Search Results (4,314)

High-precision temperature prediction is crucial for dealing with extreme weather events under the background of global warming. However, due to the limitations of computing resources, numerical weather prediction models are difficult to directly provide high spatio-temporal resolution data that meets the specific application requirements of a certain region. This problem is particularly prominent in areas with complex terrain. The use of remote sensing data, especially high-resolution terrain data, provides key information for understanding and simulating the interaction between land and atmosphere in complex terrain, making the integration of remote sensing and NWP outputs to achieve high-precision meteorological element downscaling a core challenge. Aiming at the challenge of temperature scaling in complex terrain areas of Southwest China, this paper proposes a novel deep learning model—Terrain Adaptive U-Net Transformer (TAUT). This model takes the encoder–decoder structure of U-Net as the skeleton, deeply integrates the global attention mechanism of Swin Transformer and the local spatiotemporal feature extraction ability of three-dimensional convolution, and innovatively introduces the multi-branch terrain adaptive module (MBTA). The adaptive integration of terrain remote sensing data with various meteorological data, such as temperature fields and wind fields, has been achieved. Eventually, in the complex terrain area of Southwest China, a spatio-temporal high-resolution downscaling of 2 m temperature was realized (from 0.1° in space to 0.01°, and from 3 h intervals to 1 h intervals in time). The experimental results show that within the 48 h downscaling window period, the TAUT model outperforms the comparison models such as bilinear interpolation, SRCNN, U-Net, and EDVR in all evaluation metrics (MAE, RMSE, COR, ACC, PSNR, SSIM). The systematic ablation experiment verified the independent contributions and synergistic effects of the Swin Transformer module, the 3D convolution module, and the MBTA module in improving the performance of each model. In addition, the regional terrain verification shows that this model demonstrates good adaptability and stability under different terrain types (mountains, plateaus, basins). Especially in cases of high-temperature extreme weather, it can more precisely restore the temperature distribution details and spatial textures affected by the terrain, verifying the significant impact of terrain remote sensing data on the accuracy of temperature downscaling. The core contribution of this study lies in the successful construction of a hybrid architecture that can jointly leverage the local feature extraction advantages of CNN and the global context modeling capabilities of Transformer, and effectively integrate key terrain remote sensing data through dedicated modules. The TAUT model offers an effective deep learning solution for precise temperature prediction in complex terrain areas and also provides a referential framework for the integration of remote sensing data and numerical model data in deep learning models. Full article

This study presents a novel methodology that integrates Transformer-based textual analysis from professional networking platforms with traditional demographic variables within a survival analysis framework to predict turnover. Using a dataset comprising 4087 work events from Maimai (a leading professional networking platform in China) spanning 2020 to 2022, our approach combines sentiment analysis and deep learning semantic representations to enhance predictive accuracy and interpretability for HR decision-making. Methodologically, we adopt a hybrid feature-extraction strategy combining theory-driven methods (sentiment analysis and TF-IDF) with a data-driven Transformer-based technique. Survival analysis is then applied to model time-dependent turnover risks, and we compare multiple models to identify the most predictive feature sets. Results demonstrate that integrating textual and demographic features improves prediction performance, specifically increasing the C-index by 3.38% and the cumulative/dynamic AUC by 3.43%. The Transformer-based method outperformed traditional approaches in capturing nuanced employee sentiments. Survival analysis further boosts model adaptability by incorporating temporal dynamics and also provides interpretable risk factors for turnover, supporting data-driven HR strategy formulation. This research advances turnover prediction methodology by combining text analysis with survival modeling, offering small and medium-sized enterprises a practical, data-informed approach to workforce planning. The findings contribute to broader labor market insights and can inform both organizational talent retention strategies and related policy-making. Full article

Deep learning algorithms are pivotal in the identification and classification of microseismic signals in mines subjected to impact pressure. However, conventional machine learning techniques often struggle to balance interpretability, computational efficiency, and accuracy. To address these challenges, this paper presents a hybrid feature selection and Transformer-based model for microseismic signal classification. The proposed model employs a hybrid feature selection method for data preprocessing, followed by an enhanced Transformer for signal classification. The study first outlines the underlying principles of the method, then extracts key seismic features—such as zero-crossing rate, maximum amplitude, and dominant frequency—from various microseismic signal types. These features undergo importance and correlation analyses to facilitate dimensionality reduction. Finally, a Transformer-based classification framework is developed and compared against several traditional deep learning models. The results reveal significant differences in the waveforms and spectra of different microseismic signal types. The selected feature parameters exhibit high representativeness and stability. The proposed model achieves an accuracy of 90.86%, outperforming traditional deep learning approaches such as CNN (85.2%) and LSTM (83.7%) by a considerable margin. This approach provides a reliable and efficient solution for the rapid identification of microseismic events in rockburst-prone mines. Full article

Accurate segmentation of fruit tree leaf diseases is critical for yield protection and precision crop management, yet it is challenging due to complex field conditions, irregular leaf morphology, and diverse lesion patterns. To address these issues, Disease-Seg, a lightweight real-time segmentation framework, is proposed. It integrates CNN and Transformer with a parallel fusion architecture to capture local texture and global semantic context. The Extended Feature Module (EFM) enlarges the receptive field while retaining fine details. A Deep Multi-scale Attention mechanism (DM-Attention) allocates channel weights across scales to reduce redundancy, and a Feature-weighted Fusion Module (FWFM) optimizes integration of heterogeneous feature maps, enhancing multi-scale representation. Experiments show that Disease-Seg achieves 90.32% mIoU and 99.52% accuracy, outperforming representative CNN, Transformer, and hybrid-based methods. Compared with HRNetV2, it improves mIoU by 6.87% and FPS by 31, while using only 4.78 M parameters. It maintains 69 FPS on 512 × 512 crops and requires approximately 49 ms per image on edge devices, demonstrating strong deployment feasibility. On two grape leaf diseases from the PlantVillage dataset, it achieves 91.19% mIoU, confirming robust generalization. These results indicate that Disease-Seg provides an accurate, efficient, and practical solution for fruit leaf disease segmentation, enabling real-time monitoring and smart agriculture applications. Full article

This paper presents a systematic review conducted under the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) framework, analyzing 286 scientific articles focused on vibration-based predictive maintenance strategies for wind turbines within the context of advanced Prognostics and Health Management (PHM). The review combines international standards (ISO 10816, ISO 13373, and IEC 61400) with recent developments in sensing technologies, including piezoelectric accelerometers, microelectromechanical systems (MEMS), and fiber Bragg grating (FBG) sensors. Classical signal processing techniques, such as the Fast Fourier Transform (FFT) and wavelet-based methods, are identified as key preprocessing tools for feature extraction prior to the application of machine-learning-based diagnostic algorithms. Special emphasis is placed on machine learning and deep learning techniques, including Support Vector Machines (SVM), Random Forest (RF), Convolutional Neural Networks (CNN), Long Short-Term Memory networks (LSTM), and autoencoders, as well as on hybrid digital twin architectures that enable accurate Remaining Useful Life (RUL) estimation and support autonomous decision-making processes. The bibliometric and case study analysis covering the period 2020–2025 reveals a strong shift toward multisource data fusion—integrating vibration, acoustic, temperature, and Supervisory Control and Data Acquisition (SCADA) data—and the adoption of cloud-based platforms for real-time monitoring, particularly in offshore wind farms where physical accessibility is constrained. The results indicate that vibration-based predictive maintenance strategies can reduce operation and maintenance costs by more than 20%, extend component service life by up to threefold, and achieve turbine availability levels between 95% and 98%. These outcomes confirm that vibration-driven PHM frameworks represent a fundamental pillar for the development of smart, sustainable, and resilient next-generation wind energy systems. Full article

As distribution networks become increasingly intelligent, primary–secondary integrated distribution switches are replacing the traditional electromagnetic type. However, the high degree of integration intensifies inherent electromagnetic compatibility (EMC) challenges. This paper presents a field-circuit hybrid full-wave model to investigate switch characteristics during lightning strikes. A 3D full-wave model of the switch and a distributed parameter circuit model of the connecting lines are coupled via a network parameter matrix. This approach comprehensively accounts for the impacts of transmission lines and structural components on electromagnetic disturbances. Simulation and experimental results reveal that lightning strikes induce high-frequency damped oscillatory waves, primarily caused by traveling wave reflections along overhead lines. The characteristic frequency of disturbance is inversely proportional to the transmission line length. Additionally, internal components significantly influence this frequency; specifically, a larger voltage dividing capacitance in the voltage transformer results in a lower frequency. Model validation was performed using a 20 m transmission line setup. A 75 kV standard lightning impulse was injected into Phase B. At a distance of 500 mm from the voltage transformer, the measured radiated electric field amplitude was 14.12 kV/m (deviation < 5%), and the characteristic frequency was 1.11 MHz (deviation < 20%). These findings offer vital guidance for the lightning protection and EMC design of primary–secondary integrated distribution switches. Full article

Short-term load forecasting (STLF) underpins the efficient and secure operation of power systems. This study develops and evaluates a hybrid architecture that couples deep neural networks (DNNs) with support vector regression (SVR) for national-scale day-ahead STLF using Croatian load data from 2006 to 2022. The approach employs an hour-specific framework of 24 hybrid models: each DNN learns a compact nonlinear representation for a given hour, while an SVR trained on the penultimate layer activations performs the final regression. Gradient-boosting-based feature selection yields compact, informative inputs shared across all model variants. To overcome limitations of historical local measurements, the framework integrates global numerical weather prediction data from the TIGGE archive with load and local meteorological observations in an operationally realistic setup. In the held-out test year 2022, the proposed hybrid consistently reduced forecasting error relative to standalone DNN-, LSTM- and Transformer-based baselines, while preserving a reproducible pipeline. Beyond using SVR as an alternative output layer, the contributions are as follows: addressing a 17-year STLF task, proposing an hour-specific hybrid DNN–SVR framework, providing a systematic comparison with deep learning baselines under a unified protocol, and integrating global weather forecasts into a practical day-ahead STLF solution for a real power system. Full article

Federated learning enables collaborative model training without sharing raw data, but practical deployments increasingly require verifiable guarantees that clients compute updates correctly. Zero-knowledge proofs can provide such guarantees, yet existing approaches face scalability limits due to the combined cost of polynomial commitments and fast Fourier transform (FFT) intensive verification. Pairing-based schemes offer compact proofs but incur high prover and verifier overhead, while hash-based constructions reduce algebraic cost at the expense of rapidly growing proof sizes. This paper proposes Hybrid-Commit, a polynomial commitment architecture for Binius zero-knowledge proofs that aligns cryptographic primitives with the algebraic structure of federated learning workloads. The scheme separates verification into additive and multiplicative phases: linear aggregation is handled using batched additive commitments optimized for binary fields, while non-linear constraints are verified via hash-based commitments over sparsely selected FFT domains. Proofs from multiple clients are combined through recursive aggregation while preserving non-interactivity. Experiments demonstrate scalability in prover time and proof size (near-constant prover time across 4–11 clients; 160 bytes per client representing 341× and 813× reductions vs. FRI-PCS and Orion), although verification time (762 ms per client) does not scale favorably, making the scheme suitable for bandwidth-constrained scenarios. The scheme achieves under 2% end-to-end training overhead with no impact on model accuracy, indicating that workload-aware commitment design can improve specific scalability dimensions of zero-knowledge verification in federated learning systems. Full article

Digital twin (DT) technology is recognized for its transformative potential to enhance efficiency in the construction process. However, the full potential of DT in construction practices remains largely unrealised. Moreover, few studies explore how DT success factors affect efficiency improvement (EI), energy optimization (EO), and cost control (CC) in the context of economic strength (ES). The study applied a hybrid research method to examine the impact of key DT success factors on EI, EO, and CC under the moderation of ES. After a critical literature review, five key DT success factors were identified. Then, 490 valid questionnaires were analyzed with the Partial Least Squares Structural Equation Model (PLS-SEM) to assess how success factors affect DT effectiveness. This is complemented using extreme gradient boosting (XGBoost) to assess prediction accuracy and understand which factors most influenced EI, EO, and CC. Research shows that ES exerts a significant positive influence on the relationships between most success factors and performance outcomes. High levels of ES enhance the contribution of success factors to performance in EI, EO, and CC. Resource management (RM) has a strong influence on EI and EO, but a weaker influence on CC; process optimization (PO) has the strongest influence on EO, a moderate influence on CC, and the weakest influence on EI; real-time monitoring (R-Tm) primarily affects EI; sustainable design (SD) has a comprehensive and significant regulatory effect on EI, EO, and CC; and predictive maintenance (PM) has a strong influence on both EI and CC. In practice, it offers practical guidance for implementing DT and supports policy and resource planning for building stakeholders. Full article

The growing incorporation of distributed energy resources (DER) in power distribution grids, although pivotal to the energy transition, increases operational variability and amplifies the exposure to disturbances that can compromise resilience and the continuity of service during contingencies. Addressing these challenges requires both a shift toward flexible distribution architectures and the adoption of advanced power electronics interfacing systems. In this setting, this paper proposes a resilience-oriented strategy for medium-voltage (MV) distribution systems and clustered hybrid AC/DC microgrids interfaced through solid-state transformers (SSTs). When a fault occurs along an MV feeder segment, the affected microgrids naturally transition to islanded operation. However, once their local generation and storage become insufficient to sustain autonomous operation, the proposed framework reconfigures the power routing within the cluster by activating an emergency low-voltage DC (LVDC) power path that bypasses the faulted MV section. This mechanism enables controlled power sharing between microgrids during prolonged MV outages, ensuring the supply of priority loads without oversizing SSTs or reinforcing existing infrastructure. Experimental validation on a reduced-scale SST prototype demonstrates stable grid-forming and grid-following operation. The reliability of the proposed scheme is supported by both steady-state and transient experimental results, confirming accurate voltage regulation, balanced sinusoidal waveforms, and low current tracking errors. All tests were conducted at a switching frequency of 50 kHz, highlighting the robustness of the proposed architecture under dynamic operation. Full article

Advances in sensing technologies are increasingly transforming cutting operations by enabling data-driven condition monitoring, predictive maintenance, and process optimization. This review surveys recent developments in sensing modalities for cutting systems, including vibration sensors, acoustic emission sensors, optical and vision-based systems, eddy-current sensors, force sensors, and emerging hybrid/multi-modal sensing frameworks. Each sensing approach offers unique advantages in capturing mechanical, acoustic, geometric, or electromagnetic signatures related to tool wear, process instability, and fault development, while also showing modality-specific limitations such as noise sensitivity, environmental robustness, and integration complexity. Recent trends show a growing shift toward hybrid and multi-modal sensor fusion, where data from multiple sensors are combined using advanced data analytics and machine learning to improve diagnostic accuracy and reliability under changing cutting conditions. The review also discusses how artificial intelligence, Internet of Things connectivity, and edge computing enable scalable, real-time monitoring solutions, along with the challenges related to data needs, computational costs, and system integration. Future directions highlight the importance of robust fusion architectures, physics-informed and explainable models, digital twin integration, and cost-effective sensor deployment to accelerate adoption across various manufacturing environments. Overall, these advancements position advanced sensing and hybrid monitoring strategies as key drivers of intelligent, Industry 4.0-oriented cutting processes. Full article

The high penetration of renewable energy brings significant power fluctuations and operational uncertainties to distribution networks. Traditional power allocation methods for hybrid energy storage systems (HESSs) exhibit strong parameter dependency, limited frequency-domain recognition accuracy, and poor dynamic coordination capability. To overcome these limitations, this study proposes an adaptive power allocation strategy for HESSs under renewable energy integration scenarios. The proposed method employs the Grey Wolf Optimizer (GWO) to jointly optimize the mode number and penalty factor of the Variational Mode Decomposition (VMD), thereby enhancing the accuracy and stability of power signal decomposition. In conjunction with the Hilbert transform, the instantaneous frequency of each mode is extracted to achieve a natural allocation of low-frequency components to the battery and high-frequency components to the supercapacitor. Furthermore, a multi-objective power flow optimization model is formulated, using the power commands of the two storage units as optimization variables and aiming to minimize voltage deviation and network loss cost. The model is solved through the Particle Swarm Optimization (PSO) algorithm to realize coordinated optimization between storage control and system operation. Case studies on the IEEE 33-bus distribution system under both steady-state and dynamic conditions verify that the proposed strategy significantly improves power decomposition accuracy, enhances coordination between storage units, reduces voltage deviation and network loss cost, and provides excellent adaptability and robustness. Full article

We propose the Hybrid Spatio-Temporal Transformer with Multi-Branch CNN/RNN and Extreme-Event Head (HST–MB–CREH), a hybrid spatio-temporal deep learning architecture for joint short-term photovoltaic (PV) power forecasting and the detection of rare extreme events, to support the reliable operation of renewable-rich power systems. The model combines a spatio-temporal transformer encoder with three convolutional neural network (CNN)/recurrent neural network (RNN) branches (CNN → long short-term memory (LSTM), LSTM → gated recurrent unit (GRU), CNN → GRU) and a dense pathway for tabular meteorological and calendar features. A multitask output head simultaneously performs the regression of PV power and binary classification of extremes defined above the 95th percentile. We evaluate HST–MB–CREH on the publicly available Renewable Power Generation and Weather Conditions dataset with hourly resolutions from 2017 to 2022, using a 5-fold TimeSeriesSplit protocol to avoid temporal leakage and to cover multiple seasons. Compared with tree ensembles (RandomForest, XGBoost), recurrent baselines (Stacked GRU, LSTM), and advanced hybrid/transformer models (Hybrid Multi-Branch CNN–LSTM/GRU with Dense Path and Extreme-Event Head (HMB–CLED) and Spatio-Temporal Multitask Transformer with Extreme-Event Head (STM–EEH)), the proposed architecture achieves the best overall trade-off between accuracy and rare-event sensitivity, with normalized performance of RMSE_z = 0.2159 ± 0.0167, MAE_z = 0.1100 ± 0.0085, mean absolute percentage error (MAPE) = 9.17 ± 0.45%, R² = 0.9534 ± 0.0072, and AUC_ext = 0.9851 ± 0.0051 across folds. Knowledge extraction is supported via attention-based analysis and permutation feature importance, which highlight the dominant role of global horizontal irradiance, diurnal harmonics, and solar geometry features. The results indicate that hybrid spatio-temporal multitask architectures can substantially improve both the forecast accuracy and robustness to extremes, making HST–MB–CREH a promising building block for intelligent decision-support tools in smart grids with a high share of PV generation. Full article

The aquatic plant family Lemnaceae, commonly called duckweed or water lentil, has attracted increasing interest in the scientific literature over the past two decades. It holds extraordinary potential as a new crop due to its multiple applications: as an alternative protein source for feed and food production, as a starch producer for renewable biofuel, and for its capacity to provide valuable ecosystem services. Its high biomass productivity, ability to thrive under a wide range of environmental conditions, lack of requirement for arable land, and aptitude for nutrient recycling from wastewater align with the criteria for future sustainable crops. The Lemnaceae is a small plant family comprising a still uncertain number of species and hybrids with largely unexplored genetic diversity, owing to its taxonomic complexity. We focus on critical aspects that must be addressed to establish duckweed as a viable crop: the availability and accessibility of genomic resources to understand the genetic basis of key agronomic traits; the development of protocols for flower induction and crossing; and the establishment of effective methods for genetic transformation and plant regeneration, all aimed at enabling selection and breeding strategies. We highlight the importance of duckweed germplasm collections, including accessions from a wide geographic and ecological range, as essential resources for addressing duckweed diversity and supporting both fundamental research and agronomic applications. Full article

This study investigates the design of bio-hybrid sandwich composites by combining polyester/glass skins with cores reinforced by continuous Musa paradisiaca fibres. The aim is to quantify how fibre weight fraction and alkaline surface treatment control the Charpy impact performance of these systems. Sandwich laminates were manufactured with three fibre loadings in the core (20, 25 and 30 wt.%), using fibres in the as-received condition and after alkaline treatment in NaOH solution. Charpy impact specimens were machined from the laminates and tested according to ISO 179-1. Fibre morphology and fracture surfaces were examined by scanning electron microscopy, while Fourier-transform infrared spectroscopy was used to monitor changes in surface chemistry after alkaline treatment. The combined effect of fibre content and treatment on absorbed energy was assessed through a two-way analysis of variance. Increasing Musa paradisiaca fibre content up to 30 wt.% enhanced the impact energy of the sandwich composites, and alkaline treatment further improved performance by strengthening fibre–matrix adhesion and promoting fibre pull-out, crack deflection and bridging mechanisms. The best Charpy impact response was obtained for cores containing 30 wt.% NaOH-treated fibres, demonstrating that surface modification and optimised fibre loading are effective design parameters for toughening polyester/glass bio-hybrid sandwich composites. Full article