Search Results (2,094)

To meet the demands for real-time and accurate fault warning of wind turbine gear transmission systems, this study proposes an innovative intelligent warning method based on the integration of digital twin and multi-source data fusion. A digital twin system architecture is developed, comprising a high-precision geometric model and a dynamic mechanism model, enabling real-time interaction and data fusion between the physical transmission system and its virtual model. At the algorithmic level, a CNN-LSTM-Attention fault prediction model is proposed, which innovatively integrates the spatial feature extraction capabilities of a convolutional neural network (CNN), the temporal modeling advantages of long short-term memory (LSTM), and the key information-focusing characteristics of an attention mechanism. Experimental validation shows that this model outperforms traditional methods in prediction accuracy. Specifically, it achieves average improvements of 0.3945, 0.546 and 0.061 in Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), and R-squared (R²) metrics, respectively. Building on the above findings, a monitoring and early warning platform for the wind turbine transmission system was developed, integrating digital twin visualization with intelligent prediction functions. This platform enables a fully intelligent process from data acquisition and status evaluation to fault warning, providing an innovative solution for the predictive maintenance of wind turbines. Full article

The goal of this study was to develop an automated monitoring system based on infrared thermography (IRT) for the detection of group-housed pig ears temperature. The aim in the first part of the study was to recognize pigs’ ears by using neural network analysis (SwinStar-YOLO). In the second part of the study, the goal was to automatically extract the maximum and average values of the temperature in the ear region using morphological image processing and a temperature matrix. Our dataset (3600 pictures, 10,812 pig ears) was processed using 5-fold cross-validation before training the ear detection model. The model recognized pigs’ ears with a precision of 93.74% related to threshold intersection over union (IoU). Correlation analysis between manually extracted and algorithm-derived ear temperatures from 400 pig ear samples showed coefficients of determination ($R^2$) of 0.97 for maximum and 0.88 for average values. This demonstrates that our proposed method is feasible and reliable for automatic pig ear temperature monitoring, serving as a powerful tool for early health warning. Full article

With the in-depth application of digital transformation in the oil industry, data-driven methods provide a new technical path for drilling engineering safety evaluation. In this paper, a data-driven drilling safety level evaluation system is proposed. By integrating the three-dimensional visualization technology of wellbore trajectory and the prediction model of friction torque, a dynamic and intelligent drilling risk evaluation framework is constructed. The Python platform is used to integrate geomechanical parameters, real-time drilling data, and historical working condition records, and the machine learning algorithm is used to train the friction torque prediction model to improve prediction accuracy. Based on the K-means clustering evaluation method, a three-tier drilling safety classification standard is established: Grade I (low risk) for friction (0–100 kN) and torque (0–10 kN·m), Grade II (medium risk) for friction (100–200 kN) and torque (10–20 kN·m), and Grade III (high risk) for friction (>200 kN) and torque (>20 kN·m). This enables intelligent quantitative evaluation of drilling difficulty. The system not only dynamically optimizes bottom-hole assembly (BHA) and drilling parameters but also continuously refines the evaluation model’s accuracy through a data backtracking mechanism. This provides a reliable theoretical foundation and technical support for risk early warning, parameter optimization, and intelligent decision-making in drilling engineering. Full article

Accurate forecasting of river siltation is essential for ensuring inland waterway navigability and guiding sustainable sediment management. This study investigates the downstream reach of the Shihutang navigation power hub along the Ganjiang River in Jiangxi Province, China, an area characterized by pronounced seasonal sedimentation and hydrological variability. To enable fine-scale prediction, we developed a data-driven framework using a random forest regression model that integrates high-resolution bathymetric surveys with hydrological and meteorological observations. Based on the field data from April to July 2024, the model was trained to forecast monthly siltation volumes at a 30 m grid scale over a six-month horizon (July–December 2024). The results revealed a marked increase in siltation from July to September, followed by a decline during the winter months. The accumulation of sediment, combined with falling water levels, was found to significantly reduce the channel depth and width, particularly in the upstream sections, posing a potential risk to navigation safety. This study presents an initial, yet promising attempt to apply machine learning for spatially explicit siltation prediction in data-constrained river systems. The proposed framework provides a practical tool for early warning, targeted dredging, and adaptive channel management. Full article

Prolonged inundations are altering coastal forest ecosystems of the southeastern US, causing extensive tree die-offs and the development of ghost forests. This hydrological stressor also alters carbon fluxes, threatening the stability of coastal carbon sinks. This study was conducted to investigate the interactions between hydrological drivers and ecosystem responses by analyzing daily eddy covariance flux data from a wetland forest in North Carolina, USA, spanning 2009–2019. We analyzed temporal patterns of net ecosystem exchange (NEE), gross primary productivity (GPP), and ecosystem respiration (RE) under both flooded and non-flooded conditions and evaluated their relationships with observed tree mortality. Generalized Additive Modeling (GAM) revealed that groundwater table depth (GWT), leaf area index (LAI), NEE, and net radiation (Rn) were key predictors of mortality transitions (R² = 0.98). Elevated GWT induces root anoxia; declining LAI reduces productivity; elevated NEE signals physiological breakdown; and higher Rn may amplify evapotranspiration stress. Receiver Operating Characteristic (ROC) analysis revealed critical early warning thresholds for tree mortality: GWT = 2.23 cm, LAI = 2.99, NEE = 1.27 g C m⁻² d⁻¹, and Rn = 167.54 W m⁻². These values offer a basis for forecasting forest mortality risk and guiding early warning systems. Our findings highlight the dominant role of hydrological variability in ecosystem degradation and offer a threshold-based framework for early detection of mortality risks. This approach provides insights into managing coastal forest resilience amid accelerating sea level rise. Full article

Effective earthquake early warning (EEW) is essential for disaster prevention in the built environment, enabling a rapid structural response, system shutdown, and occupant evacuation to mitigate damage and casualties. However, most current EEW systems lack rigorous reliability analyses of their predictive outcomes, limiting their effectiveness in real-world scenarios—especially for on-site warnings, where data are limited and time is critical. To address these challenges, we propose a Bayesian neural network (BNN) framework based on Stein variational gradient descent (SVGD). By performing Bayesian inference, we estimate the posterior distribution of the parameters, thus outputting a reliability analysis of the prediction results. In addition, we incorporate a continual learning mechanism based on elastic weight consolidation, allowing the system to adapt quickly without full retraining. Our experiments demonstrate that our SVGD-BNN model significantly outperforms traditional peak displacement (Pd)-based approaches. In a 3 s time window, the Pearson correlation coefficient R increases by 9.2% and the residual standard deviation $SD$ decreases by 24.4% compared to a variational inference (VI)-based BNN. Furthermore, the prediction variance generated by the model can effectively reflect the uncertainty of the prediction results. The continual learning strategy reduces the training time by 133–194 s, enhancing the system’s responsiveness. These features make the proposed framework a promising tool for real-time, reliable, and adaptive EEW—supporting disaster-resilient building design and operation. Full article

Non-polio enteroviruses continue to cause numerous epidemics world-wide that range from mild to severe disease, including acute flaccid paralysis, meningitis, severe respiratory infections and encephalitis. Using publicly available data we present a comprehensive global and regional temporal distribution of non-polio enteroviruses, with a focus on highly prevalent genotypes. We found that regional distribution did vary compared to global prevalence where the top prevalent genotypes included CVA6 and EV-A71 in Asia, EV-D68 in North America and CVA13 in Africa, while E-30 was prevalent in Europe, South America and Oceania. In 2020, the COVID-19 pandemic did interrupt non-polio enterovirus detections globally, and cases rebounded in subsequent years, albeit at lower prevalence and with decreased genotype diversity. Environmental surveillance for non-polio enteroviruses does occur and has been used in some regions as an early-warning system; however, further development is needed to effectively supplement potential gaps in clinical surveillance data. Overall, monitoring for non-polio enteroviruses is critical to identify true incidence, improve understanding of genotype circulation, provide an early warning system for emerging/re-emerging genotypes and allow for better outbreak control. Full article

Mexico City frequently experiences high near-surface ozone concentrations, and exposure to elevated near-surface ozone causes harmful effects to the inhabitants and the environment of Mexico City. This necessitates developing models for Mexico City that predict near-surface ozone levels in advance. Such models are crucial for regulatory procedures and can save a great deal of near-surface ozone detrimental effects by serving as early warning systems. We utilize three machine-learning models, trained on seven-year data (2015–2021) and tested on one-year data (2022), to forecast the near-surface ozone concentrations. The trained models predict the next day’s 24-h near-surface ozone concentrations for up to one month; before forecasting the following months, the models are trained again and updated. Based on prediction results, the convolutional neural network outperforms the rest of the models on a yearly scale with an index of agreement of 0.93 for three stations, 0.92 for nine stations, and 0.91 for one station. Full article

High moisture content (MC) harms wheat storage quality and readily leads to mold growth. Accurate localization of abnormal/high-moisture regions enables early warning, ensuring proper storage and reducing economic losses. The present study introduces the 2D microwave scanning method and investigates a novel localization method for addressing such a challenge. Both static and scanning experiments were performed on a developed mobile and non-destructive microwave detection system to quantify the MC of wheat and then locate abnormal moisture regions. For quantifying the wheat’s MC, a dual-parameter wheat MC prediction model with the random forest (RF) algorithm was constructed, achieving a high accuracy (R² = 0.9846, MSE = 0.2768, MAE = 0.3986). MC scanning experiments were conducted by synchronized moving waveguides; the maximum absolute error of MC prediction was 0.565%, with a maximum relative error of 3.166%. Furthermore, both one- and two-dimensional localizing methods were proposed for localizing abnormal moisture regions. The one-dimensional method evaluated two approaches—attenuation value and absolute attenuation gradient—using computer simulation technology (CST) modeling and scanning experiments. The experimental results confirmed the superior performance of the absolute gradient method, with a center detection error of less than 12 mm in the anomalous wheat moisture region and a minimum width detection error of 1.4 mm. The study performed two-dimensional antenna scanning and effectively imaged the high-MC regions using phase delay analysis. The imaging results coincide with the actual locations of moisture anomaly regions. This study demonstrated a promising solution for accurately localizing the wheat’s abnormal/high-moisture regions with the use of an emerging microwave transmission method. Full article

The movement towards low-emission and sustainable building practices has driven increased use of natural, carbon-based materials such as wood. While these materials offer significant environmental advantages, their inherent flammability introduces new challenges for timber building safety. Despite advancements in fire protection standards and building regulations, the risk of fire incidents—whether from technical failure, human error, or intentional acts—remains. The rapid detection of fire onset is crucial for safeguarding human life, animal welfare, and valuable assets. This study investigates the potential of monitoring fire precursor gases emitted inside building structures during pre-ignition and early combustion stages. The research also examines the sensitivity and effectiveness of commercial smoke detectors compared with custom sensor arrays in detecting these emissions. A representative structural sample was constructed and subjected to a controlled fire scenario in a laboratory setting, providing insights into the integration of gas sensing technologies for enhanced fire resilience in sustainable building systems. Full article

The Mw 7.8 Gorkha Earthquake of 25 April 2015 triggered over 25,000 landslides across central Nepal, with 4775 events concentrated in Gorkha District alone. Despite substantial advances in landslide susceptibility mapping, existing studies often overlook the compound role of post-seismic rainfall and lack robust spatial validation. To address this gap, we validated an ensemble machine learning framework for co-seismic landslide susceptibility modeling by integrating seismic, geomorphological, hydrological, and anthropogenic variables, including cumulative post-seismic rainfall. Using a balanced dataset of 4775 landslide and non-landslide instances, we evaluated the performance of Logistic Regression (LR), Random Forest (RF), and eXtreme Gradient Boosting (XGBoost) models through spatial cross-validation, SHapley Additive exPlanations (SHAP) explainability, and ablation analysis. The RF model outperformed all others, achieving an accuracy of 87.9% and a Receiver Operating Characteristic (ROC) Area Under the Curve (AUC) value of 0.94, while XGBoost closely followed (AUC = 0.93). Ensemble models collectively classified over 95% of observed landslides into High and Very High susceptibility zones, demonstrating strong spatial reliability. SHAP analysis identified elevation, proximity to fault, peak ground acceleration (PGA), slope, and rainfall as dominant predictors. Notably, the inclusion of post-seismic rainfall substantially improved recall and F1 scores in ablation experiments. Spatial cross-validation revealed the superior generalizability of ensemble models under heterogeneous terrain conditions. The findings underscore the value of integrating post-seismic hydrometeorological factors and spatial validation into susceptibility assessments. We recommend adopting ensemble models, particularly RF, for operational hazard mapping in earthquake-prone mountainous regions. Future research should explore the integration of dynamic rainfall thresholds and physics-informed frameworks to enhance early warning systems and climate resilience. Full article

The need for systems that forecast and respond proactively to meteorological disasters is growing amid climate variability. Although the early warning system in South Korea includes countermeasure information, it remains limited in terms of data recency, granularity, and regional adaptability. Additionally, its closed architecture hinders interoperability with external systems. This study aims to redesign the countermeasure function as an independent cloud-based platform grounded in the common standard terminology framework in South Korea. A multi-dimensional data model was developed using attributes such as crop type, cultivation characteristics, growth stage, disaster type, and risk level. The platform incorporates user-specific customization features and history tracking capabilities, and it is structured using a microservices architecture to ensure modularity and scalability. The proposed system enables real-time management and dissemination of localized countermeasure suggestions tailored to various user types, including central and local governments and farmers. This study offers a practical model for enhancing the precision and applicability of agrometeorological response information. It is expected to serve as a scalable reference platform for future integration with external agricultural information systems. Full article

The Mediterranean region, identified by scientists as a ‘climate hot spot’, is experiencing warmer and drier conditions, along with an increase in the intensity and frequency of extreme weather events. One such extreme phenomena is droughts. The recent wildfires in this region are a concerning consequence of this phenomenon, causing severe environmental damage and transforming natural landscapes. However, droughts involve a two-way interaction: On the one hand, climate change and various human activities, such as urbanization and deforestation, influence the development and severity of droughts. On the other hand, droughts have a significant impact on various sectors, including ecology, agriculture, and the local economy. This study investigates drought dynamics in four Mediterranean countries, Greece, France, Italy, and Spain, each of which has experienced severe wildfire events in recent years. Using satellite-based Earth observation data, we monitored drought conditions across these regions over a five-year period that includes the dates of major wildfires. To support this analysis, we derived and assessed key indices: the Normalized Difference Vegetation Index (NDVI), Normalized Difference Water Index (NDWI), and Normalized Difference Drought Index (NDDI). High-resolution satellite imagery processed within the Google Earth Engine (GEE) platform enabled the spatial and temporal analysis of these indicators. Our findings reveal that, in all four study areas, peak drought conditions, as reflected in elevated NDDI values, were observed in the months leading up to wildfire outbreaks. This pattern underscores the potential of satellite-derived indices for identifying regional drought patterns and providing early signals of heightened fire risk. The application of GEE offered significant advantages, as it allows efficient handling of long-term and large-scale datasets and facilitates comprehensive spatial analysis. Our methodological framework contributes to a deeper understanding of regional drought variability and its links to extreme events; thus, it could be a valuable tool for supporting the development of adaptive management strategies. Ultimately, such approaches are vital for enhancing resilience, guiding water resource planning, and implementing early warning systems in fire-prone Mediterranean landscapes. Full article

Housing sustainability is a cornerstone element of sustainable economic and social development. This is particularly true for China, where high-rise residential buildings are the primary form of housing. In recent years, China has experienced frequent housing-related accidents, resulting in a significant loss of life and property damage. This study aims to identify the key factors influencing housing sustainability and provide a basis for the prevention and control of housing-related safety risks. This study has developed a housing sustainability evaluation indicator system comprising three primary indicators and 16 secondary indicators. This system is based on an analysis of the causes of over 500 typical housing accidents that occurred in China over the past 10 years, employing research methods such as literature reviews and expert consultations, and drawing on the analytical frameworks of risk management theory and system safety theory. Subsequently, the NK-SNA model, which significantly outperforms traditional models in terms of adaptive learning and optimization, as well as the explicit modeling of complex nonlinear relationships, was used to identify the key risk factors affecting housing sustainability. The empirical results indicate that the risk coupling value is correlated with the number of risk coupling factors; the greater the number of risk coupling factors, the larger the coupling value. Human misconduct is prone to forming two-factor risk coupling with housing, and the physical risk factors are prone to coupling with other factors. The environmental factors easily trigger ‘physical–environmental’ two-factor risk coupling. The key factors influencing housing sustainability are poor supervision, building facilities, the main structure, the housing height, foundation settlement, and natural disasters. On this basis, recommendations are made to make full use of modern information technologies such as the Internet of Things, big data, and artificial intelligence to strengthen the supervision of housing safety and avoid multi-factor coupling, and to improve upon early warnings of natural disasters and the design of emergency response programs to control the coupling between physical and environmental factors. Full article

While prior work has explored learner behavior using learning management systems (LMS) data, few studies provide week-level clustering validated against external engagement labels. To understand and assist students in online learning platforms and environments, this study presents a week-level engagement profiling framework for e-learning environments, utilizing K-means clustering and label-based validation. Leveraging log data from 127 students over a 13-week course, 44 activity-based features were engineered to classify student engagement into high, moderate, and low levels. The optimal number of clusters (k = 3) was identified using the elbow method and assessed through internal metrics, including a silhouette score of 0.493 and R² of 0.80. External validation confirmed strong alignment with pre-labeled engagement levels based on activity frequency and weighting. The clustering approach successfully revealed distinct behavioral patterns across engagement tiers, enabling a nuanced understanding of student interaction dynamics over time. Regression analysis further demonstrated a significant association between engagement levels and academic performance, underscoring the model’s potential as an early warning system for identifying at-risk learners. These findings suggest that clustering based on LMS behavior offers a scalable, data-driven strategy for improving learner support, personalizing instruction, and enhancing retention and academic outcomes in digital education settings such as MOOCs. Full article