Search Results (36,459)

The fatigue life prediction of additively manufactured (AM) alloys remains challenging owing to process-induced defects, microstructural variability, and complex loading conditions of the alloys. This study presents a domain-knowledge-informed machine learning (ML) and deep learning (DL) framework for fatigue life prediction, in which physically motivated fatigue descriptors are integrated into the feature space using experimentally obtained stress–life (S–N) data. Four physics-guided engineered descriptors, namely the normalized stress (σ_a/UTS), R-modified stress amplitude, UTS/YS ratio, and elastic strain energy density, were incorporated into the modelling framework to improve mechanistically grounded learning across diverse alloy systems. Five ML/DL models, namely Deep Artificial Neural Network (DANN), XGBoost, Extra Trees, Stacking Ensemble, and Random Forest, were benchmarked against the classical Basquin stress–life baseline. DANN achieved the best test-set performance (R² = 0.7114, RMSE = 0.5205 log cycles), whereas XGBoost exhibited the highest cross-validation performance (R² = 0.7547 ± 0.056). Ablation analysis confirmed the positive contributions of both the engineered descriptors (ΔR² = +0.115) and runout indicator (ΔR² = +0.107) to the predictive capability. The runout flag is appropriate for retrospective database modelling. For prospective applications, the no-runout configuration (R² = 0.5504) substantially outperformed the Basquin baseline (R² = 0.1244) and is recommended when runout information is unavailable. TreeSHAP analysis identified normalized stress and elongation as dominant predictors, with σ_a/UTS showing substantially greater importance than did the raw stress amplitude. The results demonstrate that physics-informed feature engineering substantially improves fatigue life prediction across the alloy systems and processing conditions represented in the dataset; however, further validation is required for under-represented additive manufacturing processes and alloy classes. Full article

In managed pressure drilling (MPD), wellbore flow states cannot be obtained in real time, so kick intervention decisions rely on the empirical judgment of engineers, which introduces a significant lag. The central hypothesis of this study is that fusing a physics-constrained transient two-phase flow model with real-time surface measurements through data assimilation can reconstruct the unobservable downhole flow state and, on this basis, enable quantitative and earlier prediction of the safe intervention timing than empirical judgment alone. To this end, this paper proposes a method for real-time inversion of wellbore flow states and safety intervention timing prediction based on the Ensemble Kalman Filter (EnKF). Using a transient wellbore gas–liquid two-phase flow model as the EnKF model operator, the method continuously assimilates real-time casing pressure, standpipe pressure (SPP), and pit gain data. This process dynamically corrects model prediction bias while maintaining multiphase flow physical constraints. Thus, the method achieves high-precision dynamic inversion of wellbore pressure profiles and gas holdup distributions. On this basis, the authors use the inverted states as initial conditions to calculate safety casing pressure with the multiphase flow model. The method then predicts intervention timing by combining three trigger conditions: safety casing pressure, pit gain, and the density difference between the inlet and outlet. The authors validated the method using kick scenarios from Well L and Well Z in the Shunbei block. The results showed that the mean absolute errors (MAEs) for casing pressure inversion were 0.113 MPa and 0.135 MPa, respectively. The MAEs for SPP were 1.324 MPa and 0.954 MPa. The MAEs for pit gain were 0.174 m³ and 0.114 m³. The inverted spatiotemporal distribution of gas holdup reflected the entire process of gas migration and expansion in the wellbore. Prediction results for intervention timing showed that the method issued early warning signals approximately 53 min and 29 min earlier than actual field operations. This method provides a quantitative decision-making basis with safety redundancy for MPD field operations. Full article

Layered cloud cover (LCC) describes the vertical distribution of cloud occurrence and is a key variable for assessing the radiation budget of the Earth-atmosphere system. However, ground-based radars have limited spatial coverage, while existing satellite cloud-cover products rarely provide both spatiotemporal continuity and high accuracy. Because nighttime satellite observations lack visible-channel information, conventional passive satellite remote sensing remains limited in providing day-night continuous LCC retrievals. In this study, we propose an infrared-based framework for retrieving large-scale day-night LCC from geostationary satellite observations. The framework first resolves cloud vertical structure using a hybrid machine learning and physical algorithm for day-night cloud-base height (CBH) retrieval, and then derives cloud cover in different vertical layers. Validation against active measurements from spaceborne and ground-based cloud radar demonstrates that the satellite-retrieved LCC captures cloud vertical distributions and their diurnal variations. The cloud-layer identification accuracies reach 76.3% and 77.9% for daytime and nighttime, respectively, with corresponding Cohen’s kappa coefficients of 0.66 and 0.68. The primary source of algorithmic uncertainty is the low precision of low-cloud identification, which is constrained by objective factors and physical characteristics. The retrieved annual mean LCC fields reproduce major climatological features, including enhanced high and deep convective clouds over the tropical western Pacific and dominant low-cloud occurrence over the mid-latitude oceans. A case study of Typhoon Doksuri further shows that the 10 min LCC retrievals capture the vertical evolution of the typhoon cloud system during intensification, eyewall structural adjustment, landfall, and post-landfall decay. These results indicate that the proposed infrared-based retrieval framework provides a promising basis for constructing large-scale day-night LCC datasets and can support cloud-radiation studies, climate-model evaluation, and weather monitoring. Full article

A novel distributed-order Cattaneo–Christov model is proposed to effectively characterize non-classical heat conduction processes with memory effect and time–space relaxation behaviors originating from distributed-order fractional derivatives. A fractional physics-informed neural networks (fPINN) algorithm is employed to address both the forward and inverse problems of the distributed-order heat conduction model. For the forward problem, we propose an SfPINN algorithm that incorporates a squared loss term and employs an adaptive updating strategy for the loss-term weights. First, the boundary conditions are embedded into the network output such that they are automatically satisfied. In addition, we design a two-stage training strategy to enhance computational efficiency: in the first stage, the squared loss term associated with the initial condition is incorporated into the loss function; in the second stage, the squared residual term of the governing equation is introduced into the loss function. Numerical results show that the proposed algorithm outperforms the standard fPINN method in both solution accuracy and training iteration speed. For the inverse problem, the numerical results demonstrate that as the iteration number increases, the estimated parameter values progressively converge to their true values and finally stabilize. Full article

Reliable and rapid forecasting of wind turbine output power is vital for operators, particularly day-ahead and intraday market scheduling and reserve allocation. However, the inherent unpredictability, intermittency, and volatility of wind turbine output make forecasting processes difficult. To address this challenge, this study proposes a Sinusoidal Representation Network (SIREN)-based forecasting model for high-accuracy, rapid direct multi-horizon forecasting of wind turbine output power. SIREN is selected due to the periodic and symmetrical mathematical structure of its sinusoidal activation function, which allows the model to represent both low-frequency trends and high-frequency sudden changes in wind energy data. To improve data quality, compensate for asymmetric fluctuations in wind data, and provide more suitable inputs for SIREN training. Several preprocessing steps are utilized before feeding the data into the model. The proposed preprocessing step includes a moving median filter, robust scaling based on median and interquartile range, Winsorizing clipping, and a Hampel filter to reduce the effects of instantaneous noise, outliers, and local peaks without disrupting temporal continuity. Subsequently, a Savitzky–Golay smoothing is applied to attenuate high-frequency measurement noise while preserving curvature, local peaks, and physically meaningful short-term dynamics in the data. The sliding-window approach is used to formulate the multi-horizon forecasting problem directly, and a direct h-step-ahead forecasting architecture is designed, preserving structural symmetry in the time series. The SIREN is trained and tested using MATLAB with the help of two different datasets: Dataset-1 has a 10 min resolution for 1 year, and Dataset-2 has a 1 h resolution for 15 years. The forecast horizon parameter h is considered separately for each step, and the proposed SIREN is independently trained, validated, and tested for each target horizon while maintaining chronological order. The results demonstrate that the proposed model is able to yield high forecast performance for a wide spectrum of horizons ranging from 10 min to 15 days. The accuracy of the proposed model for Dataset-1 is R² of 99.6%, MSE of 0.085%, MAE of 1.7%, and MAPE of 12%, while for Dataset-2, the accuracy is R² of 98.8%, MSE of 0.3%, MAE of 3.6%, and MAPE of 23%. Ablation and sensitivity analyses are conducted to evaluate the impact of the basic components used in the proposed model on forecasting performance. In addition, combative experiments are performed using traditional time series, ML, and DL forecasting techniques to better assess the contribution of the model. The obtained results show that the SIREN-based direct forecasting approach provides strong learning capability, as well as high forecasting accuracy, for both high-resolution and low-resolution wind power data. Overall, its ability to capture the symmetric and periodic characteristics inherent in wind turbine power data makes it a promising alternative for multi-horizon wind power forecasting applications. Full article

Background/Objectives: People with diabetes are more susceptible to viral respiratory infections and worse clinical outcomes related to COVID-19 and influenza. Vaccination is considered an important prevention strategy. This study aimed to analyze the vaccination status against COVID-19 and influenza among people with diabetes mellitus and associated factors. Methods: An analytical cross-sectional study was conducted between May 2024 and May 2025 in 42 Primary Health Care Units in a municipality in Minas Gerais, Brazil. A total of 316 individuals with type 1 or type 2 diabetes mellitus participated in the study. Data were collected using a structured instrument containing socioeconomic, cultural, behavioral, and clinical variables, in addition to verification of vaccination records through physical vaccination cards and information systems. Descriptive analyses and logistic regression models were performed to estimate crude and adjusted odds ratios, with respective 95% confidence intervals. Analyses were performed using Statistical Package for the Social Sciences and Stata. Results: Adherence to COVID-19 vaccination was 21.5%, whereas influenza vaccination adherence reached 85.4%. In the multivariable analysis of COVID-19 vaccination status, previous influenza vaccination (OR = 7.74; 95% CI: 1.81–33.2) and alcohol consumption (OR = 2.11; 95% CI: 1.13–3.89) were positively associated with vaccination. Conversely, access to social media or other communication channels (OR = 0.47; 95% CI: 0.24–0.92) and insulin use (OR = 0.42; 95% CI: 0.21–0.84) were associated with lower odds of COVID-19 vaccination. Regarding influenza vaccination, positive associations were identified for religious affiliation (OR = 6.46; 95% CI: 1.79–23.30), previous COVID-19 vaccination (OR = 10.2; 95% CI: 2.22–47.06), and longer duration of diabetes diagnosis (OR = 3.47; 95% CI: 1.32–9.20). In contrast, alcohol consumption (OR = 0.42; 95% CI: 0.21–0.86), insulin use (OR = 0.35; 95% CI: 0.16–0.76), and absence of medical follow-up (OR = 0.34; 95% CI: 0.13–0.85) were associated with lower odds of influenza vaccination. Conclusions: The findings revealed a heterogeneous vaccination pattern among individuals with diabetes mellitus, in which higher influenza vaccination coverage contrasted with low adherence to COVID-19 vaccination, reflecting not only differences in the historical consolidation of immunization strategies but also contemporary dynamics related to risk perception, trust, and information circulation. The strong association with previous vaccination history suggests that vaccine adherence is part of a continuum of preventive behaviors mediated by the relationship with healthcare services and by the internalization of healthcare practices over time. Full article

Voltage and reactive power control in active distribution networks is a safety-critical and highly dynamic problem, where traditional optimization methods often struggle to balance efficiency and robustness under complex operating conditions. Recently, large language models (LLMs) have shown promise in sequential decision-making tasks, but their direct application to power system control remains limited by the lack of physical grounding and safety guarantees. In this paper, we propose SafeVolt, a closed-loop LLM-based framework that integrates multi-candidate action generation, simulator-in-the-loop evaluation, and a fine-tuned expert judge for safety-aware decision making. In addition, a high-level rule distillation mechanism that converts successful control experiences into reusable operational axioms is introduced to enable iterative self-improvement. Experiments on a standard distribution network scenario demonstrate that the proposed method outperforms representative baselines, achieving substantial improvements in average reward, voltage violation rate, reactive power loss, and system stability. In particular, voltage violations and extreme events are substantially reduced, indicating enhanced operational safety. These results suggest that combining LLM reasoning with physical simulation and structured feedback provides a promising direction for reliable and adaptive power system control. Full article

Individual geophysical inversions reflect only limited physical parameters of the subsurface and often suffer from non-uniqueness. Joint inversion of different geophysical datasets can mitigate this problem by integrating complementary information. In this study, we realize a structurally constrained joint inversion of seismic wave impedance and DC resistivity data using the cross-gradient function. The cross-gradient is discretized via the central difference quotient, and its fundamental properties are analyzed. A two-dimensional joint inversion objective function incorporating cross-gradient constraints is derived and solved using the Lagrange multiplier method. The approach relies solely on structural similarity between the two physical properties and requires no explicit petrophysical relationship. Synthetic model tests are conducted for cases where the two property distributions are structurally consistent and inconsistent, respectively. Results demonstrate that the joint inversion yields more accurate and sharper boundary delineation, geometric shapes closer to the true model, and significantly improved resolution of multiple anomalous bodies, with recovered physical property values approaching the true values and enhanced convergence speed and stability. When the two models are structurally inconsistent, the cross-gradient constraint effectively acts only on regions of common structure without introducing adverse effects or external errors elsewhere. Numerical simulations confirm the validity and reliability of the proposed algorithm in reducing inversion non-uniqueness and improving parameter accuracy. Full article

Climate change introduces severe non-stationarity and high-frequency noise into hydro-meteorological data. This noise degrades the predictive accuracy of traditional data-driven streamflow models. We propose a physics-inspired data enhancement framework coupling the CEEMDAN-based Hilbert-Huang Transform (HHT) with Stochastic Resonance (SR). We applied this framework to the Lanzhou section of the upper Yellow River. HHT isolates the dominant characteristic frequency of the basin’s streamflow system at 0.0026 cycles/day. Using this frequency as a target, we constructed a Bayesian-optimized SR system. The system converts the energy of high-frequency meteorological noise into low-frequency periodic components, facilitating frequency alignment between the meteorological inputs and the hydrological response. We evaluated the SR-enhanced meteorological inputs across three machine learning architectures: Random Forest, XGBoost, and LSTM. All algorithms demonstrated an improved performance. The SR-LSTM model achieved a Nash-Sutcliffe Efficiency (NSE) of 0.91 ± 0.03. This represents a 19% improvement over the baseline LSTM score of 0.79 ± 0.02. The SR-LSTM demonstrated robust accuracy during extreme hydrological events; it achieved a high-flow NSE of 0.89 and effectively mitigated the common peak-underestimation issue by constraining relative peak magnitude errors to approximately −5.08%. Overall, this study presents a practical data enhancement approach for streamflow forecasting under complex climatic conditions. Full article

Street-level concentrations of nitrogen dioxide (NO₂) and fine particulate matter (PM_2.5) pose serious public health risks in European cities, yet accurate multi-year prediction at traffic-dominated sites remains challenging. This study applies XGBoost (XGB) and Random Forest (RF) to predict hourly NO₂ and daily PM_2.5 at two street monitoring sites in Copenhagen, Denmark, trained on 17 years of observational data and evaluated on two independent years. Three-dimensional variational assimilation (3D-Var) and the Extended Kalman Filter (EKF) are then applied as post-processing corrections to the ML predictions using co-located observations. XGB achieved RMSE values of 9.5 and 7.4 µg/m³ for HCAB and JGTV NO₂, respectively, in the 2018 test year. Both DA methods improved substantially on the ML baseline, with 3D-Var reducing NO₂ RMSE by up to 57% and spike event RMSE by up to 51%. EKF achieved near-complete elimination of systematic bias across all configurations. The framework is computationally lightweight and can be applied to any deterministic model prediction at a monitoring station, including outputs from physics- and chemistry-based dispersion models. Overall, the findings show a practical way to improve street-level air quality prediction, with direct relevance for operational forecasting and public health protection. Full article

Grocery shopping remains a heavily car-dependent activity in urban areas, even for short-distance trips within residential neighbourhoods. A primary barrier to shifting toward active travel (walking or cycling) is the physical burden of carrying heavy or bulky goods. This study investigates whether a retailer-managed home delivery service could encourage consumers who currently rely on motorised modes for grocery shopping to shift towards active travel while preserving the in-store shopping experience. The analysis focuses on urban Italian consumers who currently use motorised modes for grocery shopping. Using a Stated Preference (SP) experiment and a Mixed Logit (MMNL) model (n = 88), we analyse the conditions under which such a service may encourage the adoption of active travel modes and support proximity-based shopping patterns. Given the exploratory nature of the study and the small, non-representative sample, the findings should be interpreted as preliminary evidence for urban motorised grocery shoppers rather than as representative of the Italian population. The results indicate a substantial willingness among respondents to adopt the proposed service configuration. Delivery time, service cost, and the availability of delivery time-window selection emerge as critical factors influencing consumers’ choices. Acceptance of the service is also influenced by perceptions of walking and cycling infrastructure quality, trust in the integrity of delivered groceries, preferences for local products, and concerns regarding the working conditions of delivery personnel. Additionally, the model reveals significant heterogeneity in preferences regarding delivery by drone/autonomous vehicle and a 100% reduction in greenhouse gas emissions relative to conventional motorised transport. Younger respondents exhibit a more favourable attitude towards automated delivery technologies, while differences in the valuation of environmental benefits emerge between male and female respondents. The findings suggest that retailer-managed home delivery may represent a promising mechanism for encouraging active travel among current motorised grocery shoppers, while maintaining consumers’ relationship with neighbourhood retail services. These results provide retailers and urban policymakers with valuable insights, suggesting that appropriately designed delivery services may support more sustainable and proximity-oriented shopping behaviours. Such services could potentially contribute to maintaining the accessibility and vitality of neighbourhood retail activities, particularly in ageing urban contexts. Full article

The Atlantic Meridional Overturning Circulation (AMOC), as the core component of the global thermohaline circulation, exerts a profound influence on the Northern Hemisphere climate. Recent observations show that AMOC intensity has weakened by approximately 15% over the past 40 years, yet the traditional theoretical framework dominated by the North Atlantic Oscillation (NAO) cannot fully explain its spatial heterogeneity. This study systematically quantifies the independent driving mechanism of the Arctic Oscillation (AO) on AMOC decline for the first time by integrating multi-source reanalysis data (ERA5, ORAS5) and CMIP6 model output. Theoretical analysis shows that the AO positive phase regulates the stability of AMOC through two coupled pathways: (1) anomalous wind stress curl leads to the weakening of Ekman suction in the subpolar seas (contribution: 42 ± 6%), inhibiting deep-water formation in the Labrador Sea; and (2) increased freshwater flux through the Fram Strait triggers a negative salinity advection feedback, which leads to shoaling of the North Atlantic high-latitude mixed layer by up to 30 m. The cross-scale interaction reveals that the AO interannual variability amplifies the modulation of the AMOC interdecadal trend. This amplification occurs through the positive feedback of sea-ice albedo. When AO and NAO are locked in opposite phases (AO+/NAO−), the AMOC weakening rate increases to 1.8 Sv/decade (1 Sv = 10⁶ m³/s), whereas the same-phase negative condition (AO−/NAO−) yields a moderate decline of 0.5 Sv/decade. This mechanism corrects the underestimation of the traditional wind-driven circulation theory for high-latitude processes and provides a physical attribution for the CMIP6 models’ systematic underestimation of AMOC sensitivity. The study further constructs the “Arctic Oscillation–subpolar basin–AMOC” three-pole coupling theoretical model and confirms that the Arctic amplification effect enhances the AO–AMOC coupling strength by a factor of 2.3 over the full study period (1979–2020; R² = 0.71, p < 0.01), with an even more pronounced enhancement of 2.1 times during the recent two decades (2000–2020; R² increased from 0.28 to 0.59). These findings have direct implications for coastal risk assessment, as AMOC weakening may accelerate sea-level rise along the North American East Coast and increase the frequency of extreme winter storm surges in European coastal areas. The results provide a dynamic basis for IPCC climate risk assessment and have practical application value for the early warning of extreme cold-wave events. Full article

Summer overheating is an escalating challenge for lightweight timber constructions, which inherently lack the thermal mass of traditional masonry. This study investigates the thermo-physical properties of a mycelium-based biocomposite (MBB) insulation produced from industrial wood waste, with particular focus on volumetric heat capacity (C_v). The C_v and thermal conductivity (λ) of MBB were experimentally measured and benchmarked against seven reference insulation materials spanning bio-based, mineral, and petroleum-derived categories, with results visualized on an Ashby diagram. The areal heat capacity (κ) of nine representative wall assemblies was theoretically calculated per EN ISO 13786. Even though the MBB achieved the highest thermal conductivity (λ = 0.0641 ± 0.0024 W·m⁻¹·K⁻¹) among the tested insulation materials, it offers 4.7 times higher C_v than EPS. Analytical modeling indicates a thermal phase shift of 8.2 h for a 185 mm layer, compared to 4.6 h for EPS. The softwood timber + MBB wall assembly achieved an areal heat capacity approaching the lower boundary of traditional masonry performance. These findings demonstrate MBB’s potential as a bio-based, waste-derived insulation for significantly enhancing the thermal inertia of lightweight timber buildings and mitigating summer overheating risk. Full article

To support offline process-parameter screening for Czochralski (CZ) silicon single crystal growth, this paper proposes a surrogate-assisted optimization framework based on an improved Langevin evolutionary algorithm. First, a multi-variable constrained optimization model is established, with the LSA-Transformer-predicted solid–liquid interface deformation used as the objective evaluation and with process-smoothness and physical-feasibility constraints considered. Six key process parameters–heater power, pulling rate, argon flow rate, crystal rotation speed, crucible rotation speed, and magnetic field strength–are selected as decision variables. Second, building on the classical Langevin algorithm, an adaptive inertia weight mechanism, a diversity promoter (DP) operator, and a local escaping operator (LEO) are introduced to improve global exploration and local optima escape in complex search spaces. Verification on 23 classical benchmark functions indicates that the ILEE algorithm shows competitive overall performance and achieves better or comparable results on many functions when compared with particle swarm optimization (PSO), grey wolf optimization (GWO), the original Langevin evolutionary algorithm (LEE), and other baseline algorithms. The proposed framework is then used for offline candidate recipe generation during the crystal equal-diameter growth stage (200 mm, 400 mm, 600 mm, 800 mm, and 1000 mm). The optimized candidate parameter combinations yield lower surrogate-predicted interface deformation under the given LSA-Transformer model and physical constraints. Because these values are not independent CFD or experimental measurements, the results should be interpreted as process-parameter guidance for future physical validation. This work provides a feasible surrogate-assisted offline screening framework for CZ silicon single crystal growth. Full article

To address the issues of limited interpretability and low predictive accuracy in traditional photovoltaic forecasting models, this paper proposes a hybrid forecasting model named HO-Transformer-KAN-PINN. First, Maximal Information Coefficient (MIC) is used to select the key meteorological features: irradiance and temperature. Then, the grey relational analysis combined with cosine similarity is applied to identify similar days. The prediction framework is then constructed. The Transformer-KAN model provides high predictive accuracy and strong interpretability, while embedding physics-informed neural network (PINN) constraints enforces compliance with the underlying physical laws, yielding the Transformer-KAN-PINN framework. Simultaneously, the Hippopotamus Optimization (HO) algorithm is used to optimize the model hyperparameters. Finally, the photovoltaic power combination prediction model of HO-Transformer-KAN-PINN is constructed. This model has achieved excellent results in short-term photovoltaic power forecasting in Yunnan, Gansu, and Australia. Taking winter in Yunnan Province as an example, the forecasting results of this model yield an MAE of 0.3204 MW, an RMSE of 0.4197 MW, a MAPE of 4.9561%, and an R² of 0.9986. Therefore, the hybrid forecasting model proposed in this paper demonstrates a certain degree of advancement and effectiveness. Therefore, it provides reliable technical support for accurate prediction of photovoltaic output. Full article