Search Results (1,690)

We present frequency- and magnetic field-dependent measurements of the complex dielectric permittivity ε*(f, H) of a kerosene-based ferrofluid, containing Mn₀.₆Fe₀.₄Fe₂O₄ nanoparticles, over 0.8–5 GHz and static fields up to ~91 kA/m. The imaginary part, ${\epsilon }_F^{″}$, shows a peak at a characteristic frequency that shifts towards higher frequencies with increasing H, revealing a magnetic field-dependent relaxation process, interpreted using the Maxwell–Wagner–Sillars model. The dielectrophoretic extraction of nanoparticles was evaluated via the squared electric field gradient, and a threshold, ${\left(\nabla E^2\right)}_{\min }$, dependent on particle size was determined. Below that threshold, Brownian forces dominate, so the ferrofluid acts as a homogeneous dielectric. For this case, the Clausius–Mossotti factor (CM) was calculated for ferrofluid droplets in air and in water as a function of frequency and magnetic field. In air, CM exhibits modest but systematic magnetic field dependence, indicating a magnetically modulated dielectric response at GHz frequencies. In contrast, when water is used as the reference medium, CM remains negative and essentially independent of H across the entire frequency range, suggesting that the high permittivity of water masks the magneto-dielectric effects in the ferrofluid. These findings provide insight into the interplay between the magnetic field and the permittivity of ferrofluids, with implications for high-frequency applications. Moreover, using a λ/4 antenna connected to a network analyzer, the existence of the dielectrophoretic force acting on a ferrofluid-impregnated textile thread at microwave frequencies was experimentally demonstrated. Full article

Ground deformation is a major geohazard in many urban areas, requiring reliable monitoring and forecasting for hazard mitigation. Although multi-temporal InSAR enables high-resolution deformation monitoring, most prediction approaches rely on single-point modeling and fail to exploit spatial dependencies within deformation fields. This study proposes a spatiotemporally synchronous prediction framework for large-scale InSAR deformation fields, integrating sequence preprocessing, spatiotemporal modeling, and deformation pattern analysis. First-order differencing reduces sequence non-stationarity, while a patch-based encoder-decoder structure preserves spatial topology during dimensionality reduction. The core prediction model, built on PredRNNv2, captures the long-term spatiotemporal evolution of InSAR deformation sequences. In addition, independent component analysis (ICA) combined with K-means clustering identifies dominant deformation patterns and their geological associations. The framework is evaluated using synthetic datasets simulating multiple deformation mechanisms and Sentinel-1 InSAR time-series data over the Beijing Plain from 2015 to 2025. Results show that the model accurately captures deformation evolution and identifies transitions associated with groundwater regulation. These findings demonstrate the potential of deep spatiotemporal learning for large-scale InSAR deformation prediction and geohazard mechanism interpretation. Full article

Forecasting monthly precipitation in mountainous terrain poses challenges that push conventional deep learning approaches to their limits: convective processes operate locally while orographic effects span entire drainage basins. We compare three architecture families on precipitation prediction across the Colombian Andes: ConvLSTM (convolutional recurrent), FNO-ConvLSTM (spectral–temporal), and GNN-TAT (graph attention LSTM). Using CHIRPS v2.0 and SRTM topography for Boyacá department (61 × 65 grid, 3965 nodes), we evaluate 39 configurations across feature bundles (BASIC, KCE elevation clusters, and PAFC autocorrelation lags) and horizons from 1 to 12 months. GNN-TAT matches ConvLSTM accuracy ($R^2$: 0.628 vs. 0.642; RMSE: 82.29 vs. 79.40 mm) with 95% fewer parameters (∼98K vs. 2.1M). Across configurations, GNN-TAT produces a lower mean RMSE (92.12 vs. 112.02 mm; $p=0.015$) and a 74.7% lower variance. The explicit graph structure, with edges weighted by elevation similarity, appears to reduce sensitivity to hyperparameter choices. Pure FNO struggles with precipitation’s spatial discontinuities ($R^2=0.206$), though adding a ConvLSTM decoder recovers much of the lost skill ($R^2=0.582$). Elevation clustering improves GNN-TAT significantly ($p=0.036$) but not ConvLSTM, suggesting that feature design should match the spatial encoding paradigm. ConvLSTM achieves peak accuracy on local patterns; GNN-TAT provides robust predictions with interpretable spatial reasoning. These complementary strengths motivate stacking ensembles that combine grid-based and graph-based representations. Full article

Vegetation coverage is a critical indicator for assessing urban ecosystems and is essential for sustainable development. However, the evolution patterns and driving mechanisms of vegetation change at the urban agglomeration scale remain underexplored. This study used the Google Earth Engine (GEE) to compute the kernel Normalized Difference Vegetation Index (kNDVI) for the Beibu Gulf Urban Agglomeration (BGUA), an important emerging coastal urban cluster in southern China, from 2000 to 2022. Trend analysis was employed to examine spatiotemporal changes in kNDVI, and an interpretable machine learning framework was applied to quantify the nonlinear, spatially heterogeneous effects of environmental and anthropogenic drivers. The results show that (1) kNDVI showed a general increasing trend, with medium-to-high kNDVI predominating. Approximately 91.91% of the region maintained an improving trend, whereas vegetation degradation concentrated in the core urban areas. (2) The Categorical Boosting model demonstrated superior performance in predicting kNDVI compared to other machine learning models. (3) The SHAP analysis identified land cover, elevation, and nighttime lights as the primary determinants of kNDVI change. These factors exhibited significant spatial heterogeneity in their nonlinear effects. These findings provide theoretical insights and practical guidance for ecological planning and environmental management in urban agglomerations. Full article

The Guposhan ore field, located in the Nanling metallogenic belt, is well known for large-scale Sn-W mineralization genetically linked to the Late Jurassic Guposhan pluton. The Lisong pluton, a product of regional magmatism, occurs in the central part of the Guposhan ore field. However, the critical factors responsible for the absence of intensive Sn polymetallic mineralization in the Lisong pluton remain poorly understood. Our geochronological results show that the coarse-grained hornblende-bearing and hornblende-free biotite monzogranites of the Lisong pluton were emplaced at 162.9 ± 1.5 Ma and 162.2 ± 2.3 Ma, respectively, which are contemporaneous with the Guposhan pluton. Geochemically, these intrusions are characterized by high SiO₂, Al₂O₃, and total alkalis (K₂O + Na₂O), high Ga/Al ratios (3.09–3.69), and peraluminous compositions (A/CNK = 1.15–1.23), consistent with high K calc-alkaline A-type granites. Similar to the adjacent Guposhan pluton, the Lisong granites yield variable _εHf(t) values from −3.0 to 5.7, apatite ⁸⁷Sr/⁸⁶Sr ratios of 0.69747–0.71190, and old two-stage Hf model ages (T_DM2) of 0.85–1.40 Ga. These features suggest that the Lisong and Guposhan granites may share a common magma source involving mixing of crustal and mantle-derived melts. Apatite grains from the Lisong granites display negative Eu anomalies (δEu = 0.03–0.22) and near-normal to positive Ce anomalies (δCe = 0.99–1.07), which we interpret to reflect plagioclase fractional crystallization and reduced melt conditions, respectively. Bulk rock geochemistry and multi-element systematics of the Lisong granites indicate that they represent early-stage magmatic products. Their relatively low differentiation signatures were unfavorable for Sn enrichment and mineralization in the melt, which likely explains the lack of intensive Sn polymetallic mineralization in the Lisong pluton. Full article

Predictive Digital soil mapping (PDSM) in Eastern Amazonia faces challenges due to its environmental complexity, difficult access, and scarce legacy data. While legacy soil maps contain valuable tacit knowledge, updating them requires methods that can handle uncertainty. This study evaluates the integration of old soil maps with machine learning to update soil information in Tracuateua, Pará, with a specific focus on the performance of ensemble learning and the explicit incorporation of uncertainty metrics in soil mapping units under hydromorphic influence, which, in addition to being difficult to access, are influenced by complex pedogenetic processes. We combined 270 sampling points, equivalent to the total pixels that captured the variability of soil mapping units, with environmental covariates and historical data. Several algorithms were tested, including an ensemble approach, to predict mapping units and quantify uncertainty through entropy and confusion indices. The ensemble model demonstrated improved stability and reduced classification uncertainty compared to single models, particularly in challenging hydromorphic environments. Although accuracy gains were modest, the models captured soil–environment relationships, with climate (Tmean_22k), topographic (CNBL and altitude) and organism variables (LST) emerging as the main predictors. Spatialized uncertainty estimates, expressed through entropy and the confusion index, provide a practical decision-support tool for guiding field surveys and identifying areas of low mapping reliability. By explicitly transferring the pedologist’s mental model—encoded as tacit knowledge in legacy soil maps—into ensemble learning, this study presents a robust and transferable framework for updating soil maps in data-scarce tropical regions, balancing predictive performance, spatial consistency, and uncertainty-aware interpretation. Full article

Port-area hydrogen refueling stations face low-frequency but high-consequence events when high-pressure leaks ignite as jet fires in wind-exposed, constrained environments. This study develops a consequence-based framework coupling theoretical screening, CFD combustion analysis, and hazard zoning to support separation-distance setting and emergency planning. A jet-fire model estimates flame-impingement distances for multiple leak diameters, and a weighted multi-point radiation model predicts heat-flux fields, from which lethal and irreversible-injury zones are delineated using thresholds of 7 and 5 kW/m², respectively. To move beyond wind-free screening, steady reacting-flow CFD is conducted for a representative release under four ambient conditions, with 4.34 m/s adopted as the representative wind speed for the windy cases based on Ningbo Port conditions. Validation against a visible-flame correlation defined by T ≥ 1573 K shows a deviation of 6.99%. Results show that radiation footprints expand markedly with diameter, with lethal and injury distances scaling approximately linearly within the studied range. Under wind, near-ground hot-plume extents defined by T ≥ 388 K and T ≥ 582 K depend strongly on wind direction and station geometry, whereas visible flame length is less sensitive. Additional sensitivity analyses indicate that the quasi-steady results are weakly affected by the selected ignition snapshot, while inclined releases modify projected plume/flame extents without altering the main engineering interpretation of the baseline case. The results support theory-based preliminary screening, but wind direction should be explicitly considered in exclusion-zone definition. Full article

Green hydrogen is a key energy carrier for industrial decarbonization; however, its large-scale deployment requires the optimization of production routes from both energetic and economic perspectives. In this study, green hydrogen production via biomass gasification and water electrolysis is comparatively evaluated using a multi-objective optimization framework based on the Differential Evolution Tabu List (DETL) algorithm. The optimization simultaneously maximizes hydrogen production while minimizing specific energy consumption and total annualized cost, explicitly capturing the trade-offs between competing technologies. Results indicate that biomass gasification outperforms water electrolysis in both energetic and economic terms. The optimal gasification configuration achieves 3625.95 kg/h of H₂ with a specific energy consumption of 39.63 kWh/kg H₂ and a total annualized cost of 2.45 MUSD/yr, whereas water electrolysis reaches 3156.78 kg/h of H₂ with 68.7 kWh/kg H₂ and a cost of 3.72 MUSD/yr. To support the interpretation of results, K-means clustering is integrated into the methodological framework, enabling the identification of representative regions within the Pareto fronts. Overall, biomass gasification provides more balanced and flexible solutions, highlighting its potential as a competitive route for sustainable hydrogen production. Full article

Differentiating AI-generated, real, or imitated artworks is becoming a tedious and computationally challenging problem in digital art analysis. AI-generated art has become nearly indistinguishable from human-made works, posing a significant threat to copyrighted content. This content is appearing on online platforms, at exhibitions, and in commercial galleries, thereby escalating the risk of copyright infringement. This sudden increase in generative images raises concerns like authenticity, intellectual property, and the preservation of cultural heritage. Without an automated, comprehensible system to determine whether an artwork has been AI-generated, authentic (real), or imitated, artists are prone to the reduction of their unique works. Institutions also struggle to curate and safeguard authentic pieces. As the variety of generative models continues to grow, it becomes a cultural necessity to build a robust, efficient, and transparent framework for determining whether a piece of art or an artist is involved in potential copyright infringement. To address these challenges, we introduce ArtUnmasked, a practical and interpretable framework capable of (i) efficiently distinguishing AI-generated artworks from real ones using a lightweight Spectral Artifact Identification (SPAI), (ii) a TagMatch-based artist filtering module for stylistic attribution, and (iii) a DINOv3–CLIP similarity module with patch-level correspondence that leverages the one-shot generalization ability of modern vision transformers to determine whether an artwork is authentic or imitated. We also created a custom dataset of ∼24K imitated artworks to complement our evaluation and support future research. The complete implementation is available in our GitHub repository. Full article

Traditional concert-hall evaluations primarily rely on ISO 3382-1 scalar parameters (e.g., C₅₀ and C₈₀), which summarize temporal energy behavior but provide limited insight into the directional composition of early reflections, particularly in geometrically shadowed seating zones. This paper presents a first-order Ambisonics (FOA)-based 3D acoustic sensing framework to diagnose under-balcony directional imbalance, with emphasis on early vertical-reflection deficiency. Scene-based FOA impulse responses (WXYZ) were measured at 11 audience positions (P1–P11) in the National Concert Hall (Taipei) and analyzed using intensity-based direction-of-arrival (DoA) proxies, axis-resolved directional energy build-up, and a distributional descriptor based on directional spatial entropy. Results are presented at three representative frequencies (125 Hz, 1 kHz, and 4 kHz) and analyzed within full (0–200 ms), early (0–80 ms), and late (80–200 ms) windows. While the magnitude proxy $\mid p^{meas}\left(f\right)\mid$ exhibits strong seat-to-seat variability and does not support a uniform attenuation assumption under the balcony, direction-resolved metrics reveal a consistent under-balcony signature. Specifically, the early–late vertical energy discrepancy $\Delta R_z={\displaystyle R_z^{early}}-{\displaystyle R_z^{late}}$ is persistently negative at under-balcony positions (P7–P11) across all three frequencies, indicating a selective reduction in early vertical contribution relative to the late field. Directional entropy analysis further shows predominantly negative $\Delta H_n={\displaystyle H_n^{early}}-{\displaystyle H_n^{late}}$, with more negative values in the under-balcony group, consistent with stronger early directional constraint in shadowed seats. Spatial trend maps are provided via Gaussian RBF interpolation within the audience domain for visualization only. The proposed FOA-based diagnostic framework provides a practical and physically interpretable approach to identify direction-specific early-reflection deficits that remain masked in conventional scalar evaluations, supporting mechanism-oriented assessment and targeted intervention in geometrically constrained listening areas. Full article

The core component to ensure the refined and safe operation of distribution network scheduling is 10 kV bus load probabilistic prediction. However, existing probabilistic prediction methods suffer from insufficient dynamic feature extraction and compromised prediction reliability caused by quantile crossing. To address these issues, this paper proposes a 10 kV bus load probabilistic prediction method integrating multi-value quantile regression (MQR) and a temporal fusion ensemble learning model (ELM). Firstly, a temporal fusion ensemble learning model is constructed, which integrates multiple temporal fusion network (TFN) sub-models through a stacking framework to parallel extract multi-dimensional temporal features of loads, effectively enhancing its feature capture capability for complex load data. Secondly, MQR is introduced as the core objective function to synchronously generate multi-quantile load forecasting results, comprehensively depicting the load probability distribution. Finally, a Listwise Maximum Likelihood Estimation (ListMLE) ranking constraint mechanism is embedded, which optimizes quantile ordering through monotonicity constraints, significantly reducing the degree of quantile crossing and improving the interpretability of forecasting results. The results show that the MQR-ELM algorithm achieves a Prediction Interval Coverage Probability of 94.624% (close to the nominal coverage rate of 95%), a Prediction Interval Averaged Width of 588.526, a Crossing Degree Index of only 0.0476, and a Continuous Ranked Probability Score as low as 84.931. All core indicators are significantly superior to those of the comparative algorithms. Full article

This study addresses the gap between predictive optimization and monitoring-oriented risk concentration by introducing a hierarchical Fuzzy Cognitive Map (FCM) framework for financial risk assessment. Financial distress prediction models are employed to estimate firm-level default probabilities and are required to comply with regulatory standards. IFRS 9 and Basel III/IV frameworks emphasize model explainability, scenario analysis and causal transparency, which are essential for compliance purposes. The methodology aggregates correlated financial ratios into financial concepts through unsupervised clustering. Concepts interact through a learned coupling matrix and a controlled multi-step propagation, which enables the amplification of risk signals. A small residual correction is applied at the final readout, preserving the interpretability of the proposed framework. The framework was applied to two severely imbalanced benchmark bankruptcy datasets. It achieved higher precision–recall performance than Logistic Regression (PR–AUC $\approx 0.32$ vs. $0.27$), improved calibration (Brier score $\approx 0.046$ vs. $0.089$) and maintained competitive Recall@Top–K under tight supervisory monitoring budgets. Hierarchical FCM achieved predictive performance comparable to nonlinear models while maintaining concept-level interpretability. Our findings demonstrate that structured concept aggregation combined with interaction-based propagation provides a transparent alternative to purely predictive black-box models in financial distress assessment and is aligned with regulatory frameworks. Full article

This study proposes a hybrid deep learning framework that integrates supervised classification and unsupervised profiling for electricity consumption analysis. In the supervised phase, a one-dimensional Convolutional Neural Network combined with Long Short-Term Memory (1D CNN–LSTM) architecture is developed to classify daily load patterns. The performance of the proposed model is compared with traditional machine learning and deep learning approaches, including Support Vector Machine (SVM), k-Nearest Neighbors (KNN), a standalone Long Short-Term Memory (LSTM) model, a Transformer-based model, and a standalone 1D CNN model. Experimental results on the Precon house dataset and the CU-BEMS dataset demonstrate that the proposed hybrid architecture outperforms the benchmark models, achieving classification accuracies of 87.59% and 86.40%, respectively. In the unsupervised phase, the trained CNN–LSTM encoder is utilized as a deep feature extractor. The resulting 32-dimensional latent embeddings are clustered using K-Means, Gaussian Mixture Model (GMM), Agglomerative, Spectral, and Ensemble methods. Clustering robustness is evaluated through bootstrap-based stability analysis using the Adjusted Rand Index (ARI) and the Normalized Mutual Information (NMI). The results demonstrate stable and interpretable electricity consumption profiles, particularly in the residential dataset, where near-perfect clustering stability is observed for K-Means. The proposed framework provides both improved classification performance and robust consumption profiling based on deep embedding, offering a practical tool for energy management. Full article

The Loess Plateau has experienced persistent vegetation greening over the past two decades, yet this recovery has occurred under a concurrent intensification of atmospheric evaporative demand and drying. This raises a key land–atmosphere question: which hydroclimatic processes most strongly constrain greening, and where do vegetation responses shift across environmental regimes? To address this issue, we integrated spatiotemporal trend analysis, Geographical Convergent Cross Mapping (GCCM)-based directional attribution, and an interpretable machine-learning framework combining Extreme Gradient Boosting (XGBoost) and SHapley Additive exPlanations (SHAP) to diagnose the dominant controls and threshold-like response patterns of vegetation activity. Using 1 km kernel Normalized Difference Vegetation Index (kNDVI) and eight hydroclimatic variables during 2000–2019, we found that regionally averaged kNDVI increased from 0.099 in 2000 to 0.164 in 2019, with a significant trend of 0.003 year⁻¹, and greening trends covered 65.503% of the Loess Plateau. Over the same period, Vapor Pressure Deficit (VPD) increased from 0.142 to 0.275 kPa (+0.133 kPa), indicating that vegetation recovery did not occur under a more humid atmospheric background. GCCM results consistently showed stronger directional influence from hydroclimatic drivers to kNDVI than the reverse, with evaporation and thermal conditions, especially Tmin, emerging as the dominant constraints, followed by Tmax, VPD, and wind speed, whereas precipitation showed comparatively weaker recoverable influence. The tuned XGBoost model achieved strong out-of-sample performance (R² = 0.9611, RMSE = 0.0188, MAE = 0.0131), and SHAP revealed clear nonlinear thresholds: evaporation and Tmin shifted into persistently positive contribution regimes beyond 302 mm and −17.6 °C, respectively; Tmax became predominantly inhibitory beyond −1.9 °C, and Palmer Drought Severity Index (PDSI) exhibited a multi-stage non-monotonic transition around −0.7. These results provide a coherent evidence chain linking directional influence, relative contribution, and threshold boundaries, offering quantitative support for identifying climate-sensitive zones and restoration risk regimes under continued warming and rising atmospheric dryness. Full article

Iron oxide–copper–gold (IOCG) deposits are widespread throughout the Carajás Province, Brazil, reflecting multiple Precambrian hydrothermal events. The Aquiri region is a relatively unexplored geological frontier in the northwestern Carajás Province. The AQW2 IOCG deposit is hosted by a Neoarchean mafic intrusive suite within metavolcano–sedimentary rocks. The pre-mineralization (Na and Na-K) and mineralization (Fe-Ca and Fe-P) hydrothermal stages appear as replacement fronts and as cement within ductile-deformed breccias. Late-mineralization (Fe-K, chlorite, and calcic-rich) assemblages occur in multidirectional veins controlled by brittle structures. Early- and main-mineralization apatite (Ap I-III) is enriched in F, Mn, and Sr, depleted in Y, shows unusually high Fe and Si (Ap III), and exhibits a pronounced positive Eu anomaly (Ap II). These characteristics indicate an alkaline fluid composition, substantial fluid–rock interaction, and episodic CO₂ degassing with the release of overpressured fluids, resulting in multiple brecciation events. A rapid decrease in temperature due to boiling is interpreted as a principal mechanism for copper precipitation. Late-mineralization apatite (Ap V–VI) is characterized by relatively higher Cl, Y, and LREE contents, lower Sr and Mn, and negative Eu-anomaly ratios, suggesting control by shallower paleostructures and more oxidizing conditions associated with the influx of basinal brines. These results highlight the evolution of the AQW2 deposit within a broader IOCG system and provide new insights into the metallogenic processes responsible for copper resources essential to the clean energy transition. Full article