Search Results (24)

Soil ecosystems generate a wide variety of biological and physical sounds, yet the temporal organization of soil acoustic environments remains poorly understood. This study investigated seasonal and daily dynamics of soil acoustic activity using continuous recordings collected over an entire calendar year at four soil stations subjected to different vegetation management regimes. Custom-built piezoelectric probes were used to record vibrations within the upper soil layer. Two complementary analytical approaches were applied. Conventional Acoustic Features (Root Mean Square, Zero Crossing Rate, Spectral Centroid, Spectral Bandwidth, Spectral Entropy, and Mel-Frequency Cepstral Coefficients) were used to characterize monthly and solar-phase variability, whereas Sonic Heterogeneity Indices (SHI_ft and SHI_tf) were employed to investigate seasonal organization and climatic forcing. Climatic variables and solar phases were analyzed using correlation analyses, clustering procedures, machine learning models, and seasonal and sinusoidal frameworks. Acoustic Features revealed a clear seasonal organization, with winter and early spring months forming coherent acoustic regimes across most stations. Responses to solar phases were detectable but strongly dependent on local site conditions. SHI_ft and SHI_tf metrics showed higher heterogeneity during autumn and winter than during spring and summer. Climatic variables emerged as important drivers of acoustic heterogeneity, while sinusoidal models generally described annual SHI_tf dynamics better than conventional seasonal classifications. These findings indicate that soil acoustic environments are structured by interacting seasonal, climatic, and astronomical processes operating across multiple temporal scales and support the development of soil ecoacoustics as a non-invasive tool for investigating ecosystem functioning. Full article

Soil quality is a critical factor impacting agricultural productivity and ecosystem functions. Accurate assessment of soil quality is crucial for sustainable agricultural development. Xinjiang is the primary cotton-producing region in China. Its unique geographical condition, characterized by two basins surrounded by three mountains, results in distinct climatic conditions, soil-forming factors, and soil physical and chemical properties across different cotton-growing areas. The spatial differentiation patterns of soil quality and their primary factors in cotton-growing regions of different river basins are not yet fully understood. This study focused on four typical cotton-growing areas of Xinjiang, China. A total of 1588 plow-layer soil samples were collected, and 21 indicators covering soil physical, chemical, and environmental properties were measured. By constructing a minimum data set (MDS) and comparing the performance of linear (LS) and non-linear (NLS) scoring functions, the effects of geographical environmental factors on the spatial distribution patterns of soil quality in cotton fields of different basins were analyzed. The results showed the MDS, composed of data on soil bulk density and the contents of organic matter, available iron, available zinc, nickel, sand, and silt, could replace the total data set. The NLS-MDS was identified as the optimal assessment model. Its Nash–Sutcliffe efficiency coefficient (E_f = 0.84) and coefficient of determination (R² = 0.70) were both higher than those of the linear model (E_f = 0.79, R² = 0.66). The study also revealed significant spatial heterogeneity in soil quality across different cotton-growing areas. The average soil quality index (SQI) in the Aksu River Basin (SQI_NLS-MDS = 0.53) and Xiaohaizi Basin (SQI_NLS-MDS = 0.50) was significantly higher than that in the Kuitun River Basin (SQI_NLS-MDS = 0.44) and Manas River Basin (SQI_NLS-MDS = 0.41). Random forest analysis demonstrated that the relative importance of topographic (digital elevation model) and climatic factors (annual mean temperature, annual mean precipitation) on SQI was higher than that of the vegetation factor (normalized difference vegetation index). The strong interaction between topographic and climatic factors was the primary driver of the spatial distribution of soil quality. This study confirms significant spatial heterogeneity of soil quality in cotton fields across different river basins in Southern and Northern Xinjiang, and identifies the synergistic interaction between topographic and climatic factors as the dominant driver of this heterogeneity in arid regions. These findings provide a scientific basis for implementing site-specific agricultural management in arid regions. Full article

Ammonium nitrogen (NH₄⁺-N) contamination in groundwater beneath chemical industrial parks exhibits extreme spatial heterogeneity, yet the comparative effectiveness of spatial prediction methods under such conditions remains poorly understood. At a chemical industrial park in a region of Shanxi Province, northern China, we analyzed 133 monitoring wells sampled across four campaigns (April–October 2024) at two aquifer depths. Global Moran’s I (0.040–0.118) and variogram nugget ratios (>75%) indicated weak spatial autocorrelation. Consequently, on the raw concentration scale, all six geostatistical methods yielded near-zero or negative leave-one-out cross-validation (LOO-CV) R². Evaluated on the log₁₀ scale, machine learning (ML) models achieved positive predictive skills, with Extreme Gradient Boosting (XGBoost) performing best (R² ≈ 0.75). Three hybrid ML–kriging methods produced physically coherent plume surfaces while retaining their predictive skills; the April upper-layer result (R² ≈ 0.67)—the only campaign without retained within-well information—best represents spatial generalization, whereas the higher later-campaign values (R² > 0.97) are optimistic. Exceedance probability mapping based on XGBoost (area under the ROC curve, AUC = 0.959) revealed a persistent high-risk zone. Because the geostatistical and ML metrics span different response scales and validation schemes, their comparison is indicative rather than a direct ranking. Spatial autocorrelation diagnostics should precede method selection at point-source-dominated industrial sites. Full article

Ground-penetrating radar (GPR) and electrical resistivity tomography (ERT) are physically complementary non-destructive evaluation methods for reinforced concrete, yet their integrated diagnostic use has been limited by the absence of controlled, ground-truth-validated calibration of the joint-signature space. This paper presents a laboratory calibration programme in which a single C30/37 reinforced concrete beam (3000 mm × 300 mm × 200 mm, three T12 bars at 35 mm cover, CEM I 42.5N, w/c = 0.50) was sequentially conditioned through four controlled deterioration states—intact reference (Model A), water-filled saw-cut crack (Model B), full saturation by seven-day top-surface ponding (Model C), and chloride-induced active corrosion (Model D). Seven RES2DINV inverted ERT sections at three electrode spacings (a = 7, 15, and 30 mm) and three 800 MHz GPR profiles were acquired across the four known ground-truth conditions. The intact-reference resistivity ρ₀ = 558 Ω·m (full-section median of the mlab dataset at a = 7 mm) and GPR-calibrated velocity v = 0.095 ± 0.008 m/ns (from hyperbola fitting at 35 mm rebar cover) establish the absolute baselines. The four conditions produce systematically distinct joint signatures: Model A exhibits uniform high resistivity with clean rebar hyperbolae and no anomalous reflections; Model B produces a localised ERT low-ρ anomaly (ρ_min = 1.46 Ω·m) co-located with a negative-polarity (R = −0.68) GPR crack-mouth reflection confirming water-fill; Model C produces pervasive low-ρ with a smooth depth gradient and 50–65% GPR amplitude attenuation (−6.0 to −9.1 dB); Model D produces the same bulk GPR signatures as Model C but with a critically different ERT spatial texture—a heterogeneous near-surface layer above a sharp boundary at z ≈ 40 mm with depth-preferential low-ρ concentrated at rebar level. This depth-preferential signature, quantified here by a reproducible Depth-Preferential Index (DPI), is the primary ERT-only diagnostic criterion distinguishing active corrosion from pervasive saturation. For the Model C versus Model D distinction, the GPR response is non-discriminating; this high-risk distinction is resolved exclusively by the ERT depth-preferential criterion. The calibration demonstrates that GPR and ERT are physically non-redundant in the strict sense: neither method alone can unambiguously discriminate all four states, but their combination yields correct classification within the controlled laboratory conditions and subject to the stated qualification conditions. The corrosion state was confirmed at the regime level (chloride above the depassivation threshold, under accelerated polarisation) but was not quantified electrochemically, so the depth-preferential signature is interpreted as an indirect spatial proxy for active corrosion rather than a measurement of corrosion rate. Seven failure modes are quantitatively characterised and embedded in the framework as a priori qualification conditions. The calibrated reference values (ρ₀, A₀, Stage 2 thresholds, depth-preferential criterion) are specific to the laboratory mix and curing history and require local Stage 1 recalibration for field application. Full article

Reliable state estimation is essential for the secure and efficient operation of sustainable energy systems, especially under the increasing integration of renewable energy, distributed resources, and heterogeneous sensing devices. However, in practical power systems, SCADA, PMU, and AMI measurements often have different sampling rates, accuracies, communication delays, and availability levels, which makes reliable data completion and multi-source fusion difficult. This paper focuses on the state estimation problem of renewable-integrated distribution networks under multi-source heterogeneous measurement conditions. In such distribution networks, the increasing penetration of distributed renewable energy resources and the joint deployment of multiple measurement devices, including SCADA, PMU, and AMI, may lead to incomplete measurements, asynchronous sampling, differences in measurement accuracy, and reduced system observability. To address these issues, this paper proposes a model-based digital twin reference-guided physics-constrained DDPM framework to improve the quality of missing-measurement completion and the reliability of state estimation in distribution-network scenarios. A four-layer simulation-oriented cyber–physical framework is first constructed to integrate physical sensing, model-based digital twin reference mapping, AI-based measurement completion, and state estimation feedback. Within this framework, a physics-constrained self-supervised denoising diffusion probabilistic model is developed to recover missing measurements by combining observed data, digital twin reference measurements, real-time topology information, and power system operational constraints. The completed pseudo-measurements and physical measurements are then fused through a credibility-aware weighting strategy that considers timeliness, data integrity, measurement accuracy, and virtual–real consistency verification under simulation settings. Simulation results on the IEEE 14-bus system show that the proposed method improves pseudo-measurement completion and supports more reliable voltage magnitude and phase angle estimation under different measurement configurations. Under the tested simulation settings and multi-source measurement configurations, the results indicate that the proposed method can improve pseudo-measurement completion and support more reliable voltage magnitude and phase angle estimation. However, its performance under frequent topology switching, high missing-data ratios, and complex abnormal data conditions remains to be further evaluated. Full article

Inter-turn insulation failure is the primary cause of dry-type air-core reactor burnout, yet early detection remains challenging due to weak power-frequency fault signatures. This paper proposes an integrated diagnostic framework combining impulse oscillation testing, electromagnetic simulation, and a physics-informed graph neural network. A scaled-down four-layer parallel reactor model and an impulse oscillation platform are developed to extract dynamic equivalent inductance and resistance as sensitive fault indicators. Validated finite element simulations reveal that inter-layer insulation near high-voltage terminals endures the highest electric field stress, with local field strength increasing nearly eightfold under short-circuit faults. For fault localization, a Spatio-Temporal Physics-Informed Graph Neural Network (ST-PIGNN) is constructed, representing winding topology as a heterogeneous graph and embedding electromagnetic transient equations as physical constraints. On a test set of 120 samples, the proposed method achieves 94.17% fault layer classification accuracy and 6.84% axial localization mean absolute error under low-noise conditions, and maintains 85.83% accuracy with 8.12% error under strong-noise interference. The proposed method is currently at the proof-of-concept stage, and further validation on full-scale reactors is required before field deployment. Full article

Accurate weather-regime classification is increasingly important for climate-sensitive decision-making in agriculture, aviation, disaster preparedness, and territorial planning, particularly in regions where strong climatic heterogeneity complicates conventional operational workflows. This study proposes a machine learning-based framework for broad-regime weather classification over Morocco using hourly METAR observations collected from 22 meteorological stations between July 2022 and February 2024. The proposed workflow integrates data cleaning, missing-value imputation, feature transformation, categorical encoding, class-imbalance handling, and model optimization under a leakage-safe experimental protocol. To preserve temporal integrity, observations were chronologically split into training, validation, and independent test subsets; SMOTE and random undersampling were applied exclusively to the training subset, whereas the validation and test subsets retained their original class distributions. Seven classifiers were evaluated, including XGBoost, LightGBM, CatBoost, Random Forest, Gradient Boosting, Support Vector Machine, and Logistic Regression, with hyperparameters optimized using Optuna. The results show that optimized boosting models are particularly effective for Moroccan station-based weather classification. XGBoost achieved the highest test-set accuracy of 95.1%, followed by LightGBM at 94.7% and CatBoost at 93.8%, with optimization improving accuracy by approximately 8–12 percentage points compared with baseline configurations. Because the dataset exhibits class imbalance, macro-averaged precision, recall, and F1-score were emphasized alongside accuracy to provide a more reliable assessment across weather classes. Confusion-matrix analysis indicates improved recognition of underrepresented regimes, especially Dust/Sand events, while residual confusion between Fog/Haze and Rain/Storm reflects both physical overlap and the limits of a four-class METAR taxonomy. Overall, the findings demonstrate that optimized ensemble learning can provide a robust, computationally efficient, and operationally relevant classification layer for regional meteorological decision support in Morocco, while future work should extend the framework to longer time series, finer weather taxonomies, and external regional validation. Full article

Accurate building performance forecasting is critical for the design and renovation of energy-saving structures, but existing methods face four key challenges: heterogeneous data fusion (sensor streams, design parameters, and environmental sequences), non-stationary physical time series, model interpretability, and sample efficiency (e.g., limited commissioning data). To address these challenges, this paper proposes Fusion-Grounded Forecasting (FGF), which is a framework integrating a gated adaptive fusion layer, deterministic trend-season decomposition, an additive predictor with component decomposition, and Bayesian regularization. This framework is designed for next-hour forecasting broadcast to hourly resolution using hourly sensor data and monthly design parameters. The dataset covers 36 months (approximately 25,920 h). In addition to the combination of existing modules, the novelty lies in the integrated architecture, in which interpretable constraints can adjust the fusion layer in both directions, with decomposition prediction alignment supporting component attributes. The framework is verified on a proprietary 36-month dataset from institutional buildings using standard prediction metrics (MAE, RMSE, MAPE, and directional accuracy) and ablation studies for comparison against 10 baselines: SARIMAX, GPR, LSTM, XGBoost, N-HiTS, Informer, Autoformer, NAM, a physics-informed hybrid, and TFT. FGF achieves a 3.1% MAPE and 92.5% directional accuracy in hourly cooling load forecasting. Ablation confirmed the contribution of each module: removing gated fusion increased the MAPE to 6.8%. Compared with manual feature engineering, the speed of the framework is increased by 1680 times, and the cost is reduced by 99.6%. The explanatory index (counterfactual reliability: 0.95; Stability of functional importance: 0.11) is in compliance with audit requirements. These results indicate that FGF connects descriptive physics with quantitative prediction. However, this study is limited to a single institutional building; transferability to residential, commercial, or industrial buildings requires further verification. While waiting for this verification, FGF has demonstrated its potential as a transparent and efficient tool to build performance models. Full article

Agricultural AI agents play a crucial role in the evolution of smart agriculture, from single-point automated applications to intelligent systems driven by tasks, collaborative decision-making, and closed-loop execution. However, their practical implementation still faces key challenges, such as heterogeneous agricultural data processing, insufficient cross-scenario generalization ability, complexity of multi-agent collaboration, difficulties in integrating software and hardware, and insufficient security and trust guarantees in real agricultural environments. This paper presents a systematic review of the architecture design, business processes, key technologies, and future challenges of agricultural AI agents. Agricultural AI agents are classified into two types: virtual agricultural AI agents and embodied agricultural AI agents. The paper summarizes a four-layer system architecture consisting of the infrastructure layer, agent management layer, agent collaboration layer, and application layer. The paper also analyzes the model capabilities required by agricultural AI agents from four typical business dimensions: perception and state understanding, knowledge memory and experience management, reasoning decision-making and task planning, and collaborative execution and resource scheduling. This research shows that technologies such as multimodal perception, knowledge graphs, retrieval-enhanced generation, digital twins, reinforcement learning, and multi-agent collaboration can provide important support for agricultural AI agents to enhance their environmental understanding, knowledge reuse, autonomous decision-making, and physical execution capabilities. Future research should focus on robust perception in open environments, long-term memory and knowledge evolution, reliable multi-agent collaboration, edge-cloud collaborative deployment, and secure and trustworthy human–machine collaboration. Integrating agricultural domain knowledge with intelligent agent technology is an important direction for promoting the large-scale, adaptive, and sustainable application of agricultural AI agents. Full article

Digital Twins (DTs) have emerged as a key technology for sensor-driven cyber–physical systems, enabling such features as real-time monitoring, predictive maintenance, and operational optimization. Despite rapid progress, existing research in the area remains fragmented, mostly addressing only singular aspects, such as data acquisition, modeling, or control, lacking a unified lifecycle-oriented methodology capable of integrating heterogeneous sensor infrastructures, hybrid analytical models, and continuous feedback mechanisms. This paper presents a comprehensive state-of-the-art review of Digital Twin technologies, focusing on sensor-centric architectures, data integration strategies, and hybrid modeling approaches. Based on the identified limitations, a novel Federated Digital Twin Lifecycle Model (F-DTLM) is proposed as a unifying framework for industrial applications. The model structures the DT lifecycle into four iterative phases—Definition and Scoping; Sensor Data and Infrastructure Federation; Hybrid Modeling and State Synchronization; and Operational Optimization and Closed-Loop Control, supported by cross-cutting layers addressing interoperability and governance. The integration of federated sensing infrastructures with hybrid physics-informed and data-driven models enables scalable synchronization between physical and digital systems. A comparative analysis and an illustrative predictive maintenance scenario illustrate the potential applicability of the proposed approach. Full article

To meet the demands for miniaturization, lightweight design, and high performance in modern electronic systems, advanced 3D TSV technology enables a substantial increase in storage capacity even within physically constrained form factors. This paper proposes a schematic design methodology and system-level integrated modeling approach for a four-layer stacked micro-module based on wafer-level packaging. By leveraging heterogeneous chip fan-out technology and TSV-based vertical stacking, the fabricated DDR3 micro-module achieves a compact footprint of 14 × 9 × 3.5 mm, a storage capacity of 4 GB, and a 64-bit bus width. Compared to conventional board-level mounting, the module reduces the footprint area by 95%. Following comprehensive multi-level testing, the micro-module fully complies with standard protocol requirements, enabling a paradigm shift in form factors for mobile computing devices while enhancing computational density and energy efficiency in data center server applications. Full article

Digital twins are increasingly used to support monitoring, prediction, and decision-making in complex cyber–physical systems; however, most existing digital twin implementations remain domain-specific, model-centric, and weakly integrated with human expertise. The aim of this study is to examine how digital twins can be designed as reusable cognitive architectures capable of consistent reasoning, semantic interpretation, and human-centered decision support across heterogeneous application domains. To achieve this aim, the paper proposes the reusable cognitive digital twin (RCDT) paradigm, which combines a reusable architectural core containing structural, behavioral, functional, and cognitive invariants with a cognitive orchestration layer implementing four coordinated reasoning modalities: structural, generative, analytical, and operational. The methodology is architectural and conceptual, supported by formal operator-based modeling and illustrated through two contrasting case studies—a safety-critical aviation system and a large-scale smart city environment. The results demonstrate that the same reusable cognitive modules and evaluation indices can be instantiated across both domains, enabling explicit management of semantic consistency, scenario adequacy, and decision confidence, as well as systematic integration of human expertise. These findings indicate that RCDTs provide a transferable and interpretable cognitive foundation for intelligent digital ecosystems, extending traditional digital twin capabilities beyond domain-bound and purely data-driven approaches. Full article

To address the practical engineering challenges of limited fault samples for high-voltage circuit breaker spring operating mechanisms and the inability of single features to fully reflect equipment status, this paper proposes a small-sample fault diagnosis method based on multi-source feature fusion and Stacking ensemble learning. First, a multi-source sensing system containing MEMS (Micro-Electro-Mechanical System) pressure and travel, coil, and motor current was constructed to achieve comprehensive monitoring of the mechanical and electrical states of a 220 kV circuit breaker; in particular, the introduction of non-invasive MEMS sensors effectively solves the difficulty of capturing static spring fatigue characteristics inherent in traditional methods. Second, a high-dimensional feature space was constructed using Savitzky–Golay filtering and physical feature extraction techniques. To address the characteristics of small-sample data distribution, a two-layer Stacking ensemble learning model based on 5-fold cross-validation was designed. This model utilizes the SVM (Support Vector Machine), RF (Random Forest), and KNN (K-Nearest Neighbors) as base classifiers and Logistic Regression as the meta-learner, achieving an adaptive fusion of the advantages of heterogeneous algorithms. True-type experimental results show that the average diagnostic accuracy of this method under normal conditions and four typical fault conditions reaches 96.1%, which is superior to single base models (the RF was 94.2%). Feature importance analysis further confirms that closing and opening pressures are the most critical features for distinguishing mechanical faults. This study provides effective theoretical basis and technical support for condition-based maintenance of high-voltage circuit breakers under small-sample conditions. Full article

Efficient and non-destructive extraction of clay minerals is fundamental for shale oil and gas reservoir evaluation and enrichment mechanism studies. However, traditional manual extraction experiments face bottlenecks such as low efficiency and reliance on operator experience, which limit their scalability and adaptability to intelligent research demands. To address this, this paper proposes an intelligent experimental scheduling system for clay mineral extraction based on deep reinforcement learning. First, the complex experimental process is deconstructed, and its core scheduling stages are abstracted into a Flexible Job Shop Scheduling Problem (FJSP) model with resting time constraints. Then, a scheduling agent based on the Proximal Policy Optimization (PPO) algorithm is developed and integrated with an improved Heterogeneous Graph Neural Network (HGNN) to represent the relationships among operations, machines, and constraints. This enables effective capture of the complex topological structure of the experimental environment and facilitates efficient sequential decision-making. To facilitate future practical applicability, a four-layer system architecture is proposed, comprising the physical equipment layer, execution control layer, scheduling decision layer, and interactive application layer. A digital twin module is designed to bridge the gap between theoretical scheduling and physical execution. This study focuses on validating the core scheduling algorithm through realistic simulations. Simulation results demonstrate that the proposed HGNN-PPO scheduling method significantly outperforms traditional heuristic rules (FIFO, SPT), meta-heuristic algorithms (GA), and simplified reinforcement learning methods (PPO-MLP). Specifically, in large-scale problems, our method reduces the makespan by over 9% compared to the PPO-MLP baseline, and the algorithm runs more than 30 times faster than GA. This highlights its superior performance and scalability. This study provides an effective solution for intelligent scheduling in automated chemical laboratory workflows and holds significant theoretical and practical value for advancing the intelligentization of experimental sciences, including shale oil and gas research. Full article

Accurate simulation of boundary layer wind field structures is essential for evaluating tropical cyclone (TC) wind hazards and supporting engineering design in coastal regions. However, existing models often assume radially symmetric and homogeneous surface conditions, leading to limited accuracy near landfall where surface roughness varies significantly. This study conducts a comprehensive evaluation of four representative TC boundary layer models of M95, K01, Y21a, and Y21b, under both idealized and real TC case conditions. The idealized experiments are used to clarify the role of vertical advection and turbulent diffusion in shaping the TC boundary layer, while the landfalling case of Typhoon Mangkhut (2018) is simulated to examine the impacts of surface roughness parameterization. Results show that Y21a, which incorporates nonlinear vertical advection, produces stronger and more realistic super-gradient phenomenon than linear models of M95 and K01. Furthermore, the model of Y21b, which accounts for spatially varying drag coefficients and using a terrain-following coordinate system, successfully reproduces the asymmetric wind patterns observed in the WRF simulations during landfall, achieving the highest correlation (R = 0.93). When the spatially varying drag coefficients incorporated into the linear models, their correlation with WRF improved markedly by about 37%. These findings highlight the necessity of incorporating nonlinear advection, dynamic turbulence, and surface heterogeneity for physically consistent TC boundary layer simulations. The results provide valuable guidance for improving parametric wind field models and enhancing TC wind hazard assessments over complex coastal terrains. Full article