Search Results (598)

In this paper we present a hybrid convolutional neural network–hidden Markov model framework for detecting solar flare events of intensity greater than or equal to M1.0 from very low frequency signals via their induced sudden ionospheric disturbances. The convolutional neural network processes fixed-length windows of raw very low frequency signals and their temporal derivatives to produce probabilistic flare estimates, which serve as emission probabilities for a two-state hidden Markov model. Viterbi decoding enforces temporal consistency, suppressing spurious fluctuations and yielding physically plausible event sequences. The approach is specifically designed to detect the onset-to-peak interval of flare events and, with further development, could operate in real time for early flare warning. The model was trained and evaluated on very low frequency data from the DHO38 transmitter in Germany to a receiver near Birr, Ireland. Sample-level evaluation achieved a balanced accuracy of 0.819 and a Matthews correlation coefficient of 0.529, while event-level detection reached a peak F1-score of 0.558 for moderate-to-strong flares of intensity greater than or equal to C6.0. These results demonstrate automated, physically consistent detection of solar flares based on sudden ionospheric disturbances, indicating the potential of the proposed approach, when combined across multiple receivers, to act as a low-cost complement to satellite-based monitoring. Full article

The large-scale integration of wind energy introduces increased uncertainty and variability in modern power systems, with direct implications for both system design and operation. In addressing similar aspects, energy storage plays a pivotal role as a key source of system flexibility. However, the design and sizing of storage systems remain challenging, especially under conditions of increased uncertainty. In this context, the present study proposes an alternative methodological framework, based on an inverse sizing pathway, i.e., from operations to design. More specifically, the uncertainty embedded in day-ahead forecasting of residual errors, associated with wind power generation and load demand, is currently exploited as a design-relevant signal, while energy storage is treated explicitly as a risk-hedging mechanism. Forecasting residuals spanning a year of operation are incorporated in the problem through probabilistic modeling, leading to the generation of trajectories that correspond to different risk levels and are managed as design scenarios. Regarding the modeling of uncertainties, the study examines two different strategies, namely a global modeling approach and a k-means clustering strategy. Accordingly, by mapping the interplay between storage capacity, uncertainty levels (or risk tolerance), achieved RES shares and system-level costs, we highlight the role of energy storage as a risk-hedging entity rather than merely a means of energy balancing. Our results to that end demonstrate that the achieved shares of RES exhibit increased sensitivity, even within constrained regions of wind power variation, while storage capacity features distinct zones of hedging value and hedging saturation effects emerging beyond certain storage levels. Moreover, evaluation of the two modeling strategies reflects on their complementary character, with the global modeling approach ensuring continuity and the clustering strategy capturing local asymmetries within different operational regimes. In conclusion, the methodology presented in this study bridges the gap between operational forecasting and long-term system design, offering a risk-aware framework for storage sizing, grounded in actual operational signals rather than relying on stationary historical data and relevant scenarios. Full article

The extreme volatility of European energy markets in 2022 has exposed the limitations of conventional forecasting models, necessitating more robust architectures capable of handling non-linear price shocks. This study proposes a novel multi-parallel hybrid forecasting framework that integrates seven heterogeneous neural networks to predict day-ahead electricity prices. The architecture employs a hierarchical approach where six parallel base models (NN1–NN6) feed into a meta-network (NN7) to generate baseline forecasts. To further enhance predictive fidelity, these results undergo a calibration stage using probabilistic error distribution analysis to produce final probability-adjusted forecasts. The model was validated using the Lithuanian electricity market during the highly volatile period of 2020–2022. Empirical results demonstrate a clear “stacking effect,” where the incremental integration of base networks consistently reduces forecasting residuals. The final probability-adjusted configuration achieved a notable nMAE of 1.57% and a sMAPE of 34.25%, significantly outperforming baseline ensemble outputs and state-of-the-art benchmarks reported in recent literature. Specifically, the probability-based refinement proved highly effective in mitigating systematic biases during nighttime and early morning hours, confirming the model’s capacity to maintain accuracy under extreme market stress. Full article

Mathematical modeling plays a key role in understanding and optimizing transport system operations under uncertain and dynamic conditions. This study proposes a data-driven predictive framework for estimating passenger-accepted vehicle occupancy, addressing a critical gap in transport system planning under public health-related constraints. Using data from a structured survey conducted across seven Southeast European countries (N = 476), the study integrates statistical analysis and machine learning approaches to model acceptable occupancy levels across multiple transport modes, including passenger cars, taxis, tourist buses, and public buses. The problem is formulated as a predictive mapping between multidimensional input variables and occupancy acceptance levels, modeled using both probabilistic and nonlinear function approximation methods. The results highlight that age, gender, and area of residence are the most significant determinants of occupancy acceptance, while education level has limited predictive relevance. Furthermore, a multi-layer feedforward artificial neural network is developed to capture nonlinear relationships between variables, achieving strong predictive performance (minimum MSE = 0.0089). The main contribution of this research lies in linking behavioral data with predictive modeling to quantify acceptable occupancy thresholds and support realistic simulation of passenger responses in crisis conditions. The proposed modeling framework contributes to transport system planning, enabling data-driven capacity management, enhanced safety strategies, and improved resilience of passenger transport operations. Full article

In underground coal mining, the gear of a shearer’s rocker arm endures extreme stress and environmental fluctuations. Failures in this vital component can pose serious safety hazards, cause prolonged operational downtime, and result in significant financial losses. Therefore, accurate gear fault diagnosis is crucial. However, conventional diagnostic methods often struggle with limited feature extraction and poor performance when dealing with non-stationary, noisy signals typical of this environment. To address these challenges, a hybrid model consisting of Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM) network, and Markov Transition Model (MTM) is proposed. In this framework, the CNN is used to extract both global and local features related to gear fault. A time-distributed feature extractor is then integrated with the LSTM to capture the temporal progression of these features, aiding in effective modeling of fault evolution over time. Finally, the MTM further refines classification by incorporating probabilistic state transition between fault conditions, thereby improving diagnostic stability and robustness under noise. Experimental validation was done using vibration data from the Taizhong Coal Machinery rocker arm test platform and gear data from Southeast University and achieved up to 99.79% accuracy. These results show this proposed method outperformed other advanced diagnostic methods, offering dependable fault diagnosis and strong noise resistance even under extreme noise conditions of −5 dB SNR. Full article

Accurate regional ocean forecasting requires models that are both computationally efficient and capable of representing predictive uncertainty. This work investigates ensemble learning strategies for sea surface temperature (SST) forecasting using Graph Neural Networks (GNNs), with a focus on how input perturbation design affects forecast skill and uncertainty representation. We adapt a GNN architecture to the Canary Islands region in the North Atlantic and implement a homogeneous ensemble approach inspired by bagging, where diversity is introduced during inference by perturbing initial ocean states rather than retraining multiple models. Several noise-based ensemble generation strategies are evaluated, including Gaussian noise, Perlin noise, and fractal Perlin noise, with systematic variation of noise intensity and spatial structure. Ensemble forecasts are assessed over a 15-day horizon using deterministic metrics (RMSE and bias) and probabilistic metrics, including the Continuous Ranked Probability Score (CRPS) and the Spread–skill ratio. The results show that, while deterministic skill remains comparable to the single-model forecast, the type and structure of input perturbations influence uncertainty representation, particularly at longer lead times. Ensembles generated with spatially coherent perturbations, such as low-resolution Perlin noise, achieve improved calibration and lower CRPS compared to purely random Gaussian perturbations. These findings highlight the role of noise structure and scale in ensemble GNN design, indicating that specifically structured input perturbations can improve ensemble diversity and calibration without additional training cost. These results provide a methodological contribution toward the study of ensemble-based GNN approaches for regional ocean forecasting. Full article

Cloud cover significantly reduces the electrical power output of photovoltaic systems, making accurate short-term cloud movement predictions essential for reliable solar energy production planning. This article presents a deep learning framework that directly estimates cloud movement from ground-based all-sky camera images, rather than predicting future production from past power data. The system is based on a three-step process: First, a lightweight Convolutional Neural Network segments cloud regions and produces probabilistic masks that represent the spatial distribution of clouds in a compact and computationally efficient manner. This allows subsequent models to focus on the geometry of clouds rather than irrelevant visual features such as illumination changes. Second, a Vector Quantized Variational Autoencoder compresses these masks into discrete latent token sequences, reducing dimensionality while preserving fundamental cloud structure patterns. Third, a GPT-style autoregressive transformer learns temporal dependencies in this token space and predicts future sequences based on past observations, enabling iterative multi-step predictions, where each prediction serves as the input for subsequent time steps. Our evaluations show an average intersection-over-union ratio of 0.92 and a pixel accuracy of 0.96 for single-step (5 s ahead) predictions, while performance smoothly decreases to an intersection-over-union ratio of 0.65 and an accuracy of 0.80 in 10 min autoregressive propagation. The framework also provides prediction uncertainty estimates through token-level entropy measurement, which shows positive correlation with prediction error and serves as a confidence indicator for downstream decision-making in solar energy forecasting applications. Full article

Coastal freak waves (CFWs) are sudden and hazardous wave events that occur near shorelines and can pose serious threats to coastal visitors and infrastructure. Due to the complex interactions among coastal bathymetry, wave dynamics, and environmental conditions, the mechanisms governing CFW formation remain poorly understood, making reliable prediction difficult. This study investigates the feasibility of applying machine learning techniques to predict CFW occurrences using observational environmental data. Three machine learning algorithms, the Random Forest (RF), Support Vector Machine (SVM), and Artificial Neural Network (ANN), were developed to generate probability-based predictions of CFW events. Environmental variables derived from buoy observations, including wave characteristics, wind conditions, swell parameters, wave grouping indicators, and nonlinear wave interaction indices, were used as model inputs. Hyperparameters were optimized using grid search combined with k-fold cross-validation. The results show that all three models achieved comparable predictive performance, with AUC values close to 0.80 and overall prediction accuracy around 74%. The ANN model achieved the highest recall, indicating strong capability in detecting CFW events, while the RF and SVM models showed more balanced precision and recall. Analysis of high-probability prediction events suggests that CFW occurrences are associated with swell-dominated conditions, strong wave grouping behavior, and enhanced nonlinear wave interactions. These results demonstrate that machine learning provides a promising framework for probabilistic prediction of coastal freak waves and has potential applications in coastal hazard assessment and early warning systems. Full article

Background/Objectives: Machine learning (ML) models can predict hospital admission from emergency department (ED) triage data with areas under the receiver operating characteristic curve (AUC) exceeding 0.85. Whether incorporating the assigned provider’s identity—as a proxy for unmeasured practice variation—improves prediction has not been systematically studied. We aimed to compare 10 supervised ML classifiers for predicting hospital admission at ED triage, with and without provider identity, and to characterize model reasoning using SHapley Additive exPlanations (SHAP). Methods: We conducted a retrospective cohort study of 186,094 ED visits (2020–2023, training) and 58,151 visits (2024, temporal holdout test) at one academic tertiary-care ED. Ten classifiers spanning linear, distance-based, tree-based, ensemble, probabilistic, and neural network families were each trained in two conditions: baseline (23 triage features) and with provider identity appended. SHAP TreeExplainer was applied to the top-performing models (CatBoost and XGBoost). Results: The admission rate was 31.3% (training) and 31.7% (test). CatBoost achieved the highest baseline AUC of 0.8906 (0.8878–0.8933). Adding provider identity produced negligible AUC changes across all models (ΔAUC range: −0.0029 to +0.0015; all DeLong p > 0.05). SHAP analysis identified ESI level, respiratory rate, temperature, complaint category, and age as the dominant predictors, with clinically intuitive directionality. Conclusions: Provider identity does not meaningfully improve ML prediction of hospital admission beyond standard triage variables. The observed 28-percentage-point variation in provider admission rates is explained by patient case-mix differences than with independent practice pattern effects on prediction. SHAP provides transparent, clinically interpretable explanations suitable for bedside decision support. Full article

Seamless localization across indoor and outdoor environments remains a fundamental challenge for wearable navigation systems, particularly those intended to assist visually impaired individuals. This challenge arises from the unreliability of GNSS signals in indoor and transitional spaces and the cumulative drift inherent to IMU–based dead reckoning. To address these limitations, this paper proposes a physics-informed GNSS–IMU sensor fusion framework that enables robust, real-time wearable navigation across heterogeneous environments. The proposed system dynamically adapts to environmental context, employing GNSS dominant localization in outdoor settings and PINN enhanced IMU-based dead reckoning during GNSS denied indoor operation. At the core of the framework is a tightly coupled Physics-Informed Neural Network (PINN) and Extended Kalman Filter (EKF), where the PINN embeds kinematic motion constraints to correct inertial drift and suppress sensor noise, while the EKF performs probabilistic state estimation and sensor fusion. The framework is implemented on a compact, energy-efficient wearable platform and evaluated using real-world indoor–outdoor pedestrian trajectories. Experimental results demonstrate improved localization accuracy, significantly reduced drift during indoor navigation, and stable indoor–outdoor transitions compared to conventional GNSS–IMU fusion methods. The proposed approach offers a practical and reliable solution for wearable assistive navigation and has broader applicability in smart mobility and autonomous wearable systems. Full article

Therapist shortages make home-based rehabilitation an essential component of post-stroke care, yet patients often exhibit reduced adherence when functional gains are difficult to quantify and interpret. This study presents a cloud-enabled assessment framework centered on a dynamic reaching task for upper-limb rehabilitation in individuals with mild stroke. The proposed system combines wearable sensing and Internet of Things (IoT) connectivity to stream kinematic data to the cloud for near real-time analysis, and integrates a force-feedback rehabilitation robot to deliver motion guidance during training. The pipeline proceeds in three stages. First, smoothness-related kinematic descriptors are extracted and fed into a deep multi-class classifier to discriminate the affected side (left, right, or healthy). Second, movement quality is modeled using a Gaussian Mixture Model (GMM) trained on IoT-acquired trajectories to quantify performance via probabilistic similarity. Third, a calibrated scoring function transforms GMM log-likelihood into a normalized 0–1 quality index, producing visual reports that support interpretable feedback for patients and therapists. The framework is validated using motion data collected from stroke patients at Taipei Veterans General Hospital. Experimental results demonstrate that the neural network multi-classifier achieved an F1-score of 0.95. Incorporating robot-derived interaction signals further improved classification performance by approximately 5%. For movement quality assessment, the derived scores showed a significant positive correlation (Pearson correlation = 0.632, p = 0.02) with therapist-defined gold reference standards for right-affected patients. Additionally, integrating robot force-feedback signals and AIoT-enabled dynamic streams improved score accuracy by 8% and score responsiveness by 10%. These quantitative outcomes substantiate the efficacy of combining IoT-driven sensing and robot-assisted training for objective, interpretable, and remotely deployable motor assessment. Full article

Accurate prediction of wind speed at sea is crucial for the site selection of wind farms, the layout of wind turbines, and the estimation of power generation. To improve the accuracy of short-term predictions under limited data conditions, this study proposes a backpropagation (BP) neural network prediction model optimized by the particle swarm optimization algorithm (PSO). This model is trained using hourly wind speed data from meteorological stations along the northeastern coast of China from 2020 to 2022, and two modeling strategies, namely the unified training model over multiple years and the seasonal model, are constructed for comparison. The validation using the measured data from January to July 2023 indicates that the unified model with a root mean square error of 1.235 and an average absolute error of 0.924 demonstrates superior generalization performance, outperforming the seasonal models (such as the spring model with RMSE = 1.243 and the summer model with RMSE = 1.324). Benchmark comparisons against LSTM, ARIMA, and persistence models further confirmed the superiority of the proposed approach. To address the stochastic nature of wind speed and support grid operation, we extended the deterministic forecasts to probabilistic prediction intervals using Monte Carlo Dropout, achieving a prediction interval coverage probability of 81.2% with a mean width of 1.38 m/s. The results indicate that while seasonal modeling offers insights into intra-annual wind variations, it does not exceed the accuracy of the globally trained multi-year model under limited data conditions. In conclusion, the proposed BP-PSO hybrid model provides a robust and low-cost solution for offshore wind speed forecasting, with the probabilistic forecasting framework offering actionable uncertainty information for grid integration. The multi-year training framework demonstrates stronger practical utility, and the findings support the application of hybrid optimization algorithms in real-world wind resource assessment. Full article

Fractured reservoir characterization is a complex and challenging task due to its depositional nature and high uncertainty in the spatial distribution of fractures, typically when well data is limited, and interpolation algorithms are employed. This paper introduces an alternative workflow designed to enhance fracture modeling between well locations by incorporating seismic attributes, using publicly released data from the Teapot Dome Field. The paper’s objective is to create a fracture model for the Tensleep reservoir in the Teapot Dome Anticline by employing seismic attributes sensitive to fault and fracture features, while also demonstrating the limitations of interpolation-based models such as Gaussian simulation. The approach uses artificial neural networks to predict fracture intensity by analyzing seismic data and well logs, training supervised probabilistic artificial networks to identify the seismic attributes that most closely correlate with the fracture intensity property derived from well log data. The validated network successfully transformed the 3D seismic data into 3D fracture intensity data, achieving a high correlation coefficient between the selected seismic attributes and the training wells. The research findings are extremely valuable because they help address the lack of information on fractures, improve reservoir management, and optimize well placement. Full article

The distribution of gas–water two-phase flow in near-horizontal wells is influenced by factors such as wellbore inclination and phase flow rates. To explore these effects, a laboratory loop simulating downhole conditions was used to conduct experiments under varying inclinations and flow parameters. Flow patterns were classified based on visual observations and existing theory, and scatter plots were used to analyze flow regime boundaries. Three classification models were developed and compared. The proposed PNN–XGBoost framework integrates explicit second-order feature crossing with XGBoost-based importance selection prior to probabilistic neural network classification. Among the evaluated models, the PNN–XGBoost approach achieved the highest predictive performance. The model was further validated using 3D wellbore holdup imaging, confirming its robustness in flow pattern identification and its applicability to practical well logging interpretation. Full article

Frequency-domain electromagnetic (FDEM) measurements for shallow subsurface exploration are frequently corrupted by noise, which masks weak secondary-field responses and degrades interpretation. We propose an electromagnetic diffusion CNN (EMDiC) for 1D multi-frequency FDEM denoising, where denoising is formulated as conditional diffusion-based generation. EMDiC combines an analytic frequency–spatial encoder, a Feature-wise Linear Modulation (FiLM)-conditioned convolutional hourglass backbone, and a physics-informed composite loss built on velocity loss to improve waveform reconstruction under severe noise. A reproducible synthetic dataset is constructed through layered-earth forward modeling with concentric Transmitter–Receiver (TX–RX) geometry, multiple target categories, and mixed noise waveforms. On synthetic benchmarks covering multiple noise levels and material types, EMDiC achieves the best overall performance in Root Mean Square Error (RMSE), Signal-to-Noise Ratio (SNR), and Normalized cross-correlation (NCC) among 1D U-Net, diffusion-based variants, and representative neural baselines, with the clearest gains under medium-to-strong noise and for targets with pronounced induction responses. Ablation experiments verify the complementary contributions of electromagnetic positional encoding (EMPE), FiLM conditioning, and the composite loss. Field data validation with a self-developed GEM-3 system further shows that EMDiC improves cross-frequency coherence and suppresses oscillations while preserving the main response characteristics. Full article