Search Results (6,041)

Ship self-sinking accidents threaten maritime safety, human life, property, and the marine environment, and understanding their causal-factor associations is essential for developing effective preventive measures. This study aims to identify the multi-level factors, recurrent association patterns, and critical structural nodes involved in ship self-sinking accidents. A hybrid framework integrating grounded theory, the Human Factors Analysis and Classification System (HFACS), FP-growth association rule mining, and complex network analysis was applied to 150 accident investigation reports released by the China Maritime Safety Administration between 2014 and 2024. Findings suggest that adverse weather and sea conditions, inadequate ship safety management, and crew incompetence are the most frequent factors. Thirty causal factors were identified and classified into four HFACS levels, and 229 association rules were generated to construct a directed weighted causal-factor association network with 19 nodes and 229 edges. Network results indicate that inadequate ship safety management, crew incompetence, ship unseaworthiness, insufficient maintenance of hull weathertight integrity, and improper or untimely emergency measures occupy critical positions in the association structure. This research offers insight into ship self-sinking accidents and identifies priority intervention points for more targeted maritime supervision, safety management and accident prevention. Full article

With the increase in operation time of DC traction systems due to the environment of tunnel and stress rupture, the insulation between the rail and ground inevitably decreases, causing increased stray current leakage. In view of this, we present an analytical and electrochemical study of stray current behavior and its corrosion impact arising from local rail-to-ground insulation damage in DC urban rail systems. A two-layer rail–earth continuous model of stray current distribution is developed (unilateral and bilateral supply cases) using Kirchhoff network formulations with insulation damage boundary conditions. Numerical simulations quantify the effects of damage location and grounding resistance on rail potential shifts, abrupt changes in rail and stray currents, and total leakage. To assess electrochemical consequences for nearby buried pipelines, the electrical model is proposed in this work with an impedance-informed corrosion model and Monte Carlo sampling of operational and electrical uncertainties to estimate dynamic corrosion rates and pitting evolution. The results show that single–point insulation faults shift the rail zero potential toward the fault, leading to instantaneous jumps in leakage and rail currents whose magnitude grows as damaged-point resistance decreases, markedly increasing pipeline corrosion risk. The integrated electrical-electrochemical framework provides a tool for detection, risk assessment, and mitigation planning for stray current-induced pipeline corrosion. Full article

Mixed ground conditions cause sudden fluctuations in the tunnel boring machine (TBM) advance rate (AR). Accurate forecasting is necessary for tunneling safety. Existing data-driven models, however, often treat the excavation process as an isolated event. They ignore the physical memory effect of rock–machine interactions. They also lack the ability to diagnose abnormal AR drops. To address these issues, an interpretable forecasting framework is proposed. First, a Selection–Processing (SP) system is established to standardize data handling and quantify geological heterogeneity. Second, a Time-Series Structure (TSS) network is developed to construct a one-ring-ahead input block using the current completed-ring state and CCF/PACF-guided historical windows. The framework is validated on the Shenzhen–Dayawan Intercity Line. The optimized GWO-LSTM model achieves high accuracy (R² = 0.977, MAE = 2.15, RMSE = 3.07). Compared with the no-TSS reference scheme, the MAE and RMSE decrease from 2.7081 and 3.6045 to 2.1496 and 3.0724, respectively. Furthermore, Shapley Additive Explanations (SHAP) are applied for ring-by-ring anomaly diagnosis. Local SHAP analysis indicates that both current-state variables and selected lagged variables provide diagnostic information for AR fluctuations. The identified lags are interpreted as project-specific memory indicators rather than universal physical delay constants. This method provides model-based diagnostic clues for associating sudden AR drops with specific operational or geological factors. The proposed framework provides a transparent and practical tool for TBM performance prediction and field diagnosis. Full article

This paper shifts the research perspective from “Buddhist monasteries” to “monastic Buddhism,” using Nālandā Mahāvihāra as a micro-level case to illuminate the broader support mechanism of Indian Buddhist monasteries, with particular focus on the concept of “non-exhaustible endowment”. Drawing on epigraphic evidence, Vinaya texts, and Chinese pilgrims’ records, it finds that major donors supported monasteries through religious rituals, land grants, and cash investments, primarily in the form of landed property and gold and silver currency, which were designated as non-exhaustible endowments. Monasteries then engaged in agriculture, handicrafts, building industry, commerce, and lending, transforming static assets into a non-exhaustible cycle of capital that benefited both monastics and laity. Systems such as Yizhi (robe funds) and Gongfu zhi Zhuang (robe-providing estates) reveal mature financial services that not only liberated monks from economic constraints but also stimulated the cotton textile trade between India and China. The wealth possessed by monasteries was not static but perpetually engaged in a dynamic cycle of capital. Major Buddhist monasteries thus emerged as regional economic engines, which became the core value for continuous royal patronage, as well as the key incentive for their violent destruction by Turkic Muslims. However, the transformation of the religious landscape and economic network in late medieval Bihār was not a simplistic process. Faced with a changing political and religious environment over time, Sufi saints, Jain followers, Shaiva ascetics and other religious communities, each grounded in their own faiths, landholdings, commercial networks and educational systems, gradually displaced, restructured and undermined the Buddhist monastery-centered endowment mechanism, causing Buddhism to progressively lose its regional dominance as an institutionalized religion. Full article

The digital transformation of agrifood systems demands an integrated infrastructure to ensure traceability, trust, and intelligent decision-making across complex and heterogeneous value chains. METROFOOD-IT, a large-scale national research infrastructure in food metrology aligned with the ESFRI METROFOOD-RI, addresses these challenges by combining advanced experimental facilities with a comprehensive digital ecosystem. This paper focuses on the IT kernel of METROFOOD-IT and presents an integrated architectural model that brings together four key technological paradigms: data acquisition through Internet of Things (IoT) and laboratory infrastructures, an Open Data Platform for interoperability and sharing, blockchain-based notarization for integrity and provenance, and Artificial Intelligence (AI) for knowledge extraction and decision support. Rather than describing these components in isolation, the paper abstracts from their implementation within the Italian National Recovery and Resilience Plan (NRRP) project METROFOOD-IT to distill a coherent and reusable architectural pattern in which data management, trust enforcement, and intelligent analytics are tightly coupled. Five explicit design principles are identified and articulated: federated data with centralized metadata, selective on-chain anchoring, user-unobtrusive trust infrastructure, explainability as a first-class architectural concern, and machine learning as the backbone of decision-making. Two empirical case studies—one centered on explainable AI for hyperspectral crop nitrogen assessment and the other on IoT-driven sustainable agriculture monitoring secured by distributed ledger technology—serve a dual role: they motivate and shape the architectural pattern, and they exemplify the operational regimes the resulting design supports. A reference deployment on the Ethereum Sepolia public test network, grounded on an IBM Power E1050 and IBM Storage Scale enterprise substrate, provides quantitative evidence for the proposed hybrid on-chain/off-chain pattern with streaming hash-only notarization. The architecture illustrates how research infrastructures can evolve into integrated digital platforms that enable transparent, verifiable, and scalable agrifood systems, and offers a foundation for generalizable design principles in data-intensive and trust-sensitive settings. Full article

Incomplete spatio-temporal (ST) data from sensor networks in precision agriculture often limits environmental modeling and decision-making accuracy. To address this, we propose the Spatio-Temporal Conditional Diffusion Framework (ST-CDF), a generative approach for high-fidelity data reconstruction. The framework’s core is a deep denoising network that integrates a Graph Attention Network (GAT) to explicitly model non-Euclidean spatial correlations, a Differential Attention Transformer to capture abrupt temporal dynamics, and an Inverse Discrete Wavelet Transform (IDWT) module to preserve multi-scale signal details. The generative process is constrained by a physics-informed training objective, which injects known physical laws (i.e., the Penman–Monteith equation for reference evapotranspiration, $E{T}_0$) as an inductive bias, ensuring the imputed data maintains physical consistency. For privacy-preserving deployment on resource-constrained IoT devices, we extend the framework with a Federated Cluster-Guided Distillation (Fed-CGD) strategy. We conducted extensive experiments against established methods on two real-world agricultural datasets. ST-CDF demonstrated improved imputation accuracy across evaluated metrics. Its efficacy was most pronounced in the physically-demanding $E{T}_0$ calculation task, where data imputed by ST-CDF at an 80% missing rate achieved a Root Mean Square Error (RMSE) of 0.3485 and a Coefficient of Determination ($R^2$) of 0.7558, outperforming the baseline models. Furthermore, we explore ST-CDF as an explainable (XAI) framework for active agricultural decision support, demonstrating its utility in performing counterfactual simulations of “what-if” interventions, such as irrigation. The findings highlight ST-CDF as an effective, physically-grounded, and interpretable tool for data-driven scientific computation and precision agriculture. Full article

We evaluated a multi-output neural network framework for jointly analyzing maize grain yield (GY) and root lodging percentage (LP) using above-ground morphological traits measured under defined environmental conditions. To address model robustness, the multi-output neural network was compared with linear regression, elastic net, random forest, and XGBoost using repeated five-fold cross-validation, an 80/20 holdout split, and independent year-wise validation. Under repeated cross-validation, XGBoost provided the strongest average predictive performance for both traits, with R² values of 0.57 for GY and 0.67 for LP. The multi-output neural network showed moderate performance, with R² values of 0.49 for GY and 0.57 for LP. Final holdout performance for the neural network for GY and LP was R² = 0.64 and R² = 0.92, respectively. Year-wise validation showed weak temporal transferability because the two seasons differed not only in environmental conditions, but also in lodging mechanism. Repeated permutation importance identified ear width (EW), kernel row number (RNE), thousand kernel mass (KM1000), and kernel number per ear (KNE) as important predictors of GY, while LP prediction was most strongly associated with internode major diameter (IDmajor), ear length (EL), and the number of green leaves (NGL). Across both permutation importance and SHAP, only RNE and NGL were consistently shared between GY and LP. Supplementary ALE diagnostics indicated that RNE showed increasing model-estimated effects for both predicted GY and LP, whereas NGL showed a positive association with predicted GY but a decreasing or nonlinear association with predicted LP. These results show that joint modeling can support exploratory trait interpretation, but the predictive relationships remain environment-specific and should not be interpreted as causal or broadly transferable without further multi-environment validation. Full article

Surface solar ultraviolet (UV) radiation represents an essential component of shortwave solar radiation, with important implications for atmospheric chemistry and climate studies. Reliable, high-quality records of surface solar UV radiation are essential for UV-related research and applications; however, ground-based UV observations remain sparse worldwide. This study presents a novel broadband parametric model, based on physical principles, for estimating solar UV irradiance ($0.280–0.400 \mu \mathrm{m}$) under clear-sky conditions. The model is computationally efficient and suitable for practical applications. The proposed approach is based on the SMARTS2 spectral radiative transfer model and employs an interdependent integration scheme to derive broadband UV irradiance from spectrally resolved shortwave radiation. The model performance is evaluated against high-quality measurements from the Baseline Surface Radiation Network (BSRN) and compared with an established parameterization. The proposed model demonstrates improved performance at both validation sites, reducing the mean nRMSE from 8.88% to 7.64% at Izaña and from 60.69% to 29.24% at Payerne, while also substantially decreasing the bias under more challenging atmospheric conditions, although the nRMSE at Payerne remains relatively high. These results highlight the potential of the proposed approach as an efficient and physically consistent tool for clear-sky UV irradiance estimation. Full article

Fringe projection profilometry (FPP) is widely used for 3D reconstruction, but conventional single-view FPP systems suffer from inherent occlusions and shadow regions, leading to incomplete surface recovery. In this study, we propose CVA-Net, an end-to-end deep learning framework with cross-view attention (CVA) that directly reconstructs dense depth maps from multi-view fringe patterns. CVA-Net simultaneously processes four fringe images acquired from orthogonal projection directions and leverages a CVA module to explicitly model inter-view dependencies, enabling adaptive fusion of complementary information. A 3D U-Net backbone with attention gates, atrous spatial pyramid pooling (ASPP), and an auxiliary parameter estimation branch further enhances reconstruction accuracy and structural consistency via multitask learning. To support Sim2Real network training, we build a Blender-based digital twin of a multi-view FPP system and generate a large-scale synthetic dataset with perfect ground truth. Extensive experiments on both synthetic and real-world objects demonstrate that CVA-Net significantly outperforms state-of-the-art single-view methods. With a symmetric four-view configuration and fringe period of 8, CVA-Net achieves an MAE of 0.0359 mm, an MSE of 0.0379 mm² and an RMSE of 0.1947 mm, reducing the MAE, MSE, and RMSE by 32.8%, 54.1%, and 32.2%, respectively, compared to the best single-view competitor. Ablation studies validate the contribution of each architectural component, while real-system experiments demonstrate the feasibility of transferring a network trained purely on synthetic data to practical FPP measurements without domain adaptation. Although further improvements are required to enhance reconstruction accuracy under real imaging conditions, the proposed framework provides an effective initial step toward bridging the gap between digital-twin-based training and real-world multi-view FPP applications. CVA-Net provides a robust, occlusion-aware solution for multi-view FPP reconstruction. Full article

Skeleton-based human action recognition (HAR) requires models that preserve the local kinematic structure of the human body while capturing long-range spatiotemporal dependencies under noisy or incomplete joint observations. Traditional Graph Convolutional Networks (GCNs) provide topology-aligned inductive bias but are often limited by local information aggregation from neighboring joints. In contrast, attention-based mechanisms capture global interactions, yet they may attend to spurious correlations when skeletal constraints are weakly enforced. This paper proposes Differential Hyperedge Attention-enhanced GCN (DHA-eGCN), a hybrid architecture that couples structure-aware Differential Hyperedge Attention with multi-scale temporal convolution for spatiotemporal skeleton sequence processing. DHA injects skeletal structure into attention via hop-distance relative positional encoding and hyperedge context tokens generated via joint-to-part pooling. It further employs differential attention to suppress shared noisy correlations and enhance interaction selectivity. To strengthen spatial grounding, an explicit GCN branch is added under partial- or full-depth configurations, where the first four or all ten layers are applied with graph convolutions. The model further employs an ensemble strategy that combines predictions from multiple complementary model instances. Our experiments on NTU RGB+D 60 under the X-Sub and X-View protocols, NTU RGB+D 120 under the X-Sub and X-Set protocols, and Northwestern-UCLA demonstrate that DHA-eGCN consistently outperforms or remains competitive with strong graph-based, transformer-based, and hybrid state-of-the-art methods based on the same four-stream architecture. The best configuration achieves 93.7% and 97.0% on NTU RGB+D 60 X-Sub and X-View, respectively; 90.9% and 91.9% on NTU RGB+D 120 X-Sub and X-Set, respectively; and 97.6% on Northwestern-UCLA. Full article

Short-term traffic forecasting is a critical component of intelligent transportation systems. While deep learning architectures for this task have proliferated rapidly, the sensor-level data characteristics—zero-value prevalence, distributional heterogeneity, and cross-sensor correlation structure—that drive architecture-specific failure modes remain insufficiently understood, and their implications for evidence-based model selection in real deployments have not been systematically addressed. This study addresses that question through a sensor-network diagnostic framework applied to the METR-LA dataset (Metropolitan Los Angeles; 207 inductive loop detectors, 5-min resolution). The framework integrates systematic characterization of sensor data properties, a controlled benchmark of four representative architectures—Transformer, Spatio-Temporal Graph Convolutional Network (STGCN), Diffusion Convolutional Recurrent Neural Network (DCRNN), and Gated Temporal Convolutional Network (Gated TCN)—under a unified 12→3 prediction setting, and a novel per-sensor regression analysis that quantitatively links zero-value ratios to model-specific prediction errors across all 207 sensors. Building on these findings, this study further proposes Graph-Enhanced Transformer (GETFormer), a lightweight hybrid architecture that augments the Transformer with a single-hop Graph Convolutional Network (GCN) layer and a gated residual fusion module. The diagnostic findings and condition-dependent model-selection guidelines provide an empirically grounded foundation for principled hybrid architecture development in urban traffic sensing. Full article

As tunnel engineering continues to advance toward deeper, longer, and more complex projects, the risks encountered during the construction phase have evolved into a combination of various disaster types and the accumulation of multiple contributing factors. Traditional empirical and semi-empirical risk management methods are increasingly revealing shortcomings in terms of timeliness, accuracy, and the ability to process multi-source data. In recent years, driven by advancements in computing power and sensor technology, artificial intelligence algorithms (AI algorithms) such as machine learning and deep learning have been rapidly adopted in tunnel construction risk management. This paper retrieved relevant literature from the Web of Science database covering the period from 2010 to 2025. After rigorous screening, 96 highly relevant papers were selected for bibliometric analysis. This paper systematically reviews research progress from two perspectives: algorithmic models and engineering applications. The review indicates that, in terms of algorithmic models, traditional machine learning, convolutional neural network, recurrent neural network, generative adversarial network, Transformer, and graph neural network constitute a multi-level technical framework encompassing feature representation, risk perception, and intelligent decision-making. In terms of applications, AI algorithms have been widely integrated into typical scenarios such as geological hazard identification and prediction, surrounding rock stability and deformation prediction, rock burst assessment and early warning, lining defect detection and structural safety assessment, construction-induced ground settlement prediction, and tunnel gas and fire hazard prediction, significantly enhancing risk identification and early warning capabilities. However, several challenges remain, including the scarcity of high-quality datasets, the prevalence of noisy, incomplete, and heterogeneous monitoring data, insufficient coupling between model interpretability and engineering mechanisms, limited cross-project transferability, and the lack of integrated management systems for multi-hazard lifecycle control. Based on this, this paper proposes future research directions in areas such as data infrastructure development, integration of mechanism constraints, and multi-hazard collaborative modeling, aiming to provide guidance for the further development of intelligent risk management in tunnel construction. Full article

Optimizing harvest time and oil production requires accurate olive fruit quality characterization. Traditional chemical methods are costly and tedious, leading to poor monitoring resolution and reliance on subjective visual assessments. While spectroscopy offers a non-destructive alternative, standard equipment remains complex and prohibitively expensive for smallholder farmers. To address this, we propose a methodology using a custom-made, low-cost multispectral device. Built upon the AS7265x board, the system acquires 18 spectral bands in the visible and near-infrared range (410–940 nm). We used these spectral data to feed artificial neural network (ANN) models for estimating the quality of intact olives. During a two-season field experiment, we monitored ripening to acquire spectral signatures and ground-truth values for oil content per fresh weight (OCFW), oil content per dry matter (OCDM), moisture (M), and titratable acidity (TA). External validation showed high accuracy for OCFW (R²p = 0.86), OCDM (R²p = 0.86), and M (R²p = 0.89), proving the system’s reliability. However, TA estimation showed lower performance (R²p = 0.21), indicating limited spectral correlation. These findings pave the way for affordable, real-time smart farming tools for olive quality monitoring. Full article

With the occurrence of global climate change and the depletion of agricultural water resources, there is a growing need to develop rapid, non-destructive, and autonomous plant health monitoring systems. As an economically valuable crop, Ocimum basilicum L. (basil) is sensitive to changes in water availability and may exhibit stress-related morphological variations under drought and over-irrigation conditions. However, due to the visual similarity of leaf symptoms under drought stress, waterlogging stress, and optimal irrigation conditions, accurately distinguishing these conditions remains challenging in practical applications. To address this challenge, this paper presents an attention-based dual-branch deep learning framework designed to extract both subtle leaf details and channel-related features from high-resolution plant images. By combining the Convolutional Block Attention Module (CBAM) and Squeeze-and-Excitation (SE) mechanism in a parallel structure, the proposed network improves the analysis of high-resolution images with an input size of 720 × 720 pixels. Under controlled environmental conditions, with ground-truth labels obtained using soil moisture sensor measurements, the proposed model was compared with eight deep learning architectures, including DenseNet121, InceptionV3, and VGG16. The proposed model achieved a hold-out evaluation accuracy of 99.54%, outperforming the second-best model, DenseNet121, which achieved 96.43%. In addition, the proposed model reached a class-specific precision value of 100% for the Drought Stress category and achieved an area under the receiver operating characteristic curve of 1.00 under the controlled experimental setting. Taylor Diagram analysis also indicated that the model closely preserved the variability pattern of the reference data. These results suggest that the proposed application-specific framework may support non-destructive basil water-stress detection under controlled conditions. After further validation with larger datasets, different cultivars, variable environmental conditions, and real-world agricultural scenarios, the proposed approach may contribute to precision irrigation management and sustainable agricultural production. The contribution of this study should be interpreted as an application-specific implementation and evaluation of complementary attention mechanisms for controlled-environment basil water-stress classification, rather than as the introduction of a fundamentally new deep learning methodology. Full article

Coastal zones are dynamic interfaces where land, ocean, and atmosphere interact, making them sensitive indicators of environmental change. However, quantifying shoreline movement across long distances and over multi-year timescales remains challenging using traditional ground-based methods alone. We conducted an analysis of environmental factors and shoreline dynamics along a 58 km stretch of the arid Cabo Pulmo shoreline in Mexico from 2020 to 2026 using the CoastSat tool. The landscape is characterized by a diverse array of geographical features, including sandy beaches, granite cliffs, estuarine systems, and various anthropogenic structures. Results indicated a sea-level rise of 2 mm/year over the last 27 years, which is consistent with the reported range for the Pacific (1.8 to 3.8 mm/year). Notably, we observed an increasing trend of Category 4 and 5 hurricanes in the Mexican Pacific, with an average of 1 additional hurricane per decade (1950–2023). A total of 457 Sentinel-2 satellite images were used for automated analysis using the CoastSat platform, all of which were acquired under tidal conditions not exceeding 1 m. Our findings indicate that the granite cliffs show no detectable horizontal changes in the satellite images; however, their minimal vertical erosion contributes sediment to adjacent beaches. The most significant shoreline erosion was observed north of a marina breakwater, measuring −19.7 m, attributed to the disruption of littoral transport toward the southeast. In contrast, sandy beaches located in front of streams and estuaries—characterized by a lack of infrastructure (houses and breakwaters) and gentle slopes of 2° to 4°—demonstrated positive accretion of up to 5.9 m. According to the autoregressive distributed lag model, wave energy and hurricane-driven wind gusts are the primary agents of shoreline retreat, displacing sediment seaward to the continental shelf. Sea level rise exacerbates this retreat, while rainfall plays a minor but contributing role by transporting sediment during hurricanes in this arid region. This study highlights the effectiveness of CoastSat as a neural network-based tool for analyzing shoreline changes; however, we faced certain limitations, such as the absence of in situ beach profiles due to restricted access. Full article