Search Results (13,345)

Tight oil horizontal wells in the Mahu block of the Junggar Basin commonly show rapid production decline and limited target-domain samples. These characteristics make accurate production prediction difficult. This work aims to address the small-sample overfitting problem of tight oil horizontal well production prediction in Mahu Sag with rapid production decline and limited measured well data. The concept of transfer learning is introduced to address the issue of insufficient target domain samples, and the Pearson correlation coefficient is utilized to select the main controlling factors for production from the production data. Next, based on the features extracted by the temporal convolutional network at different data scales, a multi-head attention mechanism is introduced to capture the dependencies across different time steps. Subsequently, an improved sparrow search algorithm is employed to optimize the hyperparameters of the bidirectional long short-term memory network. Finally, the bidirectional long short-term memory network is integrated to further extract the nonlinear features learned by the temporal convolutional network to conduct production prediction. Tailored to the exploitation conditions of tight oil horizontal wells in this block, a tight oil production prediction model based on transfer learning and the multi-head attention mechanism is proposed. Experimental results demonstrate that, compared with the standard bidirectional long short-term memory network, the proposed model’s evaluation metrics show a 60.93% decrease in root mean square error, a 78.53% decrease in mean absolute percentage error, and a 43.68% increase in coefficient of determination. This verifies the effectiveness of transfer learning in solving small-sample modeling challenges, providing precise technical support for the optimization of tight oil fracturing parameters and stimulation treatments in the Mahu block. The novelty of this work lies in the integration of multi-head attention temporal convolution network, quantum sparrow optimized bidirectional long short-term memory network and cross-block transfer learning for small-sample tight oil forecasting. Full article

To further improve prediction accuracy, a VMD-VPPSO-LSTM model is proposed in this study, which combines Variational Mode Decomposition (VMD) for signal decomposition, Velocity-Pause Particle Swarm Optimization (VPPSO) for parameter optimization, and Long Short-Term Memory (LSTM) for runoff prediction. The model was evaluated at Huangtaiqiao station in the Xiaoqing River Basin, Dawenkou station in the Dawen River Basin, and Tangnaihai station in the source region of the Yellow River Basin. The proposed model achieved the best overall performance among all comparison models, with Nash–Sutcliffe Efficiency (NSE) values of 0.970, 0.962, and 0.994 and Root Mean Square Error (RMSE) values of 1.357, 0.989, and 46.804 at the three stations, respectively. Compared with VMD-LSTM, VPPSO further reduced the RMSE at all stations and maintained training-test NSE gaps below 0.006, indicating strong generalization performance. The model also achieved the lowest Peak Percent Standard Deviation (PPSD) values for high-flow events, reaching 9.03%, 14.42%, and 3.88% at the three stations, respectively. These results demonstrate that VMD-VPPSO-LSTM is a reliable and effective model for daily runoff prediction. Full article

Air pollution negatively impacts human health and environmental sustainability, particularly in areas with high industrial activity. This study comparatively evaluated deep learning-based models for estimating PM₁₀ and SO₂ pollutants in Dilovası and Ereğli (Turkey), industrial areas with high pollutant loads. The study utilized Recurrent Neural Networks (RNNs), Long Short-Term Memory (LSTM), Gated Recurrent Units (GRUs), an RNN–GRU stacked hybrid model, an attention-based hybrid model, and the proposed GRU–LSTM dual-path hybrid model. The proposed method consists of four main stages: data conversion into a time-series format, data preprocessing and feature generation, model architecture development, and model training and performance evaluation. The dataset consisted of 365 daily PM₁₀ and SO₂ observations obtained from the Air Monitoring Center for the Dilovası and Ereğli monitoring stations. Model performance was evaluated using the coefficient of determination (R²), training time, root mean squared error (RMSE), mean squared error (MSE), and mean absolute error (MAE) metrics. The findings showed that the hybrid models provided higher accuracy compared to the single-track models. Specifically, the proposed GRU–LSTM dual-path hybrid model produced the highest R² and lowest error values for both pollutant parameters in both the Dilovası and Ereğli regions. In Dilovası, this model achieved R² = 0.97 for SO₂ and R² = 0.96 for PM₁₀; in Ereğli, it reached R² = 0.92 for SO₂ and R² = 0.98 for PM₁₀. Thus, it has been shown that the GRU–LSTM dual-path hybrid model, which models short-term and long-term temporal dependencies in parallel, is an effective and reliable method for air pollutant forecasting in industrial areas. These findings demonstrate the potential of the proposed model to support air quality monitoring, early warning systems, and environmental decision-making in industrial regions. Full article

The digital documentation of existing buildings is particularly important when original construction drawings or reliable as-built records are unavailable. This study evaluates the feasibility and selected dimensional consistency of a locally registered Scan-to-BIM workflow integrating unmanned aerial vehicle (UAV) photogrammetry for exterior documentation and smartphone LiDAR for interior data capture. A two-storey reinforced-concrete building with unavailable original project documentation was selected as a single case study. Exterior images were acquired using a DJI Mavic 3E (DJI, Shenzhen, China), while interior spaces were scanned using an iPhone 16 Pro Max (Apple Inc., Cupertino, CA, USA) and Polycam v5.1.5 in LiDAR mode. The UAV images were processed in Agisoft Metashape Professional 2.2.0 to generate the exterior photogrammetric point cloud, and the smartphone LiDAR data were organised with this dataset in Autodesk ReCap Pro 2025. Both point clouds were then used as geometric references for creating a geometry-oriented as-is BIM model in Autodesk Revit 2025. To evaluate selected dimensional consistency, 32 independent field measurements collected using a steel tape measure and a laser distance meter were compared with corresponding BIM-derived dimensions. The dimensional comparison yielded a mean absolute error (MAE) of 29.56 mm, a root mean square error (RMSE) of 31.21 mm, a maximum absolute error (MaxAE) of 46.00 mm, and a mean signed error (MSE) of +29.56 mm. These results indicate centimetre-level dimensional consistency for the selected validation dimensions, with a small systematic positive offset in the BIM-derived dimensions. The workflow can support preliminary geometric documentation and general as-is BIM for a small existing building, but it does not demonstrate survey-grade georeferencing, full registration accuracy, modelling reproducibility, or general applicability without further testing. Full article

Background: Electroencephalographic (EEG) functional connectivity analysis requires multiple signal-processing, source-modelling, and statistical steps that can limit its adoption in clinician-led randomised controlled trials (RCTs). NeuroStat was developed as a prototype research tool to integrate this workflow; formal usability validation with clinician end-users has not yet been conducted. Methods: NeuroStat is an open-source Python/PyQt6 desktop application that integrates automated artefact removal (a Generalised Eigenvalue Decomposition for Artefact Identification [GEDAI] pathway and a traditional Artefact Subspace Reconstruction (ASR)/Independent Component Analysis (ICA)/ICLabel pathway), boundary element model (BEM) source localisation using the Desikan–Killiany atlas (68 cortical regions), Phase Lag Index (PLI) connectivity estimation across five canonical frequency bands, and RCT-oriented statistical analysis. Evaluation separated sensor-space and source-space claims: a sensor-level simulation (repeated across five independent random seeds) tested preprocessing robustness, a repeated source-space simulation tested recovery of a known cortical parcel-pair contrast after forward projection and inverse reconstruction, a PhysioNet benchmark tested posterior Desikan–Killiany alpha PLI in 20 healthy adults, and an illustrative application to 20 sessions from a published chiropractic RCT demonstrated real-world workflow applicability. Results: In the sensor-level simulation benchmark, the Traditional pathway achieved a mean absolute error of $0.168\pm 0.017$ PLI units and root mean squared error of $0.219\pm 0.045$ (mean ± SD across five independent random seeds) across all artefact conditions. In the source-space simulation, reconstructed alpha PLI for the known bilateral lateral-occipital parcel pair exceeded anterior control edges across 60 repeated condition runs (mean known-control difference = 0.105 PLI units, 95% CI 0.096–0.114; $t\left(59\right)=22.61$, $p<0.001$). In the PhysioNet source-space benchmark, posterior Desikan–Killiany alpha PLI was higher during eyes-closed than eyes-open rest (Cohen’s $d=0.85$, $p=0.001$; 16/20 subjects showing the expected direction) after ICLabel-enabled preprocessing. In the pilot RCT application, all 20 sessions completed processing without manual intervention, with default-mode network alpha PLI showing a pre-to-post change of +0.071 in the intervention group versus +0.015 in the active control group. Conclusions: NeuroStat integrates preprocessing, source-space construction, connectivity estimation, and statistical reporting within a parameter-logged desktop workflow for EEG functional connectivity studies. Current evidence supports initial technical feasibility, sensor-level preprocessing robustness for one pathway in controlled simulations, source-space recovery of a known parcel-level contrast, source-space sensitivity to an expected posterior alpha resting-state contrast, and error-free processing across 20 real RCT sessions in a pilot workflow demonstration. Formal usability testing, test–retest reliability analysis, participant-specific source-model validation, and clinical-population validation remain necessary before clinician-facing or trial-deployment claims can be made. Full article

Consistent laser cutting quality is one of the problems associated with the nonlinearity of relationships between process parameters and output responses. This problem acquires particular importance when it comes to cutting advanced nanocomposites, which requires precise tuning. Despite the wide adoption of intelligent modelling, few studies have investigated the comparative efficiency of various approaches based on the use of the same dataset. In this research, the effectiveness of three models—Artificial Neural Network (ANN), Adaptive Neuro-Fuzzy Inference System (ANFIS), and Fuzzy Logic System (FLS)—was tested on experimental data related to the CO₂ laser cutting of ABS/CNT nanocomposites. Input parameters included laser power and cutting speed, whereas HAZ width, kerf width, and surface electrical resistivity were used as output data. Data was split into training, testing, and validation datasets; models were created using supervised machine learning. Model performance was evaluated using Root Mean Square Error (RMSE). Analysis of results showed that ANN demonstrated acceptable predictive capabilities, yielding correlation coefficients (R) close to 1 (≈0.99) and RMSE values of 0.2956 for HAZ, 0.2061 for kerf width, and 2.3655 for surface electrical resistivity. Prediction by means of FLS was able to identify general tendencies; however, it produced RMSE values of 0.4741 for HAZ, 0.6297 for kerf width, and 1.9258 for surface electrical resistivity. Finally, the ANFIS model proved to be the most reliable model, yielding the lowest RMSE values for HAZ (0.2784), kerf width (0.0450), and surface electrical resistivity (0.0905). In conclusion, this research shows that ANFIS can be used effectively for building models predicting laser cutting processes; therefore, it represents an approach worth using in future investigations in this field. Full article

The thermomechanical deformation behavior of high-entropy alloys (HEAs) is governed by complex interactions among strain, strain rate, and deformation temperature, necessitating robust constitutive models for accurate flow stress prediction and process optimization. In this study, a novel Zerilli–Armstrong (NZA) constitutive model was developed to characterize the hot deformation behavior of FeCoCrNi HEA. The proposed NZA model incorporates enhanced descriptions of strain hardening and deformation-temperature coupling to improve prediction accuracy. The predictability of the proposed NZA model was systematically evaluated and compared with that of the original Zerilli–Armstrong (ZA) and modified Zerilli–Armstrong (MZA) models using key statistical indicators, including the correlation coefficient (R), average absolute relative error (AARE), and root mean square error (RMSE). The findings demonstrate that the NZA model exhibits superior predictive performance, achieving an excellent correlation coefficient (R) of 0.997, a low AARE of 4.22%, and an RMSE of 5.82 MPa. These results confirm the reliability and effectiveness of the proposed constitutive framework in accurately describing the thermomechanical flow behavior of FeCoCrNi HEA over a wide range of deformation conditions. The proposed NZA model provides a robust framework for optimizing hot-forming processes and improving the manufacturing performance of HEA-based components while promoting sustainable manufacturing through reduced material consumption, enhanced energy efficiency, and support for SDGs 9 and 12. Full article

Temperature variability and weather-related fluctuations significantly affect the energy, agricultural, and industrial sectors that are highly sensitive to meteorological changes. These conditions may lead to financial losses caused by demand fluctuations and operational disruptions. This study aims to develop a fractional weather-derivative pricing model based on temperature dynamics by integrating the Ornstein–Uhlenbeck (OU) process, the classical Black–Scholes model (BSM), and the fractional Black–Scholes model (fBSM). Daily temperature data from 2016 to 2025 obtained from the Bandung Geophysical Station, West Java, Indonesia, were used as the basis of analysis. Temperature dynamics were modeled using an OU process, and parameter estimation was conducted using Ordinary Least Squares (OLS). The strike price was determined using Historical Burn Analysis (HBA), whereas weather-derivative pricing was performed using call and put option approaches under both the BSM and fBSM frameworks, incorporating the Hurst parameter to capture long-term memory effects. The results indicate that the fractional Black–Scholes model analytical solution is obtained using the Daftardar–Gejji Aboodh method. Furthermore, the OU process successfully captured daily temperature dynamics, yielding a Mean Absolute Percentage Error (MAPE) of 4.344% and a Root Mean Square Error (RMSE) of 1.396 C, indicating high predictive accuracy across both relative and absolute error measures. In addition, the fBSM consistently generated higher option values than the classical BSM, particularly under higher observed temperatures during the study period and at higher strike prices. These findings demonstrate that long-term memory significantly influences effective volatility and option valuation. This study is expected to contribute to the development of weather derivative models that more realistically represent temperature dynamics and to serve as a reference for weather derivative pricing, hedging, and decision-making, as well as for more measurable, systematic, and sustainable climate-related financial analysis using derivative pricing frameworks. Full article

Millimeter-wave radar enables non-contact monitoring of cardiac activity and therefore has the potential to reconstruct electrocardiogram signals without surface electrodes. However, existing radar-based electrocardiogram reconstruction methods still suffer from incomplete extraction of heartbeat-related information and insufficient modeling of electrocardiogram-related features, which limits reconstruction accuracy. To address these issues, this study proposes a millimeter-wave radar-based electrocardiogram reconstruction method that integrates a respiratory-harmonic-suppressed multi-channel signal-processing frontend with the proposed CA-WTBNet deep reconstruction network. First, based on maximal overlap discrete wavelet transform-based multi-resolution analysis, respiratory harmonics mixed into heartbeat-related components are suppressed by combining respiratory harmonic detection with a heart-rate frequency protection strategy, while cardiac-related information is preserved as much as possible. A multi-channel input representation is then constructed. Meanwhile, the proposed deep reconstruction network is developed to jointly model complementary channel-wise features, local waveform morphology, and temporal dependencies by integrating channel-attention mechanisms, convolutional residual modules, window-based Transformer blocks, and bidirectional long short-term memory. Experiments conducted on the public dataset show that our method achieves an average Pearson correlation coefficient of 0.9641, a mean normalized root mean square error of 0.0458, an average R-peak F1 score of 0.9956, and an average R-peak timing error of 3.13 ms on the test set. In comparison with related studies on the same public Resting dataset, the proposed method achieves the best overall performance among the compared methods, with a 0.53% improvement in Pearson correlation coefficient and a 10.20% reduction in normalized root mean square error over the best-performing compared method. Full article

Effective evaluation of the accuracy of multi-source NO₂ products from different satellites and reanalysis is of great significance for data fusion and application. Based on NO₂ observation data from Pandora stations worldwide, we verify and compare the accuracy of the total column density of NO₂ (TOTNO₂) from OMI, TROPOMI, GOME-2 satellites and CAMS reanalysis. The mean biases of the four TOTNO₂ datasets relative to the Pandora station observation data are all negative, indicating that all four TOTNO₂ products show systematic underestimation with respect to Pandora. Overall, TROPOMI has the highest correlation (R = 0.88) and the smallest root mean square error (RMSE = 4.83 Pmolec·cm⁻²), suggesting that among the four TOTNO₂ products, the accuracy of TROPOMI TOTNO₂ is higher compared with the other TOTNO₂ products. The accuracies of OMI and GOME-2 are in the middle, while the performance of CAMS is the poorest. The TOTNO₂ values and accuracies from the four TOTNO₂ products both show a seasonal characteristic. Among the four TOTNO₂ products, the accuracy is higher in summer, and the error increases in autumn and winter. After performing linear fitting correction on the four NO₂ products, the mean biases of each data are reduced by more than 79%, and the RMSE decreases by 4–28%. The consistency of the four TOTNO₂ products with the ground-based observation data is significantly improved. Full article

Real-time assessment of reading comprehension remains a challenge in educational research. Traditional evaluation methods, such as questionnaires, provide delayed and retrospective measures and therefore do not capture the dynamic nature of comprehension during reading. This exploratory study investigates whether beta-band electroencephalography (EEG) activity can be used to estimate EEG-derived indicators related to reading comprehension during academic reading. The study included 40 university students who read a conceptually demanding scientific text while EEG signals were continuously recorded. Beta-band activity (13–30 Hz) was extracted from six cognition-related channels and segmented into non-overlapping 2 s windows. Principal component analysis (PCA) was applied for dimensionality reduction, followed by kernel ridge regression (KRR) for prediction. At the window level, the proposed KRR–PCA framework achieved a mean absolute error (MAE) of 5.797, a root mean square error (RMSE) of 7.783, an MAE-based accuracy of 94.2%, and an explained variance of R² = 0.275 on a held-out test set. At the participant level, aggregated predictions showed a significant correlation with questionnaire-based comprehension scores (r = 0.59), indicating that EEG-derived features captured meaningful inter-individual differences. The framework also generated time-resolved prediction profiles that reflected fluctuations in EEG-derived comprehension estimates during reading. These findings suggest that beta-band EEG contains information related to reading comprehension and may support the development of future EEG-based educational monitoring systems. Further validation using larger cohorts and time-resolved comprehension measures is needed to confirm the practical applicability of the approach. Full article

PM_2.5 is a major air pollutant that threatens urban air quality and public health. Its concentration is influenced by both meteorological conditions and air pollutants, exhibiting complex nonlinear and temporal characteristics. Traditional statistical methods are limited in their ability to model complex relationships among environmental variables, while machine learning models still require improvements in hyperparameter optimization and interpretability. Therefore, developing an accurate and interpretable PM_2.5 estimation model remains an important research objective. This study used daily air-quality and meteorological data collected in Wuhan from 2016 to 2025 to develop six machine learning models: Decision Tree (DT), Random Forest (RF), XGBoost, LightGBM, Support Vector Machine (SVM), and Multilayer Perceptron (MLP). The Particle Swarm Optimization (PSO) algorithm was employed to optimize the hyperparameters of these models. By comparing the root mean square error (RMSE), coefficient of determination (R²), and mean absolute error (MAE) of each model on both the training and test sets, the PSO-MLP model was identified as the best-performing model. Furthermore, the Shapley Additive Explanations (SHAP) method was applied to perform both global and local interpretation analyses of the best-performing model. The results indicate that the PSO-MLP model achieved the highest estimation performance among all evaluated models, with an R² value of 0.746 on the test set. SHAP analysis revealed that CO, Temperature (Temp), and NO₂ were the most influential predictors, while all variables exhibited distinct nonlinear relationships with PM_2.5 concentration. These findings may contribute to PM_2.5 concentration estimation, air-quality management, and environmental decision-making. Full article

Reliable outdoor localization is essential for autonomous mobile robots, where the Global Navigation Satellite System (GNSS) is widely used to provide global positioning information. However, GNSS signals are often degraded in real-world environments due to occlusions, multipath effects, and environmental interference, leading to unstable localization and degraded navigation performance. This paper proposes an adaptive multi-sensor fusion framework for robust outdoor localization and path tracking under weak GNSS conditions. The proposed system integrates GNSS, LiDAR, wheel odometry, and inertial measurement unit (IMU) measurements within an Extended Kalman Filter (EKF) framework. To address the limitations of GNSS, an adaptive weighting mechanism is introduced to dynamically adjust the influence of GNSS observations based on signal quality indicators. Furthermore, a GNSS quality-aware mode-switching strategy is developed, enabling seamless transition between GNSS-dominant localization and multi-sensor fusion-based localization. In the fusion mode, LiDAR, odometry, and IMU jointly provide robust pose estimation, while GNSS acts as a weak global constraint. The IMU further enhances heading estimation, improving orientation stability and path tracking performance. The estimated pose is then used for trajectory tracking using a path-following controller. Experimental results conducted in outdoor environments demonstrate that the proposed framework significantly improves localization robustness and path tracking performance under degraded GNSS conditions. Compared with raw GNSS localization, the proposed method reduces the mean localization error by 47.2% and decreases the root mean square localization error by 55.5%, while maintaining smoother and more continuous trajectory estimation in weak GNSS environments. Full article

The emerging potential of low-Earth-orbit (LEO) satellite-based Positioning, Navigation, and Timing services has increased the need for real-time, stable, and accurate orbit determination techniques. Here, we propose a method for estimating sub-meter-level LEO satellite orbits using Global Navigation Satellite System (GNSS) code pseudorange observations. To mitigate ionospheric delay, a dual-frequency ionosphere-free combination was applied, while code-carrier smoothing was employed to reduce code observation noise. A satellite weighting model based on Signal-in-Space Range Error was developed to reflect the orbit and clock error characteristics of different GNSS, and a robust weighting scheme was applied to alleviate the impact of observation outliers. Further, Galileo High Accuracy Service corrections compensated for orbit, clock and code bias errors. The algorithm was validated using the GNSS observation data collected from the Sentinel-6A satellite on 10 August 2023. Each successively applied technique gradually improved orbit determination accuracy, achieving up to a 51% reduction in 3D root mean square error (RMSE). The final RMSE values in the radial, along-track, cross-track, and 3D components were 39.4, 18.8, 23.5, and 49.6 cm, respectively. Temporal analysis showed no distinct periodicity in orbit errors and no significant correlation with satellite visibility or ground track. Full article

To address the non-stationary and non-linear characteristics of vibration signals collected by sensors in pumped-storage units, as well as their susceptibility to strong background noise interference, this paper proposes a joint signal denoising method combining parameter-adaptive Variational Mode Decomposition (VMD) and wavelet thresholding. First, the Improved Particle Swarm Optimization (IPSO) algorithm is utilized to adaptively optimize the key parameters of VMD using a comprehensive fitness function as the objective, thereby achieving the optimal decomposition of the signal. Subsequently, a cross-correlation analysis method is introduced to screen the decomposed components, followed by a secondary denoising process using a wavelet threshold to accomplish the final signal denoising. Experimental validations using simulated run-out signals and field-measured sensor data from a pumped-storage power station, along with comparisons against other methods, demonstrate that the proposed method can eliminate noise more effectively. It significantly improves the signal-to-noise ratio (SNR) and reduces the root mean square error (RMSE). Consequently, this study provides a reliable data foundation for the subsequent research and analysis of the units, demonstrating substantial practical engineering significance. Full article