Search Results (142)

While Graph Autoencoders (GAEs) have become a standard for unsupervised representation learning, their reliance on integer-order convolutions inherently restricts information propagation to immediate local neighborhoods. This paper introduces the Fractional Graph Autoencoder (FGAE) and its variational extension (FVGAE) to move beyond these local constraints. By integrating fractional Laplace operators, our framework generalizes conventional GAEs and enables tunable non-local propagation. We show that the fractional order $\alpha$ acts as a structural regularizer, utilizing the Green’s function of anomalous diffusion to induce a form of structural memory within the latent space. This allows the model to recover long-range dependencies that are typically lost in standard architectures. Systematic benchmarking across eight datasets—ranging from homophilic citation networks to heterophilic and dense product graphs—shows that these fractional variants consistently outperform both foundational and state-of-the-art baselines (ARGA, SIG-VAE, and GraphMAE). Notably, on the Amazon Computers and Citeseer datasets, our methods achieve relative increases in Normalized Mutual Information (NMI) of 77.55% and 67.28%, respectively. Statistical analysis confirms these gains are robust, with large effect sizes (Cohen’s $d>0.80$) and significance at $p<0.05$. These findings suggest that fractional graph autoencoding offers a mathematically grounded inductive bias for capturing the complex, multi-scale dynamics of real-world networked systems. Full article

This study presents a systematic investigation of nonlinear wave interactions in a (2+1)-dimensional nonlinear Schrödinger equation with a space–time-symmetric potential. We focus on the interaction dynamics of high-order line-soliton solutions and on the anomalous scattering phenomena exhibited by high-order lump solutions, which correspond to fully localized spatiotemporal optical wave packets. Using the generalized Darboux transformation, we obtain, for the first time, explicit high-order line-soliton solutions for this model. A rigorous asymptotic analysis framework is developed to characterize the behavior of these solutions on both long and short time scales. Furthermore, high-order lump solutions are constructed, and their decomposition and anomalous scattering properties are elucidated. This work provides new insights into complex wave dynamics in higher-dimensional integrable systems and their implications for multidimensional beam propagation in nonlinear optical media. Full article

Atmospheric refractivity governs the propagation behavior of electromagnetic waves in the lower troposphere. Accurate spatial characterization of this parameter is essential for optimizing communication, radar, and navigation systems. This study presents a geostatistical framework for generating high-resolution refractivity maps using Universal Kriging (UK) applied to meteorological observations from a dense network of automatic weather stations in the Galician region (NW Spain). The methodology explicitly models the non-stationary vertical structure of the atmosphere by decomposing the refractivity field into a deterministic altitude-dependent drift and a stochastic residual component characterized by an exponential variogram. Validation, performed using independent test stations bounding the regional vertical profile, demonstrates that the UK approach significantly outperforms Ordinary Kriging (OK). UK not only reduces mean errors and improves linear agreement, but critically minimizes systematic bias and extreme outlier occurrences ($P_{95}$). Beyond accurate spatial interpolation, the dynamically estimated vertical drift retrieves the macroscopic refractivity gradient, serving as a direct, real-time diagnostic tool to classify anomalous radio-frequency (RF) propagation regimes (e.g., super-refraction and ducting) and supporting robust decision-making in complex topographies. Full article

With the rapid exploitation of offshore wind energy in the Beibu Gulf (BG), understanding local low-level wind variability is essential for wind farm operations. This study examines the interannual relationships between the BG low-level winds in June and tropical sea surface temperature (SST) during 1993–2021 using multiple datasets. The meridional and zonal winds show negligible correlation on interannual time scales. Further analysis indicates that the meridional wind over the BG is significantly linked to the tropical Indian Ocean (TIO) and tropical Atlantic (TA) SST. The TIO warming is able to intensify the Western Pacific Subtropical High via eastward-propagating Kelvin waves, inducing southerly wind anomalies over the BG. In contrast, the TA warming modulates the Walker circulation and triggers westward-propagating Rossby wave trains, forming an anomalous Philippine anticyclone and associated southerly winds. The anomalous southerly winds associated with TIO (TA) warming are contributed by changes in both rotational and divergent wind components (primarily divergent wind component). Conversely, the zonal wind over the BG is significantly correlated with the tropical Pacific SST. The equatorial eastern Pacific warming excites westward-propagating Rossby waves, generating an anomalous anticyclone and resulting in westerly anomalies over the BG. Air–sea coupling links warm SST in the northwestern Pacific to a local anticyclonic circulation, forming easterly anomalies in the BG. Notably, the tropical SST associated zonal wind anomalies are primarily driven by rotational wind component. This study clarifies how tropical SST anomalies influence low-level winds over the Beibu Gulf and distinguishes the roles of rotational and divergent wind components, providing new insights into the predictability of local wind variability. Full article

Log anomaly detection in modern distributed systems is challenging. Anomalous behaviors are rare. Manual labeling is expensive. Session boundaries are often set by fixed heuristics before model training. This fixed-boundary assumption is problematic because segmentation errors propagate into representation learning and cannot be corrected during optimization. To address this, this paper proposes BASN (Boundary-Aware Sessionization Network), a boundary-aware contrastive learning framework that jointly learns session boundaries and anomaly representations using a differentiable soft-reset mechanism. BASN does not treat sessionization as a separate step. Instead, it predicts boundary probabilities from event semantics and temporal gaps, then modulates end-to-end session-state updates. The session representations are optimized with self-supervised contrastive learning, enabling effective zero-shot anomaly detection and few-shot adaptation. Experiments on four benchmark datasets (BGL, HDFS, OpenStack, SSH) show strong zero-shot performance (area under the receiver operating characteristic curve, AUROC 0.935–0.975) and boundary alignment with expert-validated proxy segmentation (boundary F1 0.825–0.877). Comparative gains over baselines are reported in the article after bibliography correction, baseline verification, and expanded statistical analysis. BASN is also computationally efficient, requiring less than 10 ms per session on a Graphics Processing Unit (GPU) and less than 45 ms on a Central Processing Unit (CPU). This is compatible with real-time inference needs in the evaluated settings. However, cross-system transfer AUROC (0.735–0.812) remains below in-domain performance. Domain-specific adaptation is still needed for deployment in environments that differ greatly from the training domain. Full article

Railway transport is increasingly promoted as a sustainable and low-carbon mode of transportation. However, track-induced vibration propagation remains a significant challenge, particularly in metro systems situated near residential areas, where vibrations can transmit through the infrastructure into nearby buildings, disturbing residents and damaging structures. This study aimed to evaluate the cause of the significantly different vibration impact on nearby buildings caused by two nominally identical adjacent slab tracks on a metro line in Austria. Controlled weight drop tests were carried out in both track directions, and accelerations were measured to characterize wave transmission and energy dissipation. The data were processed using frequency response functions and Short-Time Fourier Transform to extract time–frequency signatures, modal parameters, and propagation delays. A three-dimensional finite element model of the railway superstructure was then calibrated against the experimental modal properties and transfer functions and used to simulate cracking or stiffness loss in the sleeper–slab region. The simulations reproduced the observed increase in slab acceleration and underground strain energy, linking the anomalous vibration transmission to hidden stiffness loss rather than to global design differences. Overall, the study demonstrates that combining impact testing, advanced signal processing, and calibrated finite element modelling provides an effective framework for diagnosing track defects and guiding the design and maintenance of more sustainable, low-vibration urban rail infrastructure. Full article

Inspired by the remarkable collaborative echolocation mechanisms of dolphin pods, the paper addresses the challenge of achieving high-precision cooperative positioning for clusters of unmanned underwater vehicles (UUVs) in complex marine environments. Cooperative positioning systems for UUVs typically rely on acoustic ranging information to correct positional errors. However, the propagation characteristics of underwater acoustic signals are susceptible to environmental disturbances, often resulting in non-Gaussian, heavy-tailed distributions of ranging noise. Additionally, the strong nonlinearity of the system and the limited observability of measurement information further constrain positioning accuracy. To tackle these issues, this paper innovatively proposes a Factor Graph-based Adaptive Cooperative Positioning Algorithm (FGAWSP) suitable for heavy-tailed noise environments. The method begins by constructing a factor graph model for UUV cooperative positioning to intuitively represent the probabilistic dependencies between system states and observed variables. Subsequently, a novel factor graph estimation mechanism integrating adaptive weights with the product algorithm is designed. By conducting online assessment of residual information, this mechanism dynamically adjusts the fusion weights of different measurements, thereby achieving robust handling of anomalous range values. Experimental results demonstrate that the proposed method reduces positioning errors by 22.31% compared to the traditional algorithm, validating the effectiveness of our approach. Full article

Tropical cyclones typically weaken rapidly during poleward propagation due to decreasing sea surface temperatures and increasing vertical wind shear. Super Typhoon Oscar (1995) deviated from this pattern by maintaining Category-5 intensity at an anomalously high latitude. This study investigates the oceanic mechanisms driving this resilience by integrating satellite SST data with atmospheric (ERA5) and oceanic (HYCOM) reanalysis products. Our analysis shows that the storm track intersected a persistent marine heatwave (MHW) characterized by a deep thermal anomaly extending to approximately 150 m. This elevated heat content formed a strong stratification barrier at the base of the mixed layer (~32 m) that prevented the typical entrainment of cold thermocline water. Instead, storm-induced turbulence mixed warm subsurface water upward to effectively mitigate the negative cold-wake feedback. This process sustained extreme upward enthalpy fluxes exceeding 210 W m⁻² and generated a regime of thermodynamic compensation that enabled the storm to maintain its structure despite an unfavorable atmospheric environment with moderate-to-strong vertical wind shear (15–20 m s⁻¹). These results indicate that the three-dimensional ocean structure acts as a more reliable predictor of typhoon intensity than SST alone in regions affected by MHWs. As MHWs deepen under climate warming, this cold-wake mitigation mechanism is likely to become a significant factor influencing future high-latitude cyclone hazards. Full article

In cloud-based distributed systems, trace anomaly detection plays a vital role in maintaining system reliability by identifying early signs of performance degradation or faults. However, existing methods often fail to capture the complex temporal and structural dependencies inherent in trace data. To address this, we propose a novel dual-branch Transformer-based framework that integrates both temporal modeling and causal reasoning. The first branch encodes the original trace data to capture direct service-level dynamics, while the second employs phase-space reconstruction to reveal nonlinear temporal interactions by embedding time-delayed representations. To better capture how anomalies propagate across services, we introduce a causal propagation module that leverages directed service call graphs to enforce the time order and directionality during feature aggregation, ensuring anomaly signals propagate along realistic causal paths. Additionally, we propose a hybrid loss function combining the reconstruction error with symmetric Kullback–Leibler divergence between attention maps from the two branches, enabling the model to distinguish normal and anomalous patterns more effectively. Extensive experiments conducted on multiple real-world trace datasets demonstrate that our method consistently outperforms state-of-the-art baselines in terms of precision, recall, and F1 score. The proposed framework proves robust across diverse scenarios, offering improved detection accuracy, and robustness to noisy or complex service dependencies. Full article

Anomaly detection in safety-critical systems often operates under severe label constraints, where only a small subset of normal and anomalous samples can be reliably annotated, while large unlabeled data streams are contaminated and high-dimensional. Deep one-class methods, such as deep support vector data description (DeepSVDD) and deep semi-supervised anomaly detection (DeepSAD), address this setting. However, they treat samples largely in isolation and do not explicitly leverage the manifold structure of unlabeled data, which can limit robustness and interpretability. This paper proposes Anomaly-Aware Graph-based Semi-Supervised Deep Support Vector Data Description (AAG-DSVDD), a boundary-focused deep one-class approach that couples a DeepSAD-style hypersphere with a label-aware latent k-nearest neighbor (k-NN) graph. The method combines a soft-boundary enclosure for labeled normals, a margin-based push-out for labeled anomalies, an unlabeled center-pull, and a k-NN graph regularizer on the squared distances to the center. The resulting graph term propagates information from scarce labels along the latent manifold, aligns anomaly scores of neighboring samples, and supports sample-level interpretability through graph neighborhoods, while test-time scoring remains a single distance-to-center computation. On a controlled two-dimensional synthetic dataset, AAG-DSVDD achieves a mean F1-score of $0.88\pm 0.02$ across ten random splits, improving on the strongest baseline by about $0.12$ absolute F1. On three public benchmark datasets (Thyroid, Arrhythmia, and Heart), AAG-DSVDD attains the highest F1 on all datasets with F1-scores of $0.719$, $0.675$, and $0.8$, respectively, compared to all baselines. In a multi-sensor fire monitoring case study, AAG-DSVDD reduces the average absolute error in fire starting time to approximately 473 s (about 30% improvement over DeepSAD) while keeping the average pre-fire false-alarm rate below $1\%$ and avoiding persistent pre-fire alarms. These results indicate that graph-regularized deep one-class boundaries offer an effective and interpretable framework for semi-supervised anomaly detection under realistic label budgets. Full article

Time-fractional interface problems arise in systems where interacting materials exhibit memory effects or anomalous diffusion. These models provide a more realistic description of physical processes than classical formulations and appear in heat conduction, fluid flow, porous media diffusion, and electromagnetic wave propagation. However, the presence of complex interfaces and the nonlocal nature of fractional derivatives makes their numerical treatment challenging. This article presents a numerical scheme that combines radial basis functions (RBFs) with the finite difference method (FDM) to solve time-fractional partial differential equations involving interfaces. The proposed approach applies to both linear and nonlinear models with constant or variable coefficients. Spatial derivatives are approximated using RBFs, while the Caputo definition is employed for the time-fractional term. First-order time derivatives are discretized using the FDM. Linear systems are solved via Gaussian elimination, and for nonlinear problems, two linearization strategies, a quasi-Newton method and a splitting technique, are implemented to improve efficiency and accuracy. The method’s performance is assessed using maximum absolute and root mean square errors across various grid resolutions. Numerical experiments demonstrate that the scheme effectively resolves sharp gradients and discontinuities while maintaining stability. Overall, the results confirm the robustness, accuracy, and broad applicability of the proposed technique. Full article

The evaporation duct, formed above the ocean surface by sharp vertical gradients of humidity, would significantly influence electromagnetic wave propagation. It is a quasi-permanent feature over the sea, and its strength is quantified by the evaporation duct height (EDH). While previous studies have focused on how local factors influence evaporation ducts, the impact of El Niño–Southern Oscillation (ENSO) on EDH in the South China Sea (SCS) remains undocumented. Using correlation analysis, empirical orthogonal function (EOF) decomposition, and wavelet transform, this study shows that evaporation is the dominant environmental factor controlling EDH variability across seasonal and inter-annual timescales in the SCS, while wind speed and relative humidity play secondary roles with contrasting effects between the northern and southern regions. ENSO drives the inter-annual variability of EDH by modulating evaporation. During El Niño events, anomalous anticyclonic circulations near the Philippine Sea, which weaken (strengthen) the evaporation in the northern (southern) SCS, alter EDH and contribute to the formation of the meridional dipole structure, particularly within the 2-to-6-year ENSO band. These results provide new insights into the mechanisms controlling EDH in the SCS and highlight the critical role of ENSO in shaping its spatial distribution. Full article

Under the global imperative for climate action and sustainable development, accelerating the transition towards high-penetration renewable energy systems remains a universal priority, central to achieving the United Nations Sustainable Development Goals. However, the inherent uncertainty and volatility of renewables such as wind and solar PV pose fundamental challenges to power system stability and flexibility worldwide. These challenges, if unaddressed, could significantly hinder the reliable and sustainable integration of clean energy on a global scale. While pumped storage hydropower (PSH) represents a mature, large-scale solution for enhancing system regulation capabilities, existing planning methodologies frequently suffer from critical limitations. These included oversimplified scenario representations—particularly the inadequate consideration of escalating extreme weather events under climate change—and computational inefficiencies in solving large-scale stochastic optimization models. These shortcomings ultimately constrained the practical value of such approaches for advancing sustainable energy planning and building climate-resilient power infrastructures globally. To address these issues, this paper proposed a bi-level stochastic planning method integrating scenario optimization and improved Benders decomposition. Specifically, an integrated framework combining affinity propagation clustering and isolation forest algorithms was developed to generate a comprehensive scenario set that covered both typical and anomalous operating days, thereby capturing a wider range of system uncertainties. A two-layer stochastic optimization model was established, aiming to minimize total investment and operational costs while ensuring system reliability and renewable integration. The upper layer determined PSH capacity, while the lower layer simulated multi-scenario system operations. To efficiently solve the model, the Benders decomposition algorithm was enhanced through the introduction of a heuristic feasible cut generation mechanism, which strengthened subproblem feasibility and accelerated convergence. Simulation results demonstrated that the proposed method achieved a 96.7% annual renewable energy integration rate and completely avoided load shedding events with minimal investment cost, verifying its effectiveness, economic efficiency, and enhanced adaptability to diverse operational scenarios. Full article

Electricity theft is a major source of non-technical losses in distribution networks, threatening both economic revenues and power supply reliability. This study addresses the identification of nodes exhibiting anomalous load behavior (anomalous nodes) in 10 kV distribution feeders. Based on the IEEE-33 bus benchmark system, the disturbance patterns induced by abnormal consumption are analyzed. The results show that voltage and current fluctuations intensify with increasing electrical distance from the power source, while branch loss peaks localize at the affected terminals and propagate unidirectionally along the power flow path. Building on these findings, an improved density-based spatial clustering of applications with noise (DBSCAN) method is proposed, integrating five spatial network features and sixteen temporal electrical features extracted from voltage, current, and power series. Prior to clustering, the features are standardized and reduced via principal component analysis (PCA), retaining over 90% of the cumulative variance. Validation on a hybrid dataset demonstrates that the proposed method achieves 90.7% accuracy, 87.5% recall, and an F1-score of 0.895, outperforming traditional K-means and approaching supervised CNN models without requiring labeled data. These results confirm the method’s robustness and suitability for practical deployment in distribution networks. Full article

Nonlocal models offer a unified framework for describing long-range spatial interactions and temporal memory effects. The review briefly outlines several representative physical problems, including anomalous diffusion, material fracture, viscoelastic wave propagation, and electromagnetic scattering, to illustrate the broad applicability of nonlocal systems. However, the intrinsic global coupling and historical dependence of these models introduce significant computational challenges, particularly in high-dimensional settings. From the perspective of algorithmic strategies, the review systematically summarizes high-dimensional numerical methods applicable to nonlocal equations, emphasizing core approaches for overcoming the curse of dimensionality, such as structured solution frameworks based on FFT, spectral methods, probabilistic sampling, physics-informed neural networks, and asymptotically compatible schemes. By integrating recent advances and common computational principles, the review establishes a dual “problem review + method review” structure that provides a systematic perspective and valuable reference for the modeling and high-dimensional numerical simulation of nonlocal systems. Full article