Search Results (38)

Machine learning approaches to wildfire spread prediction are constrained by the lack of standardized, multi-source, spatiotemporal datasets that fuse terrain, weather, and fire-state information into a single ML-ready format. We present WildfireCube, a reproducible event-centric pipeline and methodology for constructing dense fourth-order spatiotemporal tensors of shape (T, C, H, W) at 30 m spatial and 3 h temporal resolution. Following the analysis-ready data convention established in the Earth Observation community, the pipeline fuses four open data sources: the Copernicus GLO-30 Digital Elevation Model for static terrain derivatives, ERA5-Land reanalysis for hourly weather forcing, Sentinel-2 Level-2A imagery for spectral vegetation and burn-severity indices, and NASA FIRMS active-fire hotspot detections for fire-state reconstruction via ordinary kriging. The resulting 13-channel normalized tensor separates causal drivers into three physically motivated groups: static landscape controls (elevation, slope, aspect, fuel load), dynamic atmospheric forcings (wind components, temperature, precipitation), and evolving fire state (fire-front mask, burn severity, fractional burn, observation confidence). A physics-informed normalization framework maps all channels to bounded ranges using fixed physical constants rather than sample statistics, ensuring cross-event comparability and exact invertibility. We demonstrate the pipeline on 13 wildfire events across the United States, Canada, and Greece (2017–2023), producing a processed catalog exceeding 300 GB compressed and spanning a 14-fold range in burned area, a 27 °C range in mean temperature, and different fire regimes. Event tensors are stored in chunked Zarr archives with Zstandard compression, achieving a 2.58× compression ratio. As future work, the pipeline will be applied to a 40-event target catalog projected to exceed 2 TB of raw data, providing the multi-regime diversity and scale required for training robust deep learning models for spatiotemporal wildfire prediction. Full article

Diamondback moth (DBM, Plutella xylostella) outbreaks are shaped by delayed meteorological conditions, yet most forecasting models compress weather into a few monthly summaries and provide limited ecological interpretation. We propose MeteoSCOPE, an ontology-aware sparse Perceiver framework for interpretable, multi-horizon retrospective forecasting of DBM abundance from historical pest records and rich meteorological descriptors. Each feature-lag value is encoded as a token carrying feature identity, ecological group, descriptor type, lag position, and seasonal information; in the rich setting, 138 descriptors across 12 months yield 1656 tokens per sample. Sparse cross-attention compresses these tokens into a compact latent representation, while horizon-specific queries produce one- to four-month-ahead forecasts. Attention tensors and a common-plus-residual branch are aggregated into feature-, group-, descriptor-, lag-, horizon-, and residual-level explanations. Using DBM records from Huiyang and Shantou, Guangdong, MeteoSCOPE achieved the strongest overall retrospective performance, with robust gains at Shantou and metric-dependent gains at Huiyang. The explanations identified pest history as the leading attended group at both sites and surfaced site-specific secondary attributions for soil moisture, weather state, wind, soil temperature, and humidity, treated as model evidence rather than causal ecological effects and corroborated by independent occlusion and KernelSHAP analyses. Strict zero-shot cross-site transfer degrades substantially, so prospective field validation and broader multi-site testing remain required before operational deployment. MeteoSCOPE thus provides a transferable methodological framework (not a deployable forecaster) for interpretable analysis of high-dimensional agricultural time series. Full article

Renewable energy sources play a critical role in modern energy production and transmission systems. This paper presents a GIS-enhanced deep learning framework for spatially informed renewable energy potential assessment, integrating environmental variables with Geographic Information Systems (GIS) to support sustainable energy planning aligned with the United Nations Sustainable Development Goals (SDGs). A synthetic dataset comprising 100 distinct geographical regions was constructed using key environmental parameters, including solar irradiance, wind speed, temperature, relative humidity, and altitude. The dataset was further enriched with GIS-based spatial attributes (latitude and longitude) and aggregated historical energy production records used as reference values for supervised learning, without explicit temporal modeling. The standardized dataset was divided into training and testing subsets using an 80:20 split and employed to train a neural network implemented using TensorFlow’s Sequential API. The architecture incorporated dense layers and dropout regularization to prevent overfitting, and was trained for 50 epochs with a batch size of 16 using the Adam optimizer and mean squared error (MSE) loss. The model achieved stable convergence, with training loss reducing from 98,273.70 to 16,651.12 and consistent validation performance, indicating strong generalization. Model outputs were integrated with GIS tools to generate spatial visualizations of energy potential, revealing distinct geographical patterns and clusters relevant for grid planning and resource allocation. By explicitly embedding spatial features into the learning process, the proposed approach provides accurate and interpretable energy potential estimates, supporting informed decision-making for renewable energy deployment and contributing to SDG 7 (clean energy), SDG 9 (resilient infrastructure), and SDG 13 (climate action). Full article

Modern smart cities face increasing pressure to invest in sustainable and reliable energy systems while navigating uncertainties arising from fluctuating market conditions, evolving technology landscapes, and diverse expert opinions. Traditional multi-criteria decision-making (MCDM) approaches often fail to fully represent these uncertainties as they typically rely on crisp inputs, lack temporal memory, and do not explicitly account for stochastic variability. To address these limitations, this study introduces a novel Stochastic Fractional Fuzzy Tensor (SFFT)-based Group Decision-Making framework. The proposed approach integrates three dimensions of uncertainty within a unified mathematical structure: fuzzy representation of subjective expert assessments, fractional temporal operators (Caputo derivative, $\alpha =0.85$) to model the influence of historical evaluations, and stochastic diffusion terms ($\sigma =0.05$) to capture real-world volatility. A complete decision algorithm is developed and applied to a realistic smart city renewable energy selection problem involving six alternatives and six criteria evaluated by three experts. The SFFT-based evaluation identified Geothermal Energy as the optimal choice with a score of 0.798, followed by Offshore Wind (0.722) and Waste-to-Hydrogen (0.713). Comparative evaluation against benchmark MCDM methods—TOPSIS (Technique for Order Preference by Similarity to Ideal Solution), VIKOR (VIšekriterijumsko KOmpromisno Rangiranje), and WSM (Weighted Sum Model)—demonstrates that the SFFT approach yields more robust and stable rankings, particularly under uncertainty and model perturbations. Extensive sensitivity analysis confirms high resilience of the top-ranked alternative, with Geothermal retaining the first position in 82.4% of 5000 Monte Carlo simulations under simultaneous variations in weights, memory parameter ($\alpha \in [0.25,0.95]$), and noise intensity ($\sigma \in [0.01,0.10]$). This research provides a realistic, mathematically grounded, and decision-maker-friendly tool for strategic planning in uncertain, dynamic urban environments, with strong potential for deployment in wider engineering, management, and policy applications. Full article

Wind turbine blade damage detection is crucial for advancing wind energy as a sustainable alternative to fossil fuels. Existing methods based on image processing technologies face challenges such as limited adaptability to complex environments, trade-offs between model accuracy and computational efficiency, and inadequate real-time inference capabilities. In response to these limitations, we put forward MSWindD-YOLO, a lightweight real-time detection model for wind turbine blade damage. Building upon YOLOv5s, our work introduces three key improvements: (1) the replacement of the Focus module with the Stem module to enhance computational efficiency and multi-scale feature fusion, integrating EfficientNetV2 structures for improved feature extraction and lightweight design, while retaining the SPPF module for multi-scale context awareness; (2) the substitution of the C3 module with the GBC3-FEA module to reduce computational redundancy, coupled with the incorporation of the CBAM attention mechanism at the neck network’s terminus to amplify critical features; and (3) the adoption of Shape-IoU loss function instead of CIoU loss function to facilitate faster model convergence and enhance localization accuracy. Evaluated on the Wind Turbine Blade Damage Visual Analysis Dataset (WTBDVA), MSWindD-YOLO achieves a precision of 95.9%, a recall of 96.3%, an mAP@0.5 of 93.7%, and an mAP@0.5:0.95 of 87.5%. With a compact size of 3.12 MB and 22.4 GFLOPs inference cost, it maintains high efficiency. After TensorRT acceleration on Jetson Orin NX, the model attains 43 FPS under FP16 quantization for real-time damage detection. Consequently, the proposed MSWindD-YOLO model not only elevates detection accuracy and inference efficiency but also achieves significant model compression. Its deployment-compatible performance in edge environments fulfills stringent industrial demands, ultimately advancing sustainable wind energy operations through lightweight lifecycle maintenance solutions for wind farms. Full article

To address the high vibration and noise in fractional-slot concentrated-winding permanent magnet synchronous machines for electric vehicles, this study focuses on a 30-pole, 36-slot fractional-slot concentrated-winding permanent magnet synchronous machine. These issues are mainly caused by the modulation of high-order radial electromagnetic forces into low-order radial electromagnetic forces, known as the teeth modulation effect. The characteristics of radial electromagnetic forces are analyzed using the Maxwell stress tensor method, and the modulation process is examined. A novel unequal-teeth stator structure is proposed to reduce vibration and noise. Finite element simulations are performed to investigate how this structure affects the amplitude of modulated low-order radial electromagnetic forces. The optimal ratio of the unequal-teeth design is identified to effectively suppress the modulation effect. Simulation results indicate that an appropriately chosen unequal-teeth proportion leads to significant improvements in the machine’s vibration and noise performance across various operating conditions, providing a preliminary validation of the feasibility and effectiveness of the proposed unequal-teeth design methodology. Full article

Axial flux motors have gained widespread attention in the field of electric vehicles. The stator may exert a unilateral axial force on the dual rotors under uneven air gaps. The unbalanced magnetic pull can influence the production and processing of the motor, leading to issues such as vibrations, bearing degradation, reduced lifespan, and torque reduction attributed to the bearings. Accurate evaluation of the unilateral magnetic pull can reduce costs associated with bearing protection. For dual-rotor motors, the axial forces of the rotors act in opposite directions with nearly equal magnitudes, resulting in the catastrophic cancellation of unbalanced magnetic pull calculations. A similar phenomenon may occur between coils, introducing computational errors. To avoid these errors, the stator was selected as the computational target for unilateral axial force calculations. The integration domain was defined to encompass the entire air region containing all windings, rather than summing individual force components. This merged integration approach was mathematically validated through the Maxwell stress tensor method. Finally, the obtained stator axial force closely matched the rotor axial force in magnitude, demonstrating the accuracy of the proposed method. Full article

This study, based on existing research on the dynamic response of transmission tower–line systems under wind and rain loads, proposes a method for predicting these responses using the TimesNet deep learning surrogate model. Initially, a numerical model of the tower–line system is developed to generate dynamic response time series data under the influence of wind velocity and rainfall forces. Wind velocity and precipitation intensity are used as inputs for the surrogate model, with the tower’s maximum displacement and the highest tension in the line serving as the corresponding outputs. Afterward, the fast Fourier transform (FFT) is used to transform the original one-dimensional input signals into their corresponding two-dimensional representations. Feature extraction is then performed using an Inception module with 2D convolutional kernels of varying sizes. Finally, based on the amplitude-weighted information obtained through the FFT, the two-dimensional tensors are transformed back into one-dimensional output signals. The experimental results show that the proposed surrogate model provides highly accurate dynamic response predictions, even under complex conditions involving the interaction between transmission towers and lines, as well as the combined effects of wind and rainfall. Full article

The transport of pollutants with flowing waters is one of the most common processes in the natural environment. In general, this process is described by a system of differential equations, including the continuity equation, dynamic equations, pollutant transport equations and equations of state. For the analyzed problem of pollutant migration in wide rivers and the coastal zone, a two-dimensional model is particularly useful because the velocity and mass concentration profile is vertically averaged. In this model, taking into account the dispersion flux leads to appropriate equations, and the dispersion process is described by the dispersion tensor. Due to the transverse isotropy of the dispersion process, the coordinates of this tensor are expressed in terms of local dispersion coefficients along the direction of the velocity and in the direction perpendicular to it. Commonly used methods for determining mass dispersion coefficients refer to a gradient velocity profile, typical for rivers. However, in the coastal zone, the velocity profile changes from gradient to drift when shear stresses on the surface caused by the wind begin to dominate. The drift profile also occurs in estuaries, where there is a difference in the density of fresh and salt water. This paper analyzes the numerical solution of the two-dimensional dispersion equations in the coastal zone for the dispersion coefficients adopted for the gradient and drift velocity profiles and then assesses how this affects the final result. Four typical scenarios of pollutant migration in the coastal zone of the Bay of Puck are presented. The calculated dispersion coefficients differ significantly depending on the adopted velocity profile: for the gradient, D_LG = 0.17 [m²/s], and for the drift, D_LD = 89.94 [m²/s]. Full article

In response to an investigation on the paths of changes in the crystallization and radial differences during the forming process of nascent fibers, in this study, we conducted numerical simulation and analyzed the changes in crystallization mechanical parameters and tensile properties through a fluid dynamics two-phase model. The model was based on the melt-spinning method focusing on melt spinning, the environment of POLYFLOW, and the method of joint simulation, coupled with Nakamura crystallization kinetics, including the development of process collaborative parameters, stretch-induced crystallization, viscoelasticity, filament cooling, gravity term, inertia, and air resistance. Finally, for nylon 6 BHS and CN9987 resin spinning, the model successfully predicted the distribution changes in temperature, velocity, strain rate tensor, birefringence, and stress tensor along the axial and radial fibers and obtained the variation pattern of fibers’ crystallinity along the entire spinning process under different stretching rates. Furthermore, we also explored the effects of spinning conditions, including inlet flow rate, winding speeds, and the extrusion temperature, on the fibers’ crystallization process and obtained the influence rules of different spinning conditions on fiber crystallization. Knowing the paths of changes in mechanical performance can provide important guidance and optimization strategies for the future industrial preparation of high-performance fibers. Full article

Space plasma turbulence is inherently characterized by anisotropic fluctuations. The generalized k-th order correlation tensor of magnetic field increments allow us to separate the mixed isotropic and anisotropic structure functions from the purely anisotropic ones. In this work, we quantified the relative importance of anisotropic fluctuations in solar wind turbulence using two Alfvénic data samples gathered by the Solar Orbiter at 0.8 astronomical units. The results based on the joined statistics suggest that the anisotropic fluctuations are ubiquitous in solar wind turbulence and persist at kinetic scales. Using the $RTN$ coordinate system, we show that their presence depends on the anisotropic sector under consideration, e.g., the $RN$ and $RT$ sectors exhibit enhanced anisotropy toward kinetic scales, in contrast with the $TN$. We then study magnetic field fluctuations parallel and perpendicular to the local mean magnetic field separately. We find that perpendicular fluctuations are representative of the global statistics, resembling the typical picture of magnetohydrodynamic turbulence, whereas parallel fluctuations exhibit a scaling law with slope ∼1 for all the joined isotropic and anisotropic components. These results are in agreement with predictions based on the critical balance phenomenology. This topic is potentially of interest for future space missions measuring kinetic and MHD scales simultaneously in a multi-spacecraft configuration. Full article

Growing concern about climate change has intensified efforts to use renewable energy, with wind energy highlighted as a growing source. It is known that wind turbines are characterized by distinct operating modes that reflect production efficiency. In this work, we focus on the forecasting problem for univariate discrete-valued time series of operating modes. We define three prediction strategies to overcome the difficulties associated with missing data. These strategies are evaluated through experiments using five forecasting methods across two real-life datasets. Two of the forecasting methods have been introduced in the statistical literature as extensions of the well-known context algorithm: variable length Markov chains and Bayesian context tree. Additionally, we consider a Bayesian method based on conditional tensor factorization and two different smoothers from the classical tools for time series forecasting. After evaluating each pair prediction strategy/forecasting method in terms of prediction accuracy versus computational complexity, we provide guidance on the methods that are suitable for forecasting the time series of operating modes. The prediction results that we report demonstrate that high accuracy can be achieved with reduced computational resources. Full article

This paper investigates the development of a deep learning-based flight control model for a tilt-rotor unmanned aerial vehicle, focusing on altitude, speed, and roll hold systems. Training data is gathered from the X-Plane flight simulator, employing a proportional–integral–derivative controller to enhance flight dynamics and data quality. The model architecture, implemented within the TensorFlow framework, undergoes iterative tuning for optimal performance. Testing involved two scenarios: wind-free conditions and wind disturbances. In wind-free conditions, the model demonstrated excellent tracking performance, closely tracking the desired altitude. The model’s robustness is further evaluated by introducing wind disturbances. Interestingly, these disturbances do not significantly impact the model performance. This research has demonstrated data-driven flight control in a tilt-rotor unmanned aerial vehicle, offering improved adaptability and robustness compared to traditional methods. Future work may explore further flight modes, environmental complexities, and the utilization of real test flight data to enhance the model generalizability. Full article

In order to solve the electromagnetic force optimization problem of a high-power-density ironless Halbach-type permanent magnet synchronous linear motor, this paper adopts an electromagnetic force optimization method based on magnetic field analysis, electromagnetic force modeling, and genetic algorithm optimization: Firstly, the magnetic field of the Halbach permanent magnet array is solved by the combination of the equivalent magnetization strength method and the pseudo-periodic method, which takes into account the influence of the edge effect of the secondary magnetic field, and the magnetic field of the primary winding is solved by Fourier series expansion method. Secondly, the Maxwell tensor method is used to establish the functional relationship between the electromagnetic thrust and the main structural parameters of the unilateral motor. Finally, based on the parameter sensitivity analysis of the optimized variables and the response surface calculation, the optimal combination of the optimized variables to meet the optimization objective is found by a genetic algorithm. This method of the accurate modeling and optimization of an electromagnetic force can accurately calculate the motor air gap magnetic field and electromagnetic thrust, and the optimization speed is fast, which can greatly save time. The optimization results show that, under the premise of constant input power, the unilateral average thrust of the motor is increased by 18.75%, the peak value of thrust fluctuation is decreased by 30.27%, and the results match well with the finite element results, which verifies the correctness of the optimization results of the electromagnetic force and the reasonableness of the optimization method. Full article

Wind power is an essential component of renewable energy. It enables the conservation of conventional energy sources such as coal and oil while reducing greenhouse gas emissions. To address the stochastic and intermittent nature of ultra-short-term wind power, a combined prediction model based on variational mode decomposition (VMD) and gradient boosting regression tree (GBRT) is proposed. Firstly, VMD is utilized to decompose the original wind power signal into three meaningful components: the long-term component, the short-term component, and the randomness component. Secondly, based on the characteristics of these three components, a support vector machine (SVM) is selected to predict the long-term and short-term components, while gated recurrent unit-long short-term memory (GRU-LSTM) is employed to predict the randomness component. Particle swarm optimization (PSO) is utilized to optimize the structural parameters of the SVM and GRU-LSTM combination for enhanced prediction accuracy. Additionally, a GBRT model is employed to predict the residuals. Finally, the rolling predicted values of the three components and residuals are aggregated. A deep learning framework using TensorFlow 2.0 has been built on the Python platform, and a dataset measured from a wind farm has been utilized for learning and prediction. The comparative analysis reveals that the proposed model exhibits superior short-term wind power prediction performance, with a mean squared error, mean absolute error, and coefficient of determination of 0.0244, 0.1185, and 0.9821, respectively. Full article