Search Results (134)

This work aims to study and improve the long-term stability of conductimetric biosensors for urea detection in clinical and environmental samples, which are fundamentally limited by complex thermal and temporal drifts due to temperature-sensitive enzyme kinetics, variations in ionic mobility, and the progressive degradation of the sensing layer. The biosensor targets the urea concentration range 0.01–30 mM, validated against experimental data and covering the clinically relevant range for blood urea detection (2.5–7.5 mM), urine (20–40 mM), and environmental monitoring applications. Conventional calibration techniques, such as the conventional calibration method (based on reference measurements), and purely deterministic correction methods, such as deterministic methods (based on known fixed equations), often prove insufficient because they struggle to capture the non-stationary and inherently stochastic nature of these drifts. In this work, we propose an original hybrid probabilistic framework that synergistically combines machine learning and Bayesian inference for robust adaptive drift compensation. A Random Forest model is first implemented to model the deterministic nonlinear relationships between environmental parameters (temperature, pH, CO₂ concentration) and the sensor response. The residual temporal drift is then explicitly modeled as a non-stationary latent stochastic process using Bayesian inference based on a Gaussian process. This approach allows continuous online model updating, real-time uncertainty quantification, and automatic detection of anomalies. The models were trained and validated on a large dataset obtained from multiphysics simulations carried out in COMSOL Multiphysics 5.6. These simulations incorporated enzymatic reactions, thermal effects, and chemical dynamics taking place inside the sensor. Experimental results show that the hybrid approach substantially enhances sensor performance, lowering the root mean square error (RMSE) to below 0.8 μS/cm (corresponding to less than 0.5% of the full-scale response) over a wide temperature range (15–45 °C) and across extended operating periods. This represents a clear improvement over conventional compensation method. By merging the predictive power of ensemble learning with a probabilistic Bayesian model of dynamic drift, this study introduces a fresh perspective on the design of intelligent, self-adaptive, and drift-resistant conductimetric biosensors. The proposed framework holds strong potential for reliable, long-term autonomous operation in urea reliable, long-term autonomous operation in urea monitoring across biomedical diagnostics (kidney/liver function assessment) and environmental surveillance (water eutrophication prevention). Full article

Laser powder bed fusion (LPBF) is a widely utilized metal additive manufacturing (AM) process for fabricating intricate geometries with high mechanical strength. However, achieving defect-free parts remains challenging due to complex thermodynamics and process variability. Component quality is primarily determined by mel-pool morphology, which depends on key process parameters such as laser power, scan speed, and layer thickness. Improper parameter selection causes defects like porosity (keyhole and lack of fusion), balling, and residual stresses, compromising structural integrity. Optimizing these parameters is crucial but difficult due to the multi-scale, multi-physics nature of the process, which traditionally relies on costly, time-intensive experimental trials. We present results from a data-driven approach using machine learning (ML) models to predict and optimize LPBF melt-pool characteristics, reducing reliance on trial-and-error experimentation. We find that laser power and scan speed predominantly influence the melt-pool formation. Higher scan speeds produce more favorable melt pools, whereas excessive laser power at low scan speeds leads to deep keyhole defects. To predict and classify melt pools efficiently, several ML models are deployed, including logistic regression, decision trees, ensemble learning, and fully connected neural networks. The standard neural network achieved the highest cross-validated macro-F1 score of 0.978 ± 0.014, while the weighted neural network achieved the highest recall for the rare optimal melt-pool class, 0.967 ± 0.050. These findings show that class-weighted learning provides a recall-oriented strategy for identifying suitable LPBF process windows, while avoiding overreliance on single train-test split performance. The findings underscore the effectiveness of ML in accurately classifying LPBF melt pools to rapidly identify optimal process parameters. Full article

In this study, an advanced surrogate model is proposed to simultaneously predict five key output variables, including deformation, stress, temperature, current density, and resonance frequency. This study used two models: Gaussian Process Regression (GPR) and an ensemble model based on Random Forest and XGBoost. By generating 10,000 design samples using the Latin Hypercube sampling method and performing simulations in COMSOL Multiphysics, as well as applying eight preprocessing methods, GPR achieved a mean absolute percentage error (MAPE) between 0.81% and 2.58%, whereas the ensemble model’s MAPE ranged from 3.05% to 9.20%. The ensemble model offers substantially faster training, whereas GPR achieves higher prediction accuracy across all output variables. Additionally, a 5-fold cross-validation scheme was implemented to ensure reliable model evaluation. This surrogate model, achieving multi-objective prediction with strong scalability due to efficient preprocessing and sampling strategies, is an effective step in reducing computational costs and accelerating the design process of MEMS actuators. Full article

Soil moisture (SM) governs land–atmosphere exchanges and strongly influences agricultural management and hydrological assessment, yet high-resolution mapping remains challenging due to sensor-specific confounding effects and limited field observations. This study develops a practical workflow for point-scale SM estimation and wall-to-wall mapping by integrating multi-sensor remote sensing predictors with ensemble learning. A compact predictor set was constructed from Sentinel-2 optical indices, Sentinel-1 SAR descriptors (σVV and the polarization ratio σVH/σVV), and topographic information, collocated with in situ SM measurements along a transect in the study area. Three tree-based regressors—Random Forest, XGBoost, and CatBoost—were trained under an identical feature configuration and evaluated using R², Root Mean Square Error (RMSE), and Mean Absolute Error (MAE) together with predicted–observed diagnostics. A stacking ensemble was then implemented using leakage-controlled K-fold out-of-fold predictions to generate meta-features, with a Decision Tree as the meta-learner tuned via a grid search. Results show that base learners achieve comparable skill (R² ≈ 0.60–0.62; RMSE ≈ 0.038–0.039), while stacking improves test accuracy (RMSE = 0.0346) and provides a stable mapping-ready model. The trained framework was transferred to stacked raster predictors to produce spatially continuous SM maps, revealing coherent moisture heterogeneity across the region. Accordingly, the objective of this study is to develop a compact and application-oriented point-to-map workflow for high-resolution soil moisture estimation by integrating Sentinel-1/2-derived predictors with stacking-based model fusion, rather than to propose a new physically based retrieval model. Full article

Accurate simulation of landfalling typhoons is essential for urban resilience in the densely populated Pearl River Delta. Using Super Typhoon Mangkhut (2018) as a case study, this paper evaluates the Weather Research and Forecasting (WRF) model through a contribution analysis designed to disentangle the roles of surface layer, planetary boundary layer (PBL), urban canopy model (UCM), and eddy-coefficient/diffusion closure parameterizations in wind-hazard prediction. Model results are validated against observations at the Hong Kong Observatory headquarters (HKO) and King’s Park (KP) stations, demonstrating that the hierarchy of physical controls is strongly metric-dependent. Substantial and structured spread is found among the tested configurations. Controlled comparisons show that PBL selection is the primary driver of variability in peak timing and high-wind persistence, whereas surface-layer formulation and diffusion closure exert secondary but systematic influences by shifting distributional centers and reshaping variability and upper tails. Urban canopy effects are comparatively weaker in aggregate but become more apparent during the impact and recovery phases. Overall, the results confirm that no single parameterization is consistently optimal across all metrics and motivate a multi-objective physics-selection strategy, in which multi-physics ensembles are used to better represent uncertainty in wind-event duration and associated loading risks in complex urban environments. Full article

Bipolar plates are critical components of proton exchange membrane fuel cells (PEMFCs), strongly influencing thermal management, mechanical stability, and overall system efficiency. In this study, an integrated framework combining multiphysics simulation, artificial intelligence (AI), and data augmentation techniques was developed for PEMFC bipolar plate optimization. A coupled thermal–structural finite element model was established in COMSOL Multiphysics to evaluate temperature distribution, thermal stress, and structural deformation under varying operating conditions. A total of 80 parametric design cases were generated by varying six key parameters: hole radius, plate thickness, heating power, manifold pressure, plate number, and heat transfer coefficient. The dataset was expanded using SMOTE, GAN, and LLM-based augmentation techniques and used to train ANN, LR, RF, XGBoost, and SVR models. Model performance was evaluated using 5-fold cross-validation with MAE, RMSE, and LogCosh metrics. The results showed that ensemble tree-based methods, particularly RF and XGBoost, achieved the highest prediction accuracy and computational efficiency. XGBoost produced the best temperature prediction performance for the SMOTE-based dataset (RMSE = 3.668), while RF achieved the lowest stress prediction error (RMSE = 0.0490). GAN-augmented datasets provided stable and reliable predictions, whereas LLM-generated datasets resulted in higher prediction errors and lower physical consistency. Feature importance analysis revealed that plate thickness dominates displacement prediction (≈0.72 importance), manifold pressure governs stress behavior (≈0.999), and heating power is the primary factor affecting temperature prediction. The proposed AI-assisted surrogate modeling framework enables rapid and accurate thermo-mechanical prediction while significantly reducing computational cost compared to conventional multiphysics simulations. The findings demonstrate that integrating physics-based simulations with data-driven approaches provides an efficient strategy for the optimization of next-generation PEM fuel cell bipolar plates. Full article

The accurate estimation of State of Charge (SOC) and Remaining Useful Life (RUL) is a key challenge in lithium-ion battery management systems, due to the nonlinear, time-varying, and multi-physics nature of battery dynamics. This work presents a systematic comparative study for SOC and RUL estimation based on the analysis of the NASA battery dataset, characterized by significant heterogeneity in operating conditions, temperature regimes, and cycle durations. The study combines a physically informed feature engineering process with machine learning models, including tree-based ensembles, kernel methods, and neural networks. The dataset is analyzed from an electrochemical, thermal, and impedance perspective, highlighting the role of internal resistance evolution, SOC–voltage characteristics, and temperature dynamics as indicators of battery degradation. Based on these observations, two regression problems are formulated: a local window-based representation for SOC estimation and a cycle-level representation for RUL prediction. Particular attention is devoted to the impact of dataset heterogeneity, feature construction, and target representation on the predictive behavior of the considered models. In addition, the work investigates the effect of normalized RUL representations and provides an interpretability-oriented comparison of the learned regressors through feature-importance analysis and parity plots. Experimental results show that SOC estimation is a comparatively well-conditioned problem, achieving high accuracy across nonlinear models, although the dominant role of temporal and current-derived features highlights the strong dependence of the prediction task on the structure of the experimental protocol. In contrast, RUL prediction exhibits significantly higher complexity due to long-term degradation uncertainty and inter-battery variability. The introduction of a normalized RUL representation substantially improves prediction accuracy and stability, particularly for ensemble-based approaches. Feature importance analysis confirms that capacity-related variables dominate RUL estimation, while voltage, temporal, and current-derived features play a central role in SOC prediction. Overall, the results show that physically interpretable feature construction combined with ensemble learning methods provides an effective framework for battery state estimation and degradation analysis under heterogeneous operating conditions. Full article

Structural health monitoring of buried pipelines is essential due to their exposure to corrosion, impact loads, and geotechnical disturbances, which may induce abnormal vibration responses. Acceleration signals provide direct and sensitive measurements of buried pipeline structural dynamic behavior, and are therefore suitable for early anomaly identification. An acceleration-based intelligent framework integrating Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (ICEEMDAN) and a Long Short-Term Memory (LSTM) network is proposed for buried pipeline condition recognition. First, the raw acceleration signals are decomposed into a set of intrinsic mode functions (IMFs) using ICEEMDAN to enhance time–frequency resolution and isolate weak transient impact components associated with buried pipeline structural anomalies. Subsequently, multi-scale features extracted from the IMFs are fused and fed into an LSTM network to capture temporal dependencies and perform supervised health state classification. Experimental results demonstrate that the proposed framework achieves an F1-score of 0.70 and a Precision–Recall AUC of 0.72 for identifying anomalies. Furthermore, cross-validation utilizing multi-source field data (dynamic acceleration and quasi-static strain) confirms the model’s physical interpretability and its stable performance under severe noise interference. The results validate the feasibility of combining advanced signal decomposition with deep learning techniques for buried pipeline anomaly pre-warning, providing a rigorous methodological basis for the safe operation of critical energy infrastructures. Full article

Accurate and timely monitoring of soil salinity is of great significance for the ecological restoration of saline-alkali land and precision agricultural management. In this study, a typical coastal saline-alkali farmland located in Huanghua City, Hebei Province, China, in the Bohai coastal region, was selected as the study area. High-resolution images were acquired using an unmanned aerial vehicle (UAV) equipped with a multispectral sensor, and ground soil salinity samples were collected synchronously. Based on the construction of a feature library comprising spectral reflectance, vegetation indices, and salinity indices, three algorithms, PSO-SFLA, MultiSURF, and VIP, were employed for feature selection. Subsequently, an ensemble model was established, utilizing Ridge Regression (Ridge), Random Forest (RF), and Extra Trees (ET) as primary base learners, and Extreme Gradient Boosting (XGBoost) as the secondary meta-learner. This ensemble model was applied for soil salinity inversion. Furthermore, the coefficient of determination (R²), standardized root mean square error (S_RMSE), and the ratio of performance to interquartile distance (RPIQ) were introduced to comprehensively evaluate the accuracy of the models. Finally, the intrinsic physical responses of the features were explored through SHAP. The results showed that the optimization by the PSO-SFLA effectively reduced the impact of spectral multicollinearity, and 11 core features highly sensitive to salinity were selected from a vast number of indices. The ensemble model showed better predictive performance on the independent test set, achieving an R² of 0.758, an S_RMSE of 0.285, and an RPIQ of 3.382, outperforming the single Ridge, RF, and ET models under the current experimental conditions. Based on this model, the spatial distribution map of soil salinity in the experimental area was generated. The integrated and interpretable workflow proposed in this study, combining UAV multispectral imagery, PSO-SFLA-based feature selection, ensemble learning, and SHAP interpretation, provides a practical approach for accurate soil salinity inversion and dynamic agricultural monitoring in coastal saline-alkali lands. Full article

Two-dimensional transition metal carbides and nitrides, known collectively as MXenes, are attractive photocatalyst candidates because their surface chemistry and atomic composition can be tuned over a wide compositional window. A crucial design quantity is the electronic bandgap, which selects whether a given MXene couples with solar radiation and aligns with the redox levels of water splitting. High-fidelity bandgap calculations using the PBE0 hybrid functional are computationally expensive, which has motivated several machine learning surrogates. To the best of our knowledge, this is the first study to integrate a continuous-depth Neural Ordinary Differential Equation backbone with multi-fidelity $\Delta$ learning, distribution-free split-conformal calibration, and uncertainty-aware Pareto screening into a single mathematically grounded pipeline for MXene bandgap prediction. In this work, we develop a physics-constrained neural ordinary differential equation (PC-NODE) that predicts MXene bandgaps from a compact 34-dimensional descriptor set, without relying on the density of states. The model couples a classifier head for the metal/semiconductor decision with a regression head for the gap magnitude, and enforces three physically motivated properties: non-negativity of the predicted gap and monotonicity between the low-fidelity Perdew–Burke–Ernzerhof (PBE) and the high-fidelity PBE0 estimates are obtained exactly through a softplus-parameterised $\Delta$ learning construction, while a hurdle coupling that drives metal predictions towards zero is enforced via a quadratic penalty and verified empirically. In short, two of the three physical constraints are guaranteed by construction, and the third is approximately enforced and verified empirically; the same distinction is maintained consistently in the methodology, the constraint audit and the conclusion. Trained on the 4356-structure MXgap database, a ten-seed ensemble reaches a mean absolute error of $0.186$ eV (per-seed $0.206\pm 0.006$ eV) and a coefficient of determination $R^2=0.880$ on the semiconductor test subset, with a classifier accuracy of $0.856$ and a Receiver Operating Characteristic Area Under the Curve (ROC-AUC) of $0.925$. A split-conformal calibration step then delivers prediction intervals whose empirical coverage matches the 90% target within 0.5 percentage points. Finally, an uncertainty-aware Pareto screening step applies the trained surrogate to a held-out subset of 396 lanthanum-based MXenes and identifies 74 candidates inside the photocatalytic water splitting window [1.23, 3.10] eV. The framework offers a mathematically grounded, data-efficient alternative to feature-heavy pipelines and is reproducible from the open MXgap resource. Full article

This editorial synthesizes the key findings from 17 original research articles featured in the Special Issue on “Intelligent and Integrated Approaches for Efficient Oil and Gas Development.” The collection demonstrates a paradigm shift from purely data-driven methods toward physics-informed, interpretable, and operationally deployable intelligent systems across the upstream lifecycle. Advances span intelligent drilling with real-time model predictive control frameworks achieving sub-20 ms execution times and bottomhole pressure fluctuations below 0.30 MPa; AI-assisted reservoir characterization using multiscale convolutional neural networks, seismic waveform-constrained inversion, and geology-informed transformers that improve sandstone thickness prediction (R² = 0.895) and stratigraphic correlation (F1 = 0.886); production optimization through hybrid decomposition-ensemble models (R² = 0.954) and improved XGBoost (R² = 0.989); and enhanced oil recovery via self-assembled foam systems and polymer injector designs. Fundamental geochemical studies on the Qiongzhusi Formation shale and tight sandstone gas in the Ordos Basin provide critical geological constraints. The editorial identifies persistent challenges, including real-time performance versus physical fidelity, interpretability and uncertainty quantification, multi-scale integration, and generalizability across diverse geological settings. Future directions highlight reinforcement learning for autonomous operations, physics-informed digital twins, generative AI for subsurface scenario modelling, and integration with carbon capture, utilization, and storage. This Special Issue advances the convergence of petroleum engineering, artificial intelligence, and Earth sciences toward intelligent, secure, and sustainable hydrocarbon development. Full article

Concrete compressive strength is critical to structural safety, durability, and material cost. Conventional machine learning models are often limited in capturing complex nonlinear dependencies and generalizing. To address this, a residual fusion framework is proposed that combines a least squares support vector machine (LSSVM) optimized by DE with multi-level residual structure bagged decision trees (TreeBagger) and least squares boosting (LSBoost). DE-tuned LSSVM hyperparameters are followed by a multi-level residual scheme that compensates errors layer by layer, with LSBoost performing adaptive nonlinear fusion. Experiments under varied splits, ablation, and multiple seeds show the model outperforms traditional single and ensemble methods in accuracy, generalization, and stability. The ablation attributes the improvements to complementary residual mechanisms and the fusion architecture, rather than simply adding learners. Across multiple runs, an average coefficient of determination (R²) of 0.9490, a mean absolute error (MAE) of 3.7873 MPa, a root mean square error (RMSE) of 2.4998 MPa, and an R² standard deviation of 0.0029 were obtained, confirming stability. Shapley additive explanations (SHAP) analysis further reveals that age and water–cement parameters dominate, with patterns consistent with hydration and water–binder theory. The proposed framework thus offers high accuracy, physical interpretability, and engineering applicability. Full article

Outdoor jogging is a significant component of daily physical activities that benefit public health and urban living environments. However, it is still challenging to untangle the intricate associations between environmental variables and jogging paces, due to nonlinear interactions, spatial heterogeneity, and inadequacy in model interpretability. To this end, an interpretable spatial machine learning framework based on the integration of the Geographically Weighted Random Forest (GW-RF) model and SHapley Additive exPlanations (SHAP) is proposed. Drawing on multi-source urban datasets and Beijing’s large-scale jogging trajectory data, this model allows for global and local interpretation of environmental effects on the built, natural, and visual dimensions. The findings are as follows: (1) Built environment variables demonstrate the greatest explanatory power, with street network configuration (GAC, GAI) and population density identified as the dominant predictors of jogging intensity; (2) All environmental variables exhibit nonlinear threshold effects, with SHAP analysis revealing sign-switching points and optimal ranges—moderate NDVI and sky openness promote jogging while extreme values suppress it; (3) Natural and visual variables operate within distinct comfort thresholds, where moderate annual mean temperature, green view index, and sky openness are consistently associated with higher jogging intensity; and (4) The GW-RF model achieves superior predictive performance (R² = 0.7939, RMSE = 8.54, MAE = 5.72) over five benchmark models, confirming the necessity of spatial weighting in nonlinear ensemble learning. By revealing nonlinear response patterns and effective environmental ranges, the study presents quantitative evidence for the understanding urban physical activities and providing methodological guidance for fostering healthier and more activity-supportive urban environments. Full article

Artificial intelligence (AI) is rapidly redefining the management of urban energy systems by coupling predictive analytics with closed-loop control across buildings, power grids, and mobility networks, positioning cities as critical leverage points in global decarbonization efforts. Contemporary urban environments generate vast, heterogeneous datasets that enable advanced machine learning applications; however, limitations remain, including interpretability–fairness trade-offs, fragmented data governance, interoperability gaps, cybersecurity risks, and insufficient long-term validation across diverse climatic and socio-economic contexts. This review evaluates AI-driven strategies for energy-efficient urban systems and identifies the technical and governance conditions required for scalable impact. The evidence synthesized indicates that supervised and ensemble learning models achieve high predictive accuracy for electricity demand and chiller performance, with models such as Random Forest Regression achieving R² values up to 0.9835 in electricity consumption forecasting, while unsupervised approaches detect latent inefficiencies in HVAC systems, delivering measurable savings typically around 6% under controlled benchmarking conditions. Deep learning architectures improve multi-building forecasting and real-time control, with hybrid CNN–LSTM models achieving prediction accuracies up to 97% and outperforming traditional statistical approaches in weekly energy demand forecasting achieving higher prediction accuracy and significant energy savings in complex urban subsystems with reported reductions of approximately 21–23% in residential and educational buildings and up to 37% in office HVAC systems. Hybrid and physics-informed AI models embed thermodynamic principles into data-driven frameworks, improving robustness, interpretability, and generalization. IoT sensor networks and edge-computing architectures support adaptive HVAC, demand–response, and smart-grid management, while integrated building–grid–mobility systems enhance load balancing, storage use, and carbon reduction. AI-enhanced strategies offer a credible pathway toward measurable reductions in urban energy use and emissions with deep reinforcement learning in digital twin environments reducing HVAC energy demand by 10–35% while maintaining thermal comfort within ±0.5 °C in line with ASHRAE standards, and overall energy savings reaching up to 44% in optimized systems when supported by interoperable infrastructures, secure digital-twin architectures, and standardized measurement and verification protocols. Full article

To address the degradation of zenith tropospheric delay (ZTD) prediction accuracy caused by time-varying noise and error accumulation in multi-step forecasting, this study proposes an integrated prediction model, named IBX, which combines improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN), bidirectional long short-term memory (BiLSTM), and extreme gradient boosting (XGBoost). In the proposed framework, ICEEMDAN is first used to decompose the original ZTD series into components at different temporal scales. A three-criterion reconstruction strategy based on the Pearson correlation coefficient, dominant period, and sample entropy is then applied to obtain high-, medium-, and low-frequency subsequences with clearer physical meanings. BiLSTM and XGBoost are used to predict the reconstructed components, and their outputs are fused through a root mean square error (RMS)-based weighting strategy to improve forecasting robustness. Hourly ZTD data from 27 global navigation satellite system (GNSS) stations in China from 2011 to 2020 were used for model validation under 1–12 h rolling forecasting horizons. The results show that IBX achieves the best overall performance among the tested models. Its mean RMS and mean absolute error (MAE) over the 1–12 h horizons are 14.17 mm and 10.24 mm, respectively, which are 22.5% and 21.4% lower than those of the baseline BiLSTM model. Spatial and climate-region-based analyses further indicate that ZTD prediction accuracy is strongly affected by altitude, regional moisture conditions, and climate type. The proposed IBX model shows stable error suppression across heterogeneous station environments, especially in the temperate monsoon region and low-altitude regions with complex water vapor variability. These results demonstrate that IBX provides a reliable and physically interpretable approach for short- to medium-term ZTD forecasting and real-time atmospheric delay correction. Full article