Search Results (1,506)

In recent years, numerous studies have reported on intelligent analytical applications for food quality and safety. To identify the underlying patterns and development trends in this field, this paper presents a comprehensive review from the perspectives of both data-driven and mechanism-driven paradigms. Under the data-driven paradigm, detection modalities may involve either single-modal or multimodal approaches. By integrating measured detection data with appropriate intelligent learning algorithms, specific tasks for food quality or safety assessment can be achieved. Research efforts in this area encompass the development of detection techniques, optimization of measurement parameters, construction of high-dimensional spectral features, design of feature extraction methods, selection and tuning of algorithms, and formulation of multimodal data fusion strategies. This paradigm is characterized by high computational speed and superior prediction or classification efficiency. Nevertheless, it is constrained by several limitations, including poor model interpretability, limited extrapolation and generalization capabilities, and a heavy reliance on high-quality annotated data. In contrast, the data–mechanism hybrid-driven paradigm integrates physical laws and other prior knowledge as constraints that are deeply embedded into neural network training. By combining data-driven mining capabilities with theoretical prior knowledge, this approach achieves improved predictive performance and decision-making reliability. This paradigm offers notable advantages, such as enhanced interpretability, greater trustworthiness, improved data efficiency, and reduced computational costs. It is particularly well-suited for small-sample or data-sparse scenarios, and thus represents a promising and important direction for future research in this domain. Full article

Prediction of turboshaft engine performance parameters is essential for engine health management, however, traditional physics-based models and shallow neural networks struggle to effectively model the complex nonlinear characteristics of time-series data. To overcome these limitations, a hybrid model integrating a Temporal Convolutional Network (TCN), an attention mechanism, and a Bidirectional Long Short-Term Memory (BiLSTM) network is proposed for predicting turboshaft engine performance parameters. Temporal convolution is employed to extract local temporal features, while the BiLSTM network is used to capture long-term bidirectional dependencies. An attention mechanism is further incorporated to assign greater weights to critical time steps. Simulation results show that the proposed model achieves higher prediction accuracy compared to standalone LSTM and TCN models. When applied to the performance prediction of turboshaft engines under different inlet air temperature conditions, the proposed framework consistently maintained the root mean square error values for training and testing between 0.05 and 0.09 across three key performance parameters, while effectively suppressing measurement noise. These results demonstrate that the model possesses excellent generalization performance and holds significant potential for practical engineering applications. Full article

While there are evident advantages to deploying UAVs for structural inspection applications within reinforced-concrete structures where human access may be hazardous or restricted, UAV deployment is still inhibited within structures due to a lack of GPS, payload and power limitations, signal attenuation, limited transmission opportunities, and low bandwidth for communication. Within the confines of the present project, a low-cost two-layer six-rotor architecture was developed; a single Pixhawk PX4 manages stabilized flight, while a Raspberry Pi 4 manages mission-level operations. The complete prototype integrated a relative-pose/nearby-object estimator, hybrid 433 MHz and Wi-Fi/MQTT communications, avionics-side energy management, mission continuity via SQLite, and human-in-the-loop fail-safe support. Prototype experiments revealed reduced horizontal drift compared to both tested comparison configurations, continued operation under constrained communication conditions, and a 62.0% reduction in avionics-side power consumption, excluding propulsion. This was followed by a complementary PX4–Gazebo evaluation probing horizontal and vertical proximity responses, six-sector LiDAR processing, and stale-data watchdog functionality. Across 45 repeated simulation runs and 3000 retained sector-level observations, no simulated collisions occurred during the horizontal-approach, vertical-proximity, or watchdog tests. No false sector assignments were observed, and the overall mean absolute error was 0.0285 m. From this limited demonstration, the architecture appears satisfactory at the prototype and simulated-subsystem levels. Further physical testing will be needed prior to operational deployment. Full article

Vehicle-to-everything (V2X) connectivity provides electrified vehicles with previews of traffic signals, road geometry, surrounding traffic, and route conditions, yet control benefit arises only when these data are converted into variables that can shape motion and powertrain decisions. This review presents a structured, framework-driven narrative synthesis organized along an information–motion–energy chain: external preview, control-oriented prediction, energy-aware speed planning, trip-level energy and state-of-charge scheduling, power-source allocation, cross-layer coordination, and staged validation. The reviewed studies are compared in terms of coupling depth, from traffic-layer optimization and sequential speed–energy management strategy (EMS) schemes to hierarchical/weakly coupled and joint/tightly coupled formulations. Across hybrid electric vehicles (HEVs), plug-in hybrid electric vehicles (PHEVs), battery electric vehicles (BEVs), and fuel cell electric vehicle/hybrid electric vehicle (FCEV/FCHEV) platforms, the information interface is broadly shared, whereas energy-replenishment, thermal, and component-health constraints require powertrain-specific formulations. The evidence base also shows a persistent maturity gap between algorithmic simulation and hardware or vehicle validation. Key needs are uncertainty-aware closed-loop design, physically interpretable model–data fusion, fallback control under information degradation, standardized cross-layer benchmarks, and staged validation that reports both control performance and evidence level. Full article

Safe drilling in hydrate-bearing sediments is essential for environmentally responsible natural gas hydrate development. Complex pressure variations, fluid migration, and mechanical disturbances during drilling may increase the risks of gas influx, lost circulation, pipe sticking, and wellbore instability. To improve diagnostic robustness under heterogeneous and noisy drilling conditions while reducing dependence on large-scale manually labeled datasets, this study develops an adaptively coupled data–physics dual-driven diagnostic framework based on a self-organizing map (SOM) and a competitive classifier. Unlike a conventional one-way SOM–classifier cascade, changes in the downstream classification loss are fed back to adjust the SOM neighborhood radius, thereby coupling unsupervised feature mapping with supervised risk classification. In addition, class-conditional pressure-window and torque–drag consistency penalties are linked to the predicted class probabilities so that physical information directly participates in the optimization of applicable fluid-related and pipe-sticking risk predictions. Risk categories without an explicitly available physical residual remain primarily data-driven. Experiments on a hybrid measured–simulated dataset show that the proposed model achieves a test-set accuracy of 97.67%, outperforming representative baseline models. When 20% Gaussian noise is added, the accuracy decreases by only 4.20 percentage points. A three-layer data acquisition–edge-computing–cloud-monitoring early-warning system is implemented through MATLAB/VC integration. In a pilot field trial, a representative well-kick risk was identified 12 min earlier than by a conventional threshold-based alarm, and the missed-alarm rate decreased from 15% to 3%. The proposed method provides an engineering-oriented framework for improving drilling safety and environmental risk control during natural gas hydrate development. Full article

Subsurface thermo-hydro-mechanical (THM) coupled processes are fundamental to geomechanics, yet conventional mesh-based methods face high computational costs and limited efficiency in strongly nonlinear simulations and inverse problems. This review examines two representative physics-informed machine learning paradigms for THM modeling: physics-informed neural networks (PINNs) and neural operators (NOs). Relevant studies were identified through iterative keyword-based searches and citation tracking and were comparatively analyzed in terms of physical embedding, data dependence, computational efficiency, inverse capability, generalization, and engineering applications. The analysis shows that PINNs are well suited to physics-constrained simulation and parameter inversion from sparse data but are limited by training instability and loss imbalance. NOs enable rapid repeated forward predictions but depend strongly on representative training data and may perform poorly under out-of-distribution conditions. This review clarifies the complementary roles, trade-offs, and application boundaries of PINNs and NOs and highlights their hybrid integration as a promising route toward efficient and physically consistent subsurface THM simulation. Full article

Accurate forecasting of nitrogen dioxide (${\mathrm{NO}}_2$) in high-traffic urban environments is a critical challenge for public health management and environmental policy. This study presents a hybrid physics-informed machine learning pipeline for ${\mathrm{NO}}_2$ dispersion modeling and short-term forecasting along Viale Regione Siciliana in Palermo, Italy, one of the highest traffic-density corridors in Europe, over six full years (2020–2025) of hourly data resolved at approximately 11 m. Station measurements and weather data are harmonized hourly over the OpenStreetMap road network, converted into emissions with COPERT-Italy (COmputer Program to calculate Emissions from Road Transport) factors, and dispersed with the SIRANE street-network model; the chain is also inverted to recover corridor traffic from the observed ${\mathrm{NO}}_2$. The resulting field is joined with the measured predictors in the machine learning stage, and the output is mapped in GIS Geographic Information System. The hourly scatter between observations and the SIRANE model built on 44,752 h is centered on the 1:1 line, with a Pearson correlation of $\mathit{r}=0.83$. Of two “memory-less” ensembles on an identical predictor set, XGBoost (eXtreme Gradient Boosting) returns the better $R^2$, mean absolute error, and RMSE Root Mean Square Error at all twelve recursive lead times, declining from $R^2=0.79$ at $t+1$ h to a plateau of 0.66 at $t+12$ h, compared to 0.76 to 0.59 for random forest; both reproduce the mean field almost exactly ($r\ge 0.97$), with the XGBoost residual staying between 1.0 and 1.7 $\mathsf{\mu }$g m⁻³ at every horizon and that of random forest growing to 4.3 $\mathsf{\mu }$g m⁻³ by $t+12$ h. The proposed pipeline offers a transferable methodology for urban air quality management in traffic-dominated environments. Full article

For nearly a century, flotation kinetics has relied on deterministic first-order rate equations treating the cell as a homogeneous reactor, a paradigm that faces significant limitations for heterogeneous ores, especially coal, whose organic macerals, porosity, and oxidation susceptibility defy a single rate constant. While more advanced distributed-k, mixed-order, and population-balance models can account for certain types of particle heterogeneity (e.g., size or liberation), they still assume that the floatability distribution remains invariant during flotation, an assumption that fails when surface chemistry evolves concurrently with the separation process. Breaking from chronological cataloguing, this review proposes a three-dimensional taxonomy based on physical scale, inherent material heterogeneity, and epistemic certainty. We demonstrate that critical industrial prediction failures arise from structural mismatches between model physics and particle surface chemistry, notably time-dependent oxidation deactivation and selective maceral recovery. Six fundamental failure modes are identified, from neglected time-dependence of rate constants to the absence of a thermodynamic deactivation term, corroborated by experimental evidence from coal and base-metal flotation. Advanced microfluidic, automated mineralogical, surface-sensitive spectromicroscopic, CFD-DEM, and physics-informed machine learning tools are dismantling the black box of the flotation rate constant “k”. We introduce the Distributed Reactive Surface Kinetics (DRSK) framework, which embeds particle-scale heterogeneity into a population balance via an adaptive surface-sensitive selection function and treats kinetic uncertainty through stochastic differential equations. A comprehensive comparison table facilitates the transition from conventional models to the DRSK paradigm. We conclude with a roadmap for flotation kinetics 4.0, where digital twins, real-time froth analytics, and self-calibrating hybrid models transform this empirical discipline into a truly predictive engineering science. Quantitative validation against published coal and copper flotation data demonstrates that DRSK reduces prediction error by 60%–75% compared to conventional first-order and distributed-k models, while providing probabilistic uncertainty bounds essential for risk-based decision-making. The framework is elaborated for coal and conventional minerals, underscoring why coal demands its own dedicated kinetic theory and how these lessons can revolutionize the processing of increasingly complex, low-grade ores and secondary resources. Full article

Reliable finite-horizon forecasting of chaotic dynamics is challenging because small approximation errors grow rapidly during recursive prediction. This study presents a controlled comparison of data-driven and physics-regularized forecasting methods for the Lorenz and Rössler systems. The proposed Hybrid Physics-Informed Feedforward Neural Network (Hybrid PI-FNN) learns a discrete state-transition map from a ten-state observation window through a five-step recursive rollout. Unlike conventional continuous-coordinate physics-informed neural networks, physical consistency is imposed using fourth-order Runge–Kutta transition targets derived from the known governing equations. The physics weight is selected using chronological recursive validation and evaluated against an architecturally identical multi-step FNN with $\lambda =0$. Conventional FNN, LSTM, Echo State Network (ESN), Autoregressive AR(10), and Dynamic Mode Decomposition baselines are also evaluated using untouched test trajectories. For the 1000-step Lorenz test rollout, the ESN achieved the lowest mean squared error (MSE) of 0.1701, followed by the LSTM with 22.9962. The Hybrid PI-FNN produced an MSE of 95.8157, compared with 87.9260 for its $\lambda =0$ ablation; therefore, physics regularization did not improve Lorenz test MSE, although their forecast horizons at a 10% normalized-error threshold were similar (273 and 272 steps, respectively). For the Rössler system, the Hybrid PI-FNN reduced recursive MSE from 0.2202 for the $\lambda =0$ ablation to 0.0834, corresponding to a 62.11% reduction, while both models completed the maximum evaluated 1000-step forecast horizon. Nevertheless, the ESN again achieved the lowest Rössler MSE of approximately $8.04\times {10}^{-5}$. Finite-horizon correlation-dimension analysis, exact governing-equation Lyapunov spectra, computational-cost comparisons, and five-seed paired experiments were additionally conducted. The exact spectra confirmed one positive, one approximately neutral, and one negative exponent for each system, indicating chaotic but not hyperchaotic behavior. The paired multi-seed analysis did not establish a statistically significant forecasting advantage from physics regularization. These findings show that higher-order physics consistency can benefit particular systems and configurations, but it does not guarantee universal superiority in recursive chaotic forecasting. Full article

Predicting emergencies caused by uncontrolled and sometimes sudden changes in methane concentration within working and adjacent zones of coal mines remains a critical and challenging task, the solution for which can greatly enhance mining safety. This study presents a hybrid machine-learning model trained on real and synthetic data for accurate methane concentration forecasting and risk-level classification. The authors propose an ensemble method comprising staged data preprocessing, generation of physically meaningful features, and weighted ensembles for both regression and classification. The system is augmented with expert rules to correct forecasts and a built-in anomaly detection mechanism based on residual analysis. Experimental evaluation confirmed the model’s high performance: for regression, the coefficient of determination reached 0.984–0.997; the classifier achieved a recall of 92.8% for the rare “Accident” class under severe data imbalance (10:1). The ensemble approach reduced error variance by 40–60% compared to baseline models. The results indicate the feasibility of pilot application for dynamic early warning, which can substantially reduce coal mine accident risks. Full article

The increasing availability of construction data and advances in artificial intelligence (AI) have accelerated the adoption of time series forecasting across construction management. However, a comprehensive understanding of the field’s knowledge structure, methodological evolution, and future directions remains limited. To address this gap, a scientometric and qualitative review was conducted on 192 journal articles published between 2010 and December 2025 and retrieved from the Web of Science Core Collection and Scopus databases, following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) framework. VOSviewer was employed to visualize the knowledge structure, collaboration networks, and research themes. The results indicate sustained growth in research activity since 2010, accompanied by increasing international collaboration. Six major research streams were identified: cost estimation and forecasting, safety and risk management, schedule and performance monitoring, productivity and resource management, sustainability and waste management, and emerging methods and future technological directions. The findings reveal a clear transition from traditional statistical approaches, including AutoRegressive Integrated Moving Average (ARIMA) and vector error correction (VEC) models, toward machine learning, deep learning, and hybrid forecasting frameworks. At the same time, traditional methods remain important because of their interpretability and practical applicability. Three persistent challenges were identified: data quality and availability, model interpretability, and practical implementation. Future research is expected to focus on lightweight real-time forecasting, multimodal data fusion, explainable AI, and physics-informed forecasting models. This review provides an integrated understanding of the field and a research agenda for future methodological and practical development. For practitioners, it further highlights that the value of forecasting models depends not only on predictive accuracy but also on interpretability, computational efficiency, data requirements, and practical deployability in construction decision-making. Full article

Flood forecasting often depends on upstream hydrographs that are unavailable, incomplete, or unreliable. Reverse Flood Routing (RFR) addresses this gap by reconstructing upstream inflows from downstream observations, yet its operational use remains limited by numerical instability, observational uncertainty, and the ill-posed nature of the inverse problem. This review critically synthesizes RFR methodologies across a physics–fidelity continuum, ranging from storage-based and simplified hydraulic models to full hydrodynamic inversions, optimization-based techniques, Bayesian approaches, and emerging data-driven methods. The reviewed approaches are compared in terms of physical realism, numerical stability, computational demand, data requirements, uncertainty treatment, and field applicability. The synthesis indicates that storage-based methods remain attractive for data-limited and computationally constrained applications, whereas full hydrodynamic models are better suited to complex flow conditions involving backwater effects and detailed channel hydraulics. Optimization-based and Bayesian approaches can improve parameter estimation and uncertainty representation, while hybrid AI–physics methods offer promise for computational acceleration but still require stronger physical constraints and broader operational validation. Across all methodological families, error amplification, lateral inflow, transmission losses, and inconsistent benchmarking remain persistent limitations. An integrated framework is therefore proposed to connect observations, model selection, regularization, uncertainty quantification, hybrid computational methods, and operational decision support, providing a roadmap for more reliable and scalable RFR applications. Full article

Microwave-driven thermochemical cycles can split water for hydrogen production at temperatures far below those of conventional solar thermochemical routes, yet the responsible physical mechanisms remain unclear and numerical models for the coupled solar-microwave hybrid system are still scarce. Building on previous experimental work, we developed a coupled numerical model that integrates impedance matching, non-thermal enhancement, two-stage Arrhenius kinetics, and energy conservation to systematically investigate the interplay between microwave power, temperature evolution, and reaction progress. The model predictions agree well with experimental data in terms of temperature evolution trends, power threshold ranges, and reaction timescales. The results indicate that, within the present modeling framework, the effective microwave absorption efficiency increases from 1.2% at low temperatures to approximately 14% near 85 °C, with the non-thermal enhancement factor contributing as an empirical parameter. Under pure microwave mode, the required power threshold for reaction initiation is approximately 120 W; the solar-microwave synergistic mode reduces this threshold to about 70 W, a 42% reduction. At an input power of 100 W, the energy conversion efficiency reaches a maximum of 42%. Analysis of the sudden temperature change identifies 85 °C as the critical triggering temperature: below it, the system remains in a low-absorption cold state, while once crossed, a positive feedback mechanism rapidly propels the system into the high-temperature reaction regime. This study provides a numerical modeling framework for describing the coupled solar-microwave thermal behavior of the system and for guiding the optimization of its operational parameters. Since the available measurements cannot independently separate the thermal and non-thermal contributions, the non-thermal enhancement remains an empirically introduced factor rather than an experimentally established physical effect. Full article

This article presents a scoping review of the literature on digital twins (DTs) for sustainable groundwater resources management, which constitutes a very recent and rapidly expanding research field, with literature moving quickly from conceptual frameworks to application-oriented systems. The literature, selected through the PRISMA 2020 methodology, is organized into seven sub-topics: AI and ML foundations, digital twin architectures and frameworks, aquifer-scale DT applications, agricultural and water–energy–food (WEF) nexus DTs, basin and urban water DTs, sensing, monitoring and IoT infrastructures, and governance, resilience and socio-hydrology. This structure shows how the field is shifting from monitoring and prediction toward integrated decision support, where process-based models, machine learning surrogates, real-time sensing and optimization are combined to support drought mitigation, saltwater intrusion control, irrigation management, climate adaptation and basin-scale planning. Across the reviewed studies, the most recurrent contributions are the construction of hybrid model architectures, the use of DTs to close the loop between observation and control, and the growing recognition that groundwater management must incorporate governance, stakeholder decision-making and socio-hydrological feedbacks. At the same time, the literature still faces key limitations, especially uncertainty quantification, interoperability between models and data streams, transferability to data-scarce settings and limited validation under real operational conditions. Future research should therefore focus on physics-informed and explainable AI, federated and scalable DT architectures, stronger coupling with socio-hydrological and governance frameworks, and more field-tested implementations that can demonstrate robust performance across diverse hydrogeological and institutional contexts. Full article

Earthquakes remain among the most destructive natural hazards, necessitating reliable monitoring and early warning systems for effective risk mitigation. Recent advances in machine learning (ML) and deep learning (DL) have significantly improved seismic signal analysis, enabling more accurate event detection, phase picking, classification, and magnitude estimation. This study presents a systematic review of ML- and DL-based approaches for earthquake monitoring, with particular emphasis on Distributed Acoustic Sensing (DAS) as an emerging technology for high-resolution, real-time seismic observation. Following the PRISMA 2020 guidelines, a systematic literature search was conducted across Scopus, Web of Science, IEEE Xplore, and Google Scholar, yielding 252,223 initial records. After applying the predefined publication period, removing duplicate records, conducting relevance screening, and performing eligibility assessment, 138 peer-reviewed studies published between 2021 and 2025 were retained for detailed analysis and synthesis. The review reveals a significant transition from conventional signal-processing techniques to advanced artificial intelligence-based approaches, including Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM) networks, Bidirectional Long Short-Term Memory (BiLSTM) networks, Transformer-based architectures, hybrid models, and Bayesian learning methods for uncertainty quantification. The findings further demonstrate that Distributed Acoustic Sensing (DAS) has emerged as a transformative sensing technology because of its dense spatial coverage, high spatial resolution, and continuous monitoring capability. However, several challenges remain, including the lack of standardized datasets, limited model generalization across diverse geological settings, insufficient model interpretability, high computational complexity, and the limited integration of uncertainty-aware approaches for real-time seismic monitoring. This review identifies these critical research gaps and highlights promising future research directions, including multimodal data fusion, interpretable artificial intelligence, physics-informed learning, self-supervised learning, and robust uncertainty quantification for next-generation intelligent seismic monitoring systems. Unlike previous review studies that primarily focus on individual machine learning techniques or conventional seismic monitoring, this review provides a comprehensive and systematic synthesis of recent advances in machine learning, deep learning, and Distributed Acoustic Sensing (DAS), identifies current research gaps, and offers practical recommendations to guide future research on intelligent earthquake monitoring systems. Full article