mining areas. Specifically, a Siamese encoder is used to extract hierarchical bi-temporal features, while a Global–Local Feature Mixing Embedding (GLME) module is introduced to jointly capture long-range contextual information and local spatial details. Furthermore, multi-scale feature aggregation and cross-temporal feature fusion are employed to improve change representation and boundary recovery. Experimental results on mining area datasets show that the proposed method achieves 71.66% Precision, 83.78% OA, 77.53% F1-score, and 53.82% IoU. The results demonstrate that GLMECD-Net provides effective and robust performance for detecting complex and subtle changes in open-pit mining areas. Full article

Hyperspectral image classification (HSIC) is a crucial task for remote sensing applications, requiring accurate pixel-level labeling while effectively capturing both spectral and spatial information. Traditional convolutional neural network architectures often struggle to balance local texture detail and global contextual consistency, and existing neural architecture search (NAS) methods rarely incorporate attention mechanisms, limiting their performance. To address these challenges, this study proposes a multi-scale Transformer-based NAS framework (TR-NAS) for fine-grained hyperspectral image classification. The framework combines local cube sampling, shallow and deep multi-scale convolutions, and a searchable Transformer module that adaptively selects global, local window, and multi-scale attention operators. Lightweight enhanced convolution operators, including dual-gated (DG-Conv) and mixed depthwise (MixConv) convolutions, are incorporated to improve spectral discrimination and scale robustness. Extensive experiments on the PU and Hanchuan datasets demonstrate that TR-NAS achieves superior classification accuracy, stability, and boundary consistency compared to traditional methods and existing NAS architectures, showing improved robustness to spectral similarity and spatial heterogeneity in complex remote sensing scenes. Full article

Background: Locally adapted goat populations represent important reservoirs of genetic diversity and play a crucial role in the sustainability of livestock production systems, particularly in marginal environments. However, many of these populations are currently threatened by genetic erosion caused by crossbreeding with highly specialized commercial breeds. Although previous studies have described the genetic diversity of several goat populations from South America and the Iberian Peninsula, the influence of geographic factors on the genetic structure of these populations remains insufficiently understood. In this study, we investigated the influence of geographic distance and spatial factors on the genetic diversity, population structure, and relationships among locally adapted goat populations from Brazil, Spain, and Ecuador. Methods: A total of 561 goats representing 15 populations were genotyped using a panel of 23 microsatellite markers. The dataset included six locally adapted Brazilian breeds, three Spanish breeds, one Ecuadorian population (Chusca Lojana), four exotic breeds, and one undefined genotype group. Genetic diversity parameters, population structure, genetic relationships, and spatial genetic patterns were evaluated through a combination of population genetic and spatial analyses. Results: The locally adapted populations showed considerable levels of genetic diversity, with the Spanish (H_o = 0.629; H_e = 0.685) and Ecuadorian (H_o = 0.628; H_e = 0.704) populations displaying higher diversity than the Brazilian populations (H_o = 0.583; H_e = 0.628). Significant genetic differentiation was observed among geographic groups. A strong and significant correlation between genetic and geographic distances was detected when all local populations were considered (r = 0.77; R² = 0.59; p < 0.001), as well as when only Brazilian populations were analyzed (r = 0.65; R² = 0.43; p = 0.0075). Spatial analyses further identified potential genetic barriers that may restrict gene flow among certain populations. Conclusions: These findings suggest that geographic isolation plays an important role in shaping the genetic structure of locally adapted goat populations, while historical connections among Iberian and South American populations may also contribute to the observed genetic relationships. The integration of genetic and spatial information provides valuable insights for understanding the evolutionary dynamics of these populations and supports the development of more effective strategies for the conservation and sustainable management of goat genetic resources. Full article

Traffic accidents pose a persistent challenge for urban mobility, public safety, and sustainable development in smart cities, particularly in rapidly growing urban environments. This study presents a data-driven spatiotemporal analysis of traffic accidents in Ecuador, aimed at supporting evidence-based urban traffic management and road safety planning. Using large-scale historical accident records, the proposed approach combines spatial clustering and temporal forecasting techniques to characterize accident concentration patterns and temporal dynamics at national and metropolitan scales. Spatial accident hotspots are identified using Density-Based Spatial Clustering of Applications with Noise (DBSCAN), enabling the detection of high-risk zones without imposing assumptions on cluster shape or size. This analysis reveals strong spatial concentration of accidents, with a limited number of clusters accounting for a substantial proportion of fatalities and injuries. Complementary temporal analysis is conducted using a multi-model ensemble framework to examine accident trends and seasonal patterns. This approach integrates SARIMA for linear stochastic modeling and Prophet for additive trend analysis, alongside two Long Short-Term Memory (LSTM) architectures: a direct 12-month vector output and a recursive horizon-3 model. By synthesizing these statistical and neural network-based methods through inverse-RMSE weighting, the study captures both stable seasonal cycles and non-linear, short-to-medium-term variations in accident frequency. Results show that traffic accidents in Ecuador exhibit stable diurnal and seasonal structures, alongside pronounced spatial heterogeneity across urban regions. The combined spatial and temporal insights provide a coherent representation of accident risk patterns, facilitating the prioritization of critical zones and high-risk periods. The resulting hotspot maps and multi-model forecasting horizons offer actionable information for smart city stakeholders, supporting targeted infrastructure interventions, adaptive enforcement strategies, and data-informed urban mobility policies. This work contributes to the broader understanding of traffic safety analytics as a core component of smart city decision-support systems. Full article

In the classical Stochastic Subspace Identification (SSI) method, mode selection is primarily based on frequency stability, damping stability, and mode shape similarity using the Modal Assurance Criterion (MAC). However, these criteria are often insufficient for reliable modal identification in high-noise environments. This study advances beyond the classical approach by introducing a multi-criteria optimization framework for mode evaluation. In addition to the conventional frequency and damping assessments utilized in the classical SSI method, the proposed approach incorporates a range of supplementary structural metrics. These include Density, Cosine Similarity Difference (CSD), Damping Stability (DS), Spatial Roughness (SR), Mode Shape Complexity (MSC), Signal Energy Coherence (SEC), and Normalized Modal Difference (NMD). These metrics are computed within specifically optimized windows on the stabilization diagram. By integrating spatial, phase, and energy-based characteristics of mode shapes alongside traditional metrics such as the MAC, the method enables a more comprehensive and robust mode selection process that surpasses the limitations of relying solely on frequency and damping stability. Compared to the classical SSI, the optimized window approach provides a significant advantage by enabling the reliable selection of consistent modes by considering the continuity and multi-criteria coherence of modes across window transitions. As a result, the elimination of noise modes and the reliable separation of structural modes are established on a more systematic basis. To achieve this, a two-stage optimization strategy is implemented: the first stage determines the optimal frequency window width and minimum mode count threshold, while the second stage utilizes a Multi-Criteria Decision Making (MCDM) framework based on the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) algorithm to assign optimized weights to the structural metrics and rank the candidate windows accordingly. As a result, the ideal frequency window is identified based on its TOPSIS score and subsequently validated using the MAC, confirming that the selected window corresponds to reliable structural modes. The framework is validated using long-term in situ measurements from a Roller Compacted Concrete (RCC) dam operating under significant environmental and operational noise. The dataset comprises continuous, high-resolution (200 Hz) vibration recordings collected between 1 July 2023 and 30 October 2024. While the calendar duration is limited to several weeks, the uninterrupted 24 h measurements yield a high-density time-series dataset with substantial information content, enabling a statistically meaningful and robust evaluation of modal identification performance under real-world and noisy conditions. The results reveal that relying solely on traditional selection criteria such as pole density and the MAC can often lead to the identification of spurious modes, particularly in noisy environments. In contrast, the proposed TOPSIS-based multi-criteria decision-making framework incorporates a broader range of structural indicators, balancing frequency, damping, spatial, and energy-related metrics to enhance the consistency and reliability of mode selection. This approach proved effective even under high-noise conditions, successfully distinguishing true structural modes from artificial ones. Application of the TOPSIS method to RCC dam data revealed consistent fundamental frequencies at approximately 5–10 Hz, 10 Hz, and 15 Hz, confirming its robustness and suitability for complex structural monitoring tasks. Full article

Climate change and intensifying extreme weather events challenge plant adaptability, making the evaluation of adaptive potential imperative. This study aims to identify climatically stable habitats for Rhododendron dauricum, a nationally protected (Class II) shrub species in China. Species occurrence records were integrated with multiple environmental datasets, and habitat suitability was inferred using a maximum entropy model under current and future climate scenarios. The model outputs indicate that habitat suitability is primarily driven by temperature and moisture, vegetation plays a secondary role, and topographic and soil factors are less influential. Projections show a consistent contraction of suitable habitats, particularly in highly suitable areas, with stronger declines under higher emission scenarios and longer time horizons. Spatial patterns shift from continuous to fragmented distributions, with suitable habitats increasingly concentrated in the northeastern regions and northern mountain ranges. Core areas that remain suitable across scenarios are identified through multi-scenario consistency analysis, representing climatically stable regions. These areas should be prioritized for in situ conservation, while populations maintaining high suitability across scenarios may serve as candidate provenances for ex situ conservation and future landscape deployment. This study elucidates the adaptive potential of R. dauricum under future climate scenarios and identifies key environmental drivers, informing conservation, breeding, and climate-adaptive management. Full article

Remote sensing (RS) imagery often suffers from non-uniform atmospheric scattering, resulting in severe contrast degradation, detail blurring, and spectral distortion. While recent advanced State Space Models (SSMs) offer efficient long-range modeling, they frequently struggle with spectral–spatial coupling interference and lack explicit physical constraints, leading to over-smoothed textures and color biases in high-reflectance regions. In this paper, we propose PhysWave-SSN, a Physics-Inspired Frequency-Decoupled Network specifically designed for high-fidelity RS image dehazing. The architecture employs a task-adaptive frequency-specific screening strategy to effectively isolate structural details from atmospheric interference. Specifically, we first introduce a Frequency-Aware Selection Gate (FASG) that unifies adaptive channel screening with physical transmission estimation, enabling precise recalibration of frequency components. To bridge the gap between physical scattering principles and state space representation learning, we develop a Physics-Informed SSM (PI-SSM), where the discretization step size of Mamba is dynamically modulated by the estimated haze density. This mechanism allows the model to adaptively adjust its spatial receptive field according to local degradation levels, enhancing physical interpretability. Furthermore, a Luminance-Adaptive Fusion Module (LAFM) is presented to protect high-reflectance land covers and maintain spectral consistency. Extensive experiments on multiple RS datasets demonstrate that PhysWave-SSN achieves superior performance, notably attaining a maximum PSNR gain of 2.49 dB while ensuring high structural and spectral fidelity. Full article

Simulation technologies are widely used in the construction industry to analyze complex operations and evaluate project performance before physical construction begins. However, interpreting simulation outputs remains challenging due to the dynamic nature of construction activities and the difficulty of representing spatial and temporal changes using traditional numerical or textual outputs. To address these limitations, researchers increasingly integrate visualization technologies with construction simulation models to improve understanding, communication, and decision-making. Using the PRISMA methodology, this paper presents a systematic literature review of visualization technology applications in construction simulation during the building phase. A total of 118 relevant publications published between 2000 and 2023 are reviewed and analyzed. The findings reveal a strong relationship between visualization technologies and Building Information Modeling (BIM), Virtual Reality (VR), and game engine technologies. Autodesk Navisworks and Unity are identified as the most frequently used visualization platforms, with game engines showing increasing adoption in recent years due to their support for immersive and interactive environments. The reviewed studies are further categorized into six primary use cases: scheduling and planning, education and training, equipment management, safety management, workspace planning, and simulation validation and verification. The results also demonstrate increasing research interest in real-time visualization, AR/VR integration, and interactive simulation environments. Overall, the findings highlight the growing role of visualization technologies in improving construction project planning, communication, training, safety, and decision-making, while also identifying important future research directions related to interoperability, real-time interaction, and extensible visualization platforms. Full article

Background/Objectives: Delayed neurological deficits after decompressive craniectomy may improve after cranioplasty, but quantitative imaging markers for postoperative monitoring remain limited. This study evaluated diffusion tensor imaging analysis along the perivascular space (DTI-ALPS) as an exploratory diffusion-based marker of defect-referenced perivascular diffusivity asymmetry and examined its relationship with white matter microstructure. Methods: Forty-three adults undergoing first-time cranioplasty after decompressive craniectomy and thirty-four matched healthy controls underwent diffusion magnetic resonance imaging and neuropsychological assessment before cranioplasty; twenty-five patients were reassessed at 3 months. DTI-ALPS was quantified globally and according to defect laterality. The white matter microstructure was assessed using tract-based spatial statistics and automated fiber quantification. The associations between imaging measures and cognitive performance were also examined. Results: Global DTI-ALPS was significantly lower in patients than in controls both before cranioplasty and at 3-month follow-up, with no significant longitudinal increase. Defect-referenced hemispheric asymmetry persisted, with lower ALPS values on the affected side, and white matter abnormalities were widespread before cranioplasty and remained evident at follow-up. Associations between imaging measures and cognitive performance were not significant after multiple-comparison correction. Conclusions: DTI-ALPS may capture persistent defect-related hemispheric diffusion asymmetry after cranioplasty and provide complementary information to conventional white matter metrics. However, in patients with substantial postoperative anatomical and fiber-orientation changes, ALPS should be interpreted cautiously as an exploratory proxy of perivascular diffusivity rather than as a direct measure of glymphatic function or physiological recovery. Full article

We study underwater optical communication under photon-counting (Poisson) detection with realistic attenuation, background radiance, directionality, and pointing uncertainty. Information is embedded in (i) a temporal dictionary of pseudo-random noise (PRN) intensity sequences and (ii) an optional spatio-temporal extension, denoted SIM–TS (spatial-index modulation with temporal signaling), that combines temporal coding with spatial indexing across multiple transmit/receive apertures. For a fixed optical energy-per-symbol (photon budget), these structured waveforms increase observation dimensionality and improve maximum-likelihood separability under Poisson statistics. We present a layered modeling framework, derive the corresponding Poisson detection metrics, and use Monte Carlo evaluation to extract maximum range at a target symbol error rate. The results show that dimensional signaling provides a modest but repeatable gain in clear-water photon-limited regimes: at 100 kbps, SIM–TS increases the clear-water range from 593.8 m to 617.2 m at 450 nm (3.95%) and from 457.8 m to 473.4 m at 420 nm (3.41%) under fixed total power. In coastal water the gain falls below 1%, while in the 1 Gbps benchmark SIM–TS under fixed total power remains within about 2% of on–off keying (OOK) and the larger improvement under power combining is attributable primarily to increased photon budget. These rate–range trade-offs clarify when dimensional signaling yields practical gains and when attenuation, background, and misalignment dominate the link budget. Full article

As global energy demands rise and concerns about environmental sustainability intensify, renewable energy sources like solar photovoltaic (PV) systems have gained significant attention. An integrated approach is proposed, leveraging spatial analysis using Helioscope, a 3D solar design tool, incorporated with Geographic Information System (GIS) data. This study conducted a spatial analysis of Cape Peninsula University of Technology (CPUT) Bellville campus’s potential for renewable energy, and the results are promising. The research indicated that the campus has enough rooftop space to optimally place solar panels with a capacity of 7.8 megawatts, which is more than the campus’s total energy needs of 6.3 megawatts. This study identified 13,249 modules that can be optimally placed to achieve this. Full article

Understanding how staple-crop geography aligns with climate resources is important for food-security planning under climate change. Focusing on rice, winter wheat and maize in China from 2001 to 2020, this study constructed 1 km crop-abundance grids from annual 30 m crop-distribution data and integrated weighted centres of gravity (COGs), Standard Deviational Ellipses (SDEs), effective accumulated temperature and a Climate Resource Matching Index (CRMI) to evaluate crop migration, spatial-form change and matching with thermal, pluvial and radiant resource centres. Results show that rice exhibited the strongest northeastward migration, with a cumulative COG path of 448.9 km, but its CRMI declined markedly, indicating that thermal relaxation did not translate into coordinated multi-resource improvement. Winter wheat remained anchored in the Huang-Huai-Hai Plain, with adjustment mainly occurring through internal concentration and persistent moisture constraints. Maize showed expansion before 2015 followed by partial correction, and its CRMI trough in 2015 was robust under alternative weighting schemes. Overall, China’s staple-crop change represents a differentiated spatial reconfiguration rather than a uniform northward shift. Because these metrics are national-scale, the findings should inform crop zoning as broad spatial signals rather than direct local yield responses. Full article