Search Results (95)

High-precision semantic segmentation of remote sensing imagery is crucial in geospatial analysis. It plays an immeasurable role in fields such as urban governance, environmental monitoring, and natural resource management. However, when confronted with complex objects (such as winding roads and dispersed buildings), existing semantic segmentation methods still suffer from inadequate target recognition capabilities and multi-scale representation issues. This paper proposes a neural network model, LMVMamba (LoRA Multi-scale Vision Mamba), for semantic segmentation of remote sensing images. This model integrates the advantages of convolutional neural networks (CNNs), Transformers, and state-space models (Mamba) with a multi-scale feature fusion strategy. It simultaneously captures global contextual information and fine-grained local features. Specifically, in the encoder stage, the ResT Transformer serves as the backbone network, employing a LoRA fine-tuning strategy to effectively enhance model accuracy by training only the introduced low-rank matrix pairs. The extracted features are then passed to the decoder, where a U-shaped Mamba decoder is designed. In this stage, a Multi-Scale Post-processing Block (MPB) is introduced, consisting of depthwise separable convolutions and residual concatenation. This block effectively extracts multi-scale features and enhances local detail extraction after the VSS block. Additionally, a Local Enhancement and Fusion Attention Module (LAS) is added at the end of each decoder block. LAS integrates the SimAM attention mechanism, further enhancing the model’s multi-scale feature fusion capability and local detail segmentation capability. Through extensive comparative experiments, it was found that LMVMamba achieves superior performance on the OpenEarthMap dataset (mIoU 52.3%, OA 69.8%, mF1: 68.0%) and LoveDA (mIoU 67.9%, OA 80.3%, mF1: 80.5%) datasets. Ablation experiments validated the effectiveness of each module. The final results indicate that this model is highly suitable for high-precision land-cover classification tasks in remote sensing imagery. LMVMamba provides an effective solution for precise semantic segmentation of high-resolution remote sensing imagery. Full article

Heat stress is one of the main welfare and productivity problems faced by dairy cattle in Mediterranean climates. The main objective of this work is to predict heat stress in livestock from shade-seeking behavior captured by computer vision, combined with some climatic features, in a completely non-invasive way. To this end, we evaluate two soft computing algorithms—Random Forests and Neural Networks—clarifying the trade-off between accuracy and interpretability for real-world farm deployment. Data were gathered at a commercial dairy farm in Titaguas (Valencia, Spain) using overhead cameras that counted cows in the shade every 5–10 min during summer 2023. Each record contains the shaded-cow count, ambient temperature, relative humidity, and an exact timestamp. From here, three thermal indices were derived: the current THI, the previous-night mean THI, and the day-time accumulated THI. The resulting dataset covers 75 days and 6907 day-time observations. To evaluate the models’ performance a 5-fold cross-validation is also used. The results show that both soft computing models outperform a single Decision Tree baseline. The best Neural Network (3 hidden layers, 16 neurons each, learning rate $={10}^{-3}$) reaches an average RMSE of $14.78$, while a Random Forest (10 trees, depth $=5$) achieves $14.97$ and offers the best interpretability. Daily error distributions reveal a median RMSE of $13.84$ and confirm that predictions deviate less than one hour from observed shade-seeking peaks. Although the dataset came from a single farm, the results generalized well within the observed range. However, the models could not accurately predict the exact number of cows in the shade. This suggests the influence of other variables not included in the analysis (such as solar radiation or wind data), which opens the door for future research. Full article

This study presents an innovative pipeline for processing, compressing, and remotely visualizing large-scale numerical simulations of fluid dynamics in a virtual wind tunnel (VWT), leveraging virtual and augmented reality (VR/AR) for enhanced analysis and high-end visualization. The workflow addresses the challenges of handling massive databases generated using Direct Numerical Simulation (DNS) while maintaining visual fidelity and ensuring efficient rendering for user interaction. Fully immersive visualization of supersonic (Mach number 2.86) spatially developing turbulent boundary layers (SDTBLs) over strong concave and convex curvatures was achieved. The comprehensive DNS data provides insights on the transport phenomena inside turbulent boundary layers under strong deceleration or an Adverse Pressure Gradient (APG) caused by concave walls as well as strong acceleration or a Favorable Pressure Gradient (FPG) caused by convex walls under different wall thermal conditions (i.e., Cold, Adiabatic, and Hot walls). The process begins with a .vts file input from a DNS, which is visualized using ParaView software. These visualizations, representing different fluid behaviors based on a DNS with a high spatial/temporal resolution and employing millions of “numerical sensors”, are treated as individual time frames and exported in GL Transmission Format (GLTF), which is a widely used open-source file format designed for efficient transmission and loading of 3D scenes. To support the workflow, optimized Extract–Transform–Load (ETL) techniques were implemented for high-throughput data handling. Conversion of exported Graphics Library Transmission Format (GLTF) files into Graphics Library Transmission Format Binary files (typically referred to as GLB) reduced the storage by 25% and improved the load latency by 60%. This research uses Unity’s Profile Analyzer and Memory Profiler to identify performance limitations during contour rendering, focusing on the GPU and CPU efficiency. Further, immersive VR/AR analytics are achieved by connecting the processed outputs to Unity engine software and Microsoft HoloLens Gen 2 via Azure Remote Rendering cloud services, enabling real-time exploration of fluid behavior in mixed-reality environments. This pipeline constitutes a significant advancement in the scientific visualization of fluid dynamics, particularly when applied to datasets comprising hundreds of high-resolution frames. Moreover, the methodologies and insights gleaned from this approach are highly transferable, offering potential applications across various other scientific and engineering disciplines. Full article

In this study, we examined the microclimates at eight entrances to a karst system distributed between an elevation of 812 and 906 m in Southern Spain. The karst system, characterised by subvertical open tectonic joints that form narrow shafts, developed on the slope of a mountainous area with a Mediterranean climate and strong chimney effect, resulting in an intense airflow throughout the year. The airflows modify the entrance temperatures, creating a distinctive pattern in each opening that changes with the seasons. The objective of this work is to characterise the outflows and find simple temperature-based parameters that provide information about the karst interior. The entrances were monitored for five years (2017–2022) with temperature–humidity dataloggers at different depths. Other data collected include discrete wind measurements and outside weather data. The most significant parameters identified were the characteristic temperature (T_y), recorded at the end of the outflow season, and the rate of cooling/warming, which ranges between 0.1 and 0.9 °C/month. These parameters allowed the entrances to be grouped based on the efficiency of heat exchange between the outside air and the cave walls, which depends on the rock-boundary geometry. This research demonstrates that simple temperature studies with data recorded at selected positions will allow us to understand geometric aspects of inaccessible karst systems. Dynamic high-airflow cave systems could become a natural source of evidence for climate change and its effects on the underground world. Full article

The observations of atmospheric, oceanic, and sea ice data from the Multidisciplinary drifting Observatory for the Study of Arctic Climate (MOSAiC) expedition were used to analyze the influence of snow redistribution and melt-pond processes on the evolution of sea ice thickness (SIT) in 2019 and 2020. To mitigate the effect of missing atmospheric observations from the time of the expedition, we used ERA5 atmospheric reanalysis along the MOSAiC drift trajectory to force the single-column sea ice model Icepack. SIT simulations from six combinations of two melt-pond schemes and three snow-redistribution configurations of Icepack were compared with observations and analyzed to investigate the sources of model–observation discrepancies. The three snow-redistribution configurations are the bulk scheme, the snwITDrdg scheme, and one simulation conducted without snow redistribution. The bulk scheme describes snow loss from level ice to leads and open water, and snwITDrdg describes wind-driven snow redistribution and compaction. The two melt-pond schemes are the TOPO scheme and the LVL scheme, which differ in the distribution of melt water. The results show that Icepack without snow redistribution simulates excessive snow–ice formation, resulting in an SIT thicker than that observed in spring. Applying snow-redistribution schemes in Icepack reduces snow–ice formation while enhancing the congelation rate. The bulk snow-redistribution scheme improves the SIT simulation for winter and spring, while the bias is large in simulations using the snwITDrdg scheme. During the summer, Icepack underestimates the sea ice surface albedo, resulting in an underestimation of SIT at the end of simulation. The simulations using the TOPO scheme are characterized by a more realistic melt-pond evolution compared to those using the LVL scheme, resulting in a smaller bias in SIT simulation. Full article

Some of the most intense thunderstorms and extreme weather events on Earth occur in the Hindu Kush Himalaya (HKH) region of Southern Asia. The need to provide end users, stakeholders, and decision makers with accurate forecasts and alerts of extreme weather is critical. To that end, a cutting edge weather modeling framework coined the High Impact Weather Assessment Toolkit (HIWAT) was created through the National Aeronautics and Space Administration (NASA) SERVIR Applied Sciences Team (AST) effort, which consists of a suite of varied numerical weather prediction (NWP) model runs to provide probabilities of straight-line damaging winds, hail, frequent lightning, and intense rainfall as part of a daily 54 h forecast tool. The HIWAT system was first deployed in 2018, and the recently released model archive hosted by the Global Hydrometeorology Resource Center (GHRC) Distributed Active Archive Center (DAAC) provides daily model outputs for the years of 2018–2022. With a nested modeling domain covering Nepal, Bangladesh, Bhutan, and Northeast India, the HIWAT archive spans the critical pre-monsoon and monsoon months of March–October when severe weather and flooding are most frequent. As part of NASA’s Transformation To Open Science (TOPS), this data archive is freely available to practitioners and researchers. Full article

Exposure modeling plays a crucial role in disaster risk assessments by providing geospatial information about assets at risk and their characteristics. Detailed exposure data enhances the spatial representation of a rapidly changing environment, enabling decision-makers to develop effective policies for reducing disaster risk. This work proposes and demonstrates a methodology linking volunteered geographic information from OpenStreetMap (OSM), street-level imagery from Google Street View (GSV), and deep learning object detection models into the automated creation of exposure datasets for power grid transmission towers, assets particularly vulnerable to strong wind, and other perils. Specifically, the methodology is implemented through a start-to-end pipeline that starts from the locations of transmission towers derived from OSM data to obtain GSV images capturing the towers in a given region, based on which their relevant features for risk assessment purposes are determined using two families of object detection models, i.e., single-stage and two-stage detectors. Both models adopted herein, You Only Look Once version 5 (YOLOv5) and Detectron2, achieved high values of mean average precision (mAP) for the identification task (83.67% and 88.64%, respectively), while Detectron2 was found to outperform YOLOv5 for the classification task with a mAP of 64.89% against a 50.62% of the single-stage detector. When applied to a pilot study area in northern Portugal comprising approximately 5.800 towers, the two-stage detector also exhibited higher confidence in its detection on a larger part of the study area, highlighting the potential of the approach for large-scale exposure modeling of transmission towers. Full article

This paper introduces a novel field-oriented control (FOC) strategy for an open-end stator three-phase winding induction motor (OEW-TP-IM) using dual space vector modulation-pulse width modulation (SVM-PWM) inverters. This configuration reduces common mode voltage at the motor’s terminals, enhancing efficiency and reliability. The study presents a backstepping control approach combined with a mean value theorem (MVT)-based observer to improve control accuracy and stability. Stability analysis of the backstepping controller for key control loops, including flux, speed, and currents, is conducted, achieving asymptotic stability as confirmed through Lyapunov’s methods. An advanced observer using sector nonlinearity (SNL) and time-varying parameters from convex theory is developed to manage state observer error dynamics effectively. Stability conditions, defined as linear matrix inequalities (LMIs), are solved using MATLAB R2016b to optimize the observer’s estimator gains. This approach simplifies system complexity by measuring only two line currents, enhancing responsiveness. Comprehensive simulations validate the system’s performance under various conditions, confirming its robustness and effectiveness. This strategy improves the operational dynamics of OEW-TP-IM machine and offers potential for broad industrial applications requiring precise and reliable motor control. Full article

Today, power electronic-based converters are at the core of many modern systems, such as smart grids and electric vehicles. In this context, the Dual Two-Level Inverter (DTLI) supplying an open-end winding machine offers an innovative and promising solution for marine propulsion, aeronautics, and electric vehicles. This configuration provides several advantages, including a reduced DC bus voltage, enhanced fault tolerance, and improved overall system performance. However, ensuring optimal energy efficiency and high-power quality remains a major challenge given the increasing demands for performance and sustainability. This paper presents a state-of-the-art review of the main DTLI configurations and their impact on system performance. Three architectures are analyzed, highlighting their benefits and limitations. This study aims to demonstrate the influence of the DC bus voltage ratio and pulse width modulation strategies on power quality and energy efficiency. The objective is to enhance the understanding of the DTLI’s potential and to guide its integration into other electrical systems. Full article

High-torque-density motors are essential in humanoid, wearable, and rehabilitation robots due to their ability to minimize gear ratios, improve back-drivability, and support compact joint design. However, their inherently high back-EMF limits speed performance, and safety regulations often constrain supply voltages to below 50 V in human-interactive environments. To overcome these limitations, this study introduces a novel winding strategy called parallel open-end winding (POEW), which combines the benefits of two individual approaches: Parallel Connected Winding (PCW) and Open-End Winding (OEW). PCW reduces phase resistance and inductance, thereby mitigating voltage drop and back-EMF, while OEW eliminates the neutral point, allowing full-phase voltage utilization. Experimental results show that the POEW configuration achieves a 3.5-fold increase in maximum speed compared to the conventional Series-Connected Winding (SCW), without altering the rotor or stator structure. Torque constant measurements confirm that all proposed configurations maintain torque output with minimal variation. Although the motor constant slightly decreases due to the higher current in parallel paths, the significant speed enhancement under low-voltage conditions demonstrates the practicality and effectiveness of POEW for advanced robotic applications requiring both high torque and speed. Full article

Modular construction is a modern and efficient type of construction that has gained wide recognition in the construction industry. Limited research has been conducted on how large door openings affect the stress state of modular blocks. The present study aims to investigate the features of the stressed state of modular blocks with large door openings and the effect of size and place of the doors on the openings on the overall structural behavior of the building. Four full-scale (room-sized) modular blocks of the “lying cup” type were tested to failure under vertical loading with eccentricity simulating wind effects. The varied parameters of the specimens included concrete strength and the size of the window openings. Experimental results revealed that crack opening characteristics, main load-bearing wall deformations, horizontal deflections, and failure patterns under vertical loads are directly influenced by the small thickness and increased flexibility of the blocks. The effects of size and the placement of openings on the overall structural behavior of the building were analyzed. Tests revealed the distribution of compressive stresses in the main load-bearing walls of the “lying cup” blocks with an embedded reinforced concrete panel, considering vertical load eccentricity. Maximum compressive stresses in the longitudinal walls reached 70–80% of concrete strength, while in end walls and panel walls, they were 50–60%. Additionally, non-uniform deformations were observed in the supports of main load-bearing walls near the conjunction with the end walls and the edges of door openings. Average compressive strains in these walls were in the range of 470–500 × 10⁻⁶, which corresponds to 22–29% of the cylindrical compressive strength of concrete. Partial factors accounting for loading conditions were introduced, allowing for further processing and the evaluation of the experimental data along with developing methods of analysis of buildings constructed with modular blocks. Full article

Electric Vehicles (EVs) are set to play a crucial role in the energy transition. Although EVs offer significant environmental benefits, their technology still faces major challenges related to performance optimization, energy efficiency improvement, and cost reduction. A key point to address these challenges is the accurate identification of the speed/torque operating points of the drive systems. However, this identification is generally achieved using mechanical sensors, which are fragile, bulky, and expensive. This paper aims to develop, implement, and validate a speed/torque observer in real time based on the Extended Kalman Filter (EKF) approach for an EV equipped with an Open-End Winding Induction Motor with Dual Inverter (OEWIM-DI). The implementation of the EKF is based on the state modeling of the OEWIM-DI, enabling the observation of the torque and speed using voltage and current measurements. The validation of this approach is conducted experimentally on the FPGA and DS1104 boards. The results show that this approach offers excellent performance in terms of accuracy, stability, and real-time response speed. These results suggest that the proposed method could significantly contribute to the advancement of EV technology by providing a more robust and cost-effective alternative to traditional mechanical sensors while improving the overall efficiency and performance of EV drive systems. Full article

The rise of high-rise vertical farms in cities is helping to mitigate urban constraints on crop production, including land, transportation, and yield requirements. However, separate issues arise regarding energy consumption. The utilisation of wind energy resources in high-rise vertical farms is therefore on the agenda. In this study, we investigate the aerodynamic performance of an ellipsoidal tall building with large openings to determine, on the one hand, the threshold income wind that could impact human comfort, and on the other, the turbulence intensity at specific locations on the roof and façade where micro-wind turbines could operate. To this end, we calculate the wind pressure coefficient and turbulence intensity of two scale models tested within a wind tunnel facility and compare the results with a separate CFD simulation completed in the past. The results confirm that the wind turbines installed on the building façade at a height of at least z/h = 0.725 can operate properly when the inlet wind speed is greater than 7 m/s. Meanwhile, the wind regime on the roof is more stable, which could yield higher energy harvesting via wind turbines. Furthermore, we observe that the overall aerodynamic performance of the models tested best under wind flowing at angles of 45° and 60° with respect to their centreline, whereas the turbulence at the wind envelope compares to that of the free wind flow at roof height. Full article

The fuel economy of electric vehicles (EVs) is an important factor in determining the competitiveness of EVs. Since the fuel economy is affected by the efficiency of an e-powertrain composed of a motor and inverter, it is necessary to select a high-efficiency topology for the e-powertrain. In this paper, a novel topology of e-powertrains to improve the fuel economy of EVs is proposed. The proposed topology aims to improve the system efficiency by integrating open-end winding (OEW) and winding changeover (WC). The proposed OEW-PMSM with WC enables to drive a permanent magnet synchronous motor (PMSM) in four different modes. Each mode can increase inverter efficiency and motor efficiency by changing motor parameters and maximum modulation index. In this paper, the system efficiency of the proposed topology was evaluated using electromagnetic finite element analysis and a loss model of power semiconductors. In addition, the vehicle simulations were performed to evaluate the fuel economy of the proposed topology, thereby proving the superiority of the proposed topology compared with the conventional PMSM. Full article

The monitoring of coastal evolution (coastline and associated geomorphological features) caused by episodic and persistent processes associated with climatic and anthropic activities is required for coastal management decisions. The availability of open access, remotely sensed data with increasing spatial, temporal, and spectral resolutions, is promising in this context. The coastline of Northern Tunisia is currently showing geomorphic process, such as increasing erosion associated with lateral sedimentation. This study aims to investigate the potential of time-series optical data, namely Landsat (from 1985–2019) and Google Earth^® satellite imagery (from 2007 to 2023), to analyze shoreline changes and morphosedimentary and geomorphological processes between Cape Serrat and Kef Abbed, Northern Tunisia. The Digital Shoreline Analysis System (DSAS) was used to quantify the multitemporal rates of shoreline using two metrics: the net shoreline movement (NSM) and the end-point rate (EPR). Erosion was observed around the tombolo and near river mouths, exacerbated by the presence of surrounding dams, where the NSM is up to −8.31 m/year. Despite a total NSM of −15 m, seasonal dynamics revealed a maximum erosion in winter (71% negative NSM) and accretion in spring (57% positive NSM). The effects of currents, winds, and dams on dune dynamics were studied using historical images of Google Earth^®. In the period from 1994 to 2023, the area is marked by dune face retreat and removal in more than 40% of the site, showing the increasing erosion. At finer spatial resolution and according to the synergy of field observations and photointerpretation, four key geomorphic processes shaping the coastline were identified: wave/tide action, wind transport, pedogenesis, and deposition. Given the frequent changes in coastal areas, this method facilitates the maintenance and updating of coastline databases, which are essential for analyzing the impacts of the sea level rise in the southern Mediterranean region. Furthermore, the developed approach could be implemented with a range of forecast scenarios to simulate the impacts of a higher future sea-level enhanced climate change. Full article