Search Results (3,575)

In the field of subgrade compaction quality assessment, accurate volume measurement of excavated pits is hindered by non-uniform point cloud distribution, environmental noise interference, and complex irregular boundary features. To address these challenges, this paper proposes a robust volume detection framework that integrates adaptive point cloud refinement and morphological discrimination. First, a pose normalization method employing RANSAC plane fitting and rigid body transformation corrects the spatial orientation of the raw point clouds. To balance data redundancy removal with feature preservation, a gradient adaptive simplification strategy based on local density feedback and K-nearest neighbor estimation is developed. Subsequently, a cross-sectional area calculation model utilizing piecewise-cubic polynomial fitting is proposed to mitigate boundary noise and accurately reconstruct irregular contours. Furthermore, a dynamic outlier removal mechanism based on the Median Absolute Deviation (MAD) and sliding windows is introduced to eliminate non-physical geometric fluctuations. Finally, the total volume is aggregated using a hybrid strategy of Simpson’s rule and a frustum compensation operator. Experimental results on simulated pits with typical topological defects demonstrate that the proposed algorithm outperforms traditional methods, achieving an average relative volume error of less than 0.8%. This approach significantly improves the robustness and precision of sensor-based automated subgrade compaction quality measurement. Full article

To address the uncertainty of the measurement noise covariance matrix in vehicle state estimation, this paper proposes a symmetry-aware extended Kalman filter optimized by a chaotic-gradient strategy. The symmetry-aware concept is introduced from the approximate mirror symmetry of vehicle lateral dynamics under left and right steering excitations. Under identical road adhesion and vehicle operating conditions, the yaw-rate and sideslip-angle responses should exhibit balanced statistical characteristics for positive and negative lateral motions. However, a fixed measurement noise covariance matrix may break this balance and lead to direction-dependent estimation bias or delayed convergence. To improve the statistical consistency of the estimation process, the proposed method adaptively tunes the measurement noise covariance matrix according to the innovation covariance mismatch. A chaotic search mechanism is first used to enhance global exploration, and a variable-step gradient method is then applied to refine the local optimal solution. Through the iterative combination of chaotic traversal and gradient-based refinement, the proposed observer improves the balance between model prediction and measurement correction under stochastic disturbances. The effectiveness of the proposed method is verified through CarSim and MATLAB/Simulink co-simulation. The results show that, compared with EKF, UKF, and AEKF benchmark observers, the proposed CG_EKF provides more accurate estimation of vehicle yaw rate and sideslip angle. Full article

Credit risk evaluation is a key factor in financial intermediation, regulatory capital provision, and risk management in the portfolio. In this study, we compare the deep learning performance for probability-of-default (PD) estimation with a structured financial econometric model using loan-level data of an Indian non-banking financial agency between May and August 2025. Using the interpretation of PD as a conditional expectation, which is in line with reduced-form default-intensity models, we compare deep learning, logistic regression, and gradient boosting using a pure time-based out-of-sample design. Model assessment focuses on discrimination and calibration, where the area under the precision–recall curve (AUC-PR), Brier score, log-loss, and Hosmer–Lemeshow goodness-of-fit tests are utilized. The findings show that deep learning achieves higher accuracy in terms of calibration but a lower Brier score by about 18; this gap could be reduced by comparing logistic regression with statistically significant improvements in formal tests that compare forecasts. In portfolio back-testing, better probability scaling is translated into an actual loss reduction of about 12–13% for the August 2025 cohort. Although the improvements compared with the advanced ensemble techniques are moderate, the results indicate that deep learning improves the estimation of conditional default probabilities because of the better nonlinear modeling and upper-tail risk perception. This study contributes to the literature via its incorporation of machine learning and credit risk assessment into a formalized risk management and econometric assessment system. Full article

We present an offline-first edge telemedicine platform designed for clinics and outreach programs where internet access, power, and IT support are unreliable. The system runs local electronic health record (EHR) and clinical “plug-in” screening services on a single embedded device, accessed through a clinician-facing web app over local WiFi. Data are stored locally with role-based access control and record-level encryption, while interoperability is provided as a best-effort queued synchronization pathway to external systems using HL7 FHIR when connectivity is available. As a representative plug-in, we implement non-invasive anemia screening from fingernail photographs. Images are processed fully on-device: an INT8-quantized YOLOv8n detector extracts nail regions, lightweight color and summary-statistic features are computed per ROI and concatenated, and a supervised regressor estimates hemoglobin. On an NVIDIA Jetson Orin Nano, ROI extraction runs in 22 ms and hemoglobin inference in 34 ms. Across six training strategies (unbalanced, augmented, and KDE-balanced by remark or severity), test RMSE ranges from 2.05–3.13 g/dL; the strongest numeric performance is achieved by severity-balanced SVR (RMSE 2.048 g/dL) and remark-balanced Gradient Boosting (RMSE 2.091 g/dL). Raincloud analyses restricted to true-anemic test cases show that balancing primarily reduces systematic overestimation (which drives false negatives) while augmentation can widen error tails, highlighting the importance of selecting training strategy to match screening objectives rather than optimizing a single aggregate metric. Full article

Plant diversity is a key indicator of ecosystem structure, function, and restoration status, yet its rapid assessment remains challenging in sandy ecosystems where vegetation is sparse, spatially heterogeneous, and strongly affected by exposed soil backgrounds. In such environments, conventional greenness-based spectral indices may not adequately capture species-level variation because plant communities are controlled not only by photosynthetic biomass but also by soil moisture, micro-topography, and dune-related habitat heterogeneity. This study evaluated the potential of Sentinel-2-derived spectral indices for estimating plant α-diversity in the Hunshandak Sandland, northern China. Based on field observations from 888 plots collected during 2017–2024, four α-diversity metrics—species richness, Shannon–Wiener index, Simpson index, and Pielou evenness index—were calculated and compared with 21 spectral indices using correlation analysis, partial least squares regression (PLSR), and random forest (RF) models. The results showed that model performance varied substantially among diversity metrics. Species richness was estimated with the highest accuracy, whereas Shannon–Wiener, Simpson, and Pielou indices showed weaker predictability, indicating that remotely sensed spectral indices were more sensitive to species number than to abundance distribution and evenness. Moisture- and soil-background-sensitive indices, including the Normalized Difference Water Index (NDWI), Modified Normalized Difference Water Index (MNDWI), Bare Soil Index (BSI/BRI), and Chlorophyll Absorption Ratio Index (CARI), showed relatively stable relationships with plant diversity across different vegetation gradients. Although the overall explanatory power was moderate rather than high, the results demonstrate the practical value of Sentinel-2 spectral indices for regional screening of plant diversity patterns in sandy ecosystems. This study provides empirical evidence for biodiversity monitoring and ecological restoration assessment in semi-arid sandy landscapes and highlights the need to integrate environmental covariates, multi-source remote sensing, and phenological information in future studies. Full article

The eastern coast of China, characterized by a pronounced climatic gradient and diverse ecosystems, is an ideal region for exploring the spatiotemporal dynamics of carbon fluxes and their drivers. Based on observations from eight flux tower sites, together with meteorological, remote sensing, and ecohydrological variables from 2001 to 2022, this study developed Back Propagation (BP), Support Vector Regression (SVR), Extreme Gradient Boosting (XGBoost), and Random Forest (RF) models to estimate regional gross primary productivity (GPP), ecosystem respiration (ER), and net ecosystem productivity (NEP). Among them, RF performed best, achieving validation R² values of 0.92, 0.84, and 0.83 for GPP, ER, and NEP, respectively, and was therefore selected for regional upscaling. The regional mean GPP, ER, and NEP were 1578.38, 1286.05, and 334.56 g C m⁻² yr⁻¹, respectively, indicating that the region functioned as a net carbon sink during the study period. GPP, ER, and NEP exhibited a clear spatial gradient, with higher values in the south and lower values in the north. Total regional NEP increased from 344.12 Tg C in 2001 to 517.73 Tg C in 2022, reflecting a continuous strengthening of terrestrial carbon sink strength. Forests contributed most to the regional carbon sink, while the ecosystem-level NEP contribution of croplands increased over time; by contrast, the total carbon sink of wetlands declined because of area loss. These results suggest that ecological restoration, vegetation greening, and land cover optimization jointly enhanced the carbon sink along the eastern coast of China. These findings have important implications for ecological management and green low-carbon development along the eastern coast of China. Full article

The tectonic setting of Taiwan and its surrounding regions is characterized by the complex interaction between the northwest-oriented Ryukyu subduction zone and the east-oriented Manila subduction zone. Within this subduction framework, the elastic thickness of the lithosphere (Te) serves as a critical parameter for elucidating the mechanical behavior of the area. In this study, we employed the admittance–correlation method to estimate Te values across Taiwan and adjacent territories. The findings indicate that sedimentary loading results in an overestimation of the maximum Te by approximately 50 km; after adjustment, the Te values range from 0 to 60 km throughout the study area. On Taiwan, Te values predominantly lie between 20 and 30 km, decreasing to 10–20 km near the margins adjacent to the Ryukyu and Manila subduction fronts. The Philippine Sea Plate exhibits comparatively higher Te values, ranging from 40 to 65 km. The spatial distribution of Te broadly corresponds with major tectonic subdivisions. Statistical analyses reveal a weak negative correlation between Te and surface heat flow (r = −0.44) and a weak positive correlation with shear-wave velocity anomalies at a depth of 100 km (r = 0.22), suggesting that the thermal structure exerts only a moderate influence on lithospheric strength in this region. Nonetheless, within oceanic crustal domains, the relationship between Te and oceanic crustal age largely adheres to models of crustal cooling and lithospheric thickening, consistent with isotherm depths of approximately 200–400 °C. Additionally, dynamic topography associated with slab subduction may locally diminish Te by up to 25 km. Cross-sectional profiles through northern Taiwan and the Philippine Sea block reveal pronounced coupling between subduction geometry and Te distribution. The observed spatial patterns of Te reflect the mechanical imprint of prolonged tectonic evolution, with the orientation of Te gradients generally aligned with the direction of maximum principal compressive stress. Collectively, these results suggest that subduction geometry and tectonic processes are important factors influencing the spatial variability and evolutionary trajectory of lithospheric strength in Taiwan and its environs. Full article

This study investigates the integration of categorical inverter alarm data into data-driven frameworks for photovoltaic (PV) system monitoring. While most existing approaches rely exclusively on continuous SCADA measurements, the potential of categorical operational data remains largely unexplored. In this work, categorical alarm signals are incorporated into power forecasting to enable anomaly detection. The proposed approach is evaluated on a large-scale real-world dataset comprising multiple PV plants and more than 100 inverters, representing over 1000 inverter-years of operation. The four most popular time series forecasting models, including Multi-Layer Perceptron, Long Short-Term Memory, Extreme Gradient Boosting, and Mamba, are used to estimate power output from continuous inputs, while categorical variables are integrated using one-hot encoding and entity embeddings. Anomaly detection is performed by analyzing residuals between predicted and measured power output. The results show that categorical alarm data contain relevant operational information and can be effectively incorporated into forecasting-based monitoring frameworks. However, their impact on predictive performance varies depending on the encoding strategy and model choice, highlighting important trade-offs between model complexity and feature representation. By providing a systematic evaluation of categorical data integration across a large, diverse dataset, this work addresses a gap in the literature and establishes a benchmark for future research on hybrid continuous–categorical approaches for PV inverter monitoring. Full article

In the context of the rapid growth of the digital economy and the continued implementation of China’s “dual carbon” strategy, clarifying the interactive relationships among the digital economy, low-carbon logistics, and the ecological environment is crucial for promoting sustainable regional development and green transformation. Based on the theoretical mechanisms underlying the coordinated development of these three systems, this study constructs a comprehensive evaluation index system for the Digital Economy–Low-Carbon Logistics–Ecological Environment (DLE) system. The entropy weighting method, a modified coupling coordination model, kernel density estimation, spatial autocorrelation analysis, and the barrier model are integrated to investigate the spatiotemporal evolution and driving mechanisms of coupling coordination among the three systems. The results indicate that (1) the development levels of the digital economy, low-carbon logistics, and the ecological environment have generally increased, although their evolutionary trajectories differ across stages. The digital economy shows the most rapid improvement, low-carbon logistics maintains steady progress, and the ecological environment exhibits gradual optimization. (2) From a temporal perspective, the overall coupling coordination of the national DLE system has shown a fluctuating upward trend, with the coordination type gradually evolving from a near-coordination stage to an initial coordination stage, though it remains at a low-to-medium coordination level overall. (3) From a spatial perspective, the coupling coordination degree presents a stable gradient pattern, with higher levels in eastern China, intermediate levels in central China, and lower levels in western China. Medium- and high-coordination areas are gradually extending from coastal regions to inland areas, while regional disparities remain evident. (4) The spatial autocorrelation results reveal significant positive spatial clustering at the provincial level. Both high-value and low-value clusters show a certain degree of stability, indicating clear spatial spillover effects. (5) An analysis of constraining factors reveals that insufficient scale of digital economic development and innovation application capabilities, constraints on ecological and environmental resource carrying capacity and governance, as well as low operational efficiency and delayed transformation of low-carbon logistics, are the primary types of obstacles hindering the coordinated improvement of the three systems. These findings provide empirical evidence and policy implications for leveraging the digital economy to facilitate low-carbon logistics transformation and enhance coordinated regional sustainability. Full article

Frost heave in cold-region pavements is governed by coupled heat and moisture migration, but the specific contribution of vapour transport in multilayer subgrades remains poorly constrained. This study combines field temperature monitoring with analytical modelling to estimate effective thermal conductivities of pavement structural layers and to evaluate vapour-driven moisture fluxes during seasonal freezing. A vertical thermistor array beneath a two-lane highway near Astana (Kazakhstan) and in the adjacent snow-covered ground is used to back-calculate layer-specific conductivities from midwinter temperature gradients by applying Fourier’s law under quasi-steady conditions. Vapour migration is then assessed by two complementary approaches. A diffusion-based formulation, which couples measured vapour-density gradients with air-filled porosity, provides a conservative lower bound and yields very small fluxes, with maximum daily ice deposition of 8.17 × 10⁻⁵ kg·m⁻²·day⁻¹ beneath the pavement and cumulative seasonal masses of order 10⁻² kg·m⁻² (10⁻³ kg·m⁻² under snow). An energy-balance approach, which relates conductive heat flux to latent heat of vapour–ice phase change and introduces an efficiency parameter α, supplies a physically constrained upper envelope. For a central scenario with α = 0.6, daily deposition in the 0.60–1.00 m layer reaches 0.0961 and 0.0330 kg·m⁻²·day⁻¹ beneath pavement and snow, respectively, yielding seasonal totals of 12.1 and 4.1 kg·m⁻². Together, these bounds indicate that vapour migration beneath pavements, although unlikely to be the dominant driver of frost heave, can be substantially more intense than under adjacent snow-covered ground due to steeper temperature gradients in the upper subgrade. Full article

In the domain of river engineering, estimating the total sediment load in rivers is a crucial challenge. For tens to hundreds of kilometers downstream, the additional sand and gravel in the sediment can raise the elevation of channel beds. For highly braided rivers like the Brahmaputra-Jamuna, the accurate prediction of the total sediment load depends on the complex relationships among different hydro-meteorological variables. As a result, manual selection of the lagged features from only antecedent sediment records can produce suboptimal predictions, which can be considered a significant research gap. In addition, the predictive accuracy can be further enhanced through the application of advanced decomposition techniques. To address these deficiencies, we implemented three sophisticated feature selection methodologies: SelectKBest, Mutual Information, and Random Forest utilizing the Boruta Algorithm as an alternative to manual feature selection. Furthermore, we investigated complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), variational mode decomposition (VMD), and the Hodrick–Prescott Filter (HPF) to improve data mining efficiency. Four distinct artificial neural network (ANN) training algorithms were considered: back propagation (BP), cascade correlation (CC), conjugate gradient (CG), and Levenberg–Marquardt (LM), as alternatives to the conventional BP-based training approach. The effectiveness of the variants of the ANN was assessed in comparison to a powerful ensemble learning model, specifically the decision tree (DT). Results indicate that the HPF-enhanced ANN-LM model exhibited the strongest performance metrics when compared to alternative techniques, with values of NRMSE = 0.004, MAE = 455.242 kg/s, NSE = 0.998, and KGE = 0.990. The outcomes from Sobol’s sensitivity analysis suggest that the sediment dynamics in this region can be better predicted through the inclusion of rainfall-based features. Full article

This paper proposes an adaptive residual extended Kalman filter method optimized by a multi-strategy improved parrot optimization algorithm (MIPO-ARKEKF) to improve the kinematic parameter calibration accuracy and efficiency of robotic polishing systems. To address the limitations of the standard extended Kalman filter (EKF), such as truncation-error accumulation during repeated linearization and sensitivity to manually selected noise parameters, an integrated improvement framework is developed. Specifically, a gradient stabilizer based on state-estimation increments is introduced to alleviate estimation degradation caused by accumulated truncation errors, while the proposed MIPO algorithm is employed to adaptively optimize the process and measurement noise covariance matrices, thereby improving the robustness of parameter identification under practical measurement uncertainty. The calibration process is established on the basis of high-precision external measurement data obtained from the robotic polishing system. In benchmark-function tests, MIPO demonstrates superior convergence performance. In physical experiments based on a KUKA KR210 R2700 robot, the proposed MIPO-ARKEKF method reduces the root mean square positioning error from 0.8927 mm to 0.4858 mm, corresponding to a 45.58% improvement in accuracy. Compared with representative hybrid calibration methods, the proposed method achieves comparable compensation accuracy while reducing computation time by 34.88% to 65.08%. Practical polishing experiments on ultra-low-expansion glass lenses further verify that the proposed method effectively improves end-effector trajectory tracking accuracy and polishing quality, providing an efficient solution for high-precision robotic polishing. Full article

The inherent nonlinearity and uncertainty of wind power generation pose significant challenges to the security, stability, and economic operation of power grids. Therefore, accurate and reliable wind power forecasting is crucial for seamless grid integration and effective risk assessment. Existing forecasting models often focus on improving point-prediction accuracy while overlooking effective multivariate dependency modeling and reliable uncertainty quantification, limiting both the informativeness and reliability of their forecasts. This study proposes a Fractional-order Momentum optimized Evidential iTransformer (FoM-EiT) for short-term wind power forecasting from multivariate time series. The proposed model integrates cyclic feature encoding for periodic variables, an inverted Transformer for variable-wise interaction learning, and an evidential output head that jointly produces point forecasts and uncertainty estimates from a shared representation. The proposed fractional-order momentum (FoM) optimization accumulates gradient history over an extended window, thereby smoothing oscillations caused by gradient competition and stabilizing the joint training process. Experiments on four real-world wind farms from different geographical regions show that FoM-EiT achieves competitive point forecasting performance, with $R^2$ values of 0.6342, 0.8211, 0.7844, and 0.9161, and the Wilcoxon signed-rank test indicates that its advantages over the baselines are statistically significant in the vast majority of comparisons. For uncertainty quantification, FoM-EiT achieves Prediction Interval Coverage Probability (PICP) values of 0.9492, 0.9682, 0.9709, and 0.9498, while the Winkler score results further show that its prediction intervals outperform the conformal prediction and quantile regression baselines in terms of overall interval quality. These results indicate that FoM-EiT provides both accurate forecasts and trustworthy uncertainty information, making it a practical tool for dispatch, reserve allocation, and risk-aware short-term power system operation. Full article

Accurately determining the parameters of an unmodeled spacecraft is crucial. Filtering methods that are resilient to uncertainty, employing dual quaternion frameworks to ascertain orientation and position, introduce a design for an extended Kalman filter based on variational Bayesian inference and dual vector quaternions (VB-DVQEKF) to carry out parameter estimation for a non-cooperative spacecraft. The system kinematics and dynamics are modeled using dual vector quaternions, rendering the representation manifestly concise. The method achieves thoroughness by accounting for the coupled interactions between translational and rotational motions. Furthermore, to address uncertainties in the measurements, a variational Bayesian approach is employed for the dependable simultaneous estimation of state parameters and measurement noise covariance. Mathematical simulations are used to verify the proposed VB-DVQEKF, and its robust capabilities are demonstrated through comparisons with several conventional parameter estimation techniques, including the conventional DVQ-EKF and the Sage–Husa adaptive DVQ-EKF (SH-DVQEKF). Quantitative results based on root-mean-square error (RMSE), convergence time, and final estimation error confirm that the proposed VB-DVQEKF achieves the smallest steady-state error among the compared methods and remains stable under white-burst, gradient (drift), and outlier-type measurement anomalies. Full article

In this paper, a flexible steady-state model of a highly integrated, natural convection-driven condensing methanol reactor was developed. The flowsheet model includes 1D submodels of the different sections of the integrated reactor–condenser and includes a method to estimate the maximum possible natural convection-driven flow. Experimental data are used to create a shortcut description for the heat transfer coefficients in the model. The model results indicate that when heat losses can be mitigated, autothermal operation is possible. The major part of the heat integration takes place in the economizer section; however, a significant amount of heat transfer occurs at the catalyst bed also. The model predicts that the loop mass flow and single-pass conversion strongly depend on the catalyst bed inlet temperature. Experimentally measured catalyst preheater and condenser duties suggest, however, that the model-calculated mass flow is likely too low and that it is less dependent on the catalyst bed inlet temperature than the model predicts. A possible cause for this is the neglect of radial temperature gradients in the catalyst bed in the model, overestimating the conversion. Another possible cause is a measurement error in the bed inlet temperature, causing the actual temperature to be lower than the measured value. Natural convection calculations show that the maximum achievable flow strongly depends on the single-pass conversion and that given a single-pass conversion, a minimum temperature difference is required for flow in the right direction. Sensitivity analyses (neglecting heat losses to the environment) show that with the current heat transfer description, the feasible operating range for autothermal, natural convection-driven flow is sizeable. However, at lower recycle mass flows, heat transfer is too fast, leading to premature condensation in the economizer section. If the heat transfer coefficient is smaller than the currently predicted value, autothermal operation is possible in a wide range of conditions. If heat losses are mitigated, the maximum productivity of 2000 ${\mathrm{kg}}_{\mathrm{MeOH}}{\mathrm{m}}_{\mathrm{cat}.}^{-3}{\mathrm{h}}^{-1}$ is achievable at high pressure, a moderate catalyst bed inlet temperature and a low condenser temperature. Full article