Search Results (25)

Seasonal tropical wetlands such as the Brazilian Pantanal are increasingly threatened by climate variability and extreme hydrological events, creating a need for robust monitoring tools that capture flood dynamics at high spatial and temporal resolution. This study used Sentinel-1 Synthetic Aperture Radar (SAR) imagery to map and monitor flooding in the northern Pantanal, a Ramsar site renowned for its wildlife, between 2017 and 2020. Ground Range Detected (GRD) VV-polarized scenes were preprocessed using radiometric terrain normalization and speckle filtering (Lee filter, 5 × 5 window) to improve the separability of water and non-water surfaces. Flooded areas were initially extracted with Otsu’s histogram thresholding and validated using high-resolution optical imagery (PlanetScope and Landsat-8). A supervised Random Forest classifier then refined land-cover discrimination into three classes (open water/flood, open land/vegetation, and others), achieving an overall accuracy of 97.70% on the independent testing dataset (n = 6622), while temporal consistency was supported by Cuiabá River hydrological data. The results revealed strong interannual variability in flood extent, with inundation covering 34.7% of the reserve in March 2017 compared with 0.75% in March 2020 and reaching a peak of 79.9% in April 2017. Overall, Sentinel-1 SAR effectively delineated open water and flood-affected surfaces under persistent cloud cover, demonstrating its value for complementing existing products such as MapBiomas, strengthening wetland management, and supporting scalable flood monitoring in other tropical flood-prone Ramsar sites. Full article

The variability of renewable energy sources, coupled with the decentralised configuration of distributed generation (DG), significantly complicates grid management, necessitating sophisticated visual analytics to enhance power system performance and energy distribution. This paper presents a probabilistic visualisation technique based on polar histograms to identify the dynamic influence zones of DG units by analysing line current flows. The proposed framework explicitly accounts for the probabilistic representation of reverse power flows, which provides an overall view of DG impacts on distribution networks. Quasi-dynamic simulations are conducted on a 33-bus distribution system using DIgSILENT PowerFactory 2020, MATLAB R2020, and Python 3.8. The results demonstrate that the polar histogram approach provides intuitive insights into DG influence, revealing zones of grid-dominated, DG-dominated, and shared interactions. These findings act as a potential practical tool for voltage management, demand balancing, and secure integration of renewable DG units into modern power grids. Full article

With the rapid development of Internet of Things (IoT) and Artificial Intelligence (AI) technologies, information security has become a critical issue. To develop a highly secure image encryption transmission system, this study proposes a novel key generation mechanism based on the combination of fractional-order chaotic system synchronization control and the SHA-256 algorithm. This proposed method dynamically generates high-quality synchronous random number sequences and is combined with the Advanced Encryption Standard (AES) algorithm. To quantitatively evaluate the mechanism, the generated sequences are tested using NIST SP 800-22, ENT, and DIEHARD suites. The comparative results show that the key generation mechanism produces sequences with higher randomness and unpredictability. In the evaluation of image encryption, histogram distribution, information entropy, adjacent pixel correlation, NPCR, and UACI are used as performance metrics. Experimental results show that the histogram distributions are uniform, the values of information entropy, NPCR, and UACI are close to their ideal levels, and the pixel correlation is significantly reduced. Compared to recent studies, the proposed method demonstrates higher encryption performance and stronger resistance to statistical attacks. Furthermore, the system effectively addresses key distribution and management problems inherent in traditional symmetric encryption schemes. These results validate the reliability and practical feasibility of the proposed approach. Full article

Present financial markets are characterized by great volatility and nonlinear dynamics since they are driven by both quantitative forces and qualitative mood. Traditional trading practices cannot capture such nuance. This study proposes an automated trading system based on machine learning that uses technical analysis as well as sentiment factors for better decision-making. Historical OHLCV stock price data from 2000 to 2025 was augmented with financial indicators such as SMA, EMA, RSI, and Bollinger Bands, as well as sentiment scores based on real-time news via natural language processing. LightGBM regression for predicting the price range and Histogram-Based Gradient Boosting classification for directional prediction were employed. Signals were generated with volatility-adjusted thresholds and classifier confirmation, and a risk management layer enforced position sizing, stop-loss triggering, and drawdown constraint. Back testing demonstrated improved Sharpe ratio, Sortino ratio, and win rates versus baseline strategies. The findings emphasize that the combination of machine learning and sentiment analysis with risk-conscious design improves predictive accuracy, dependability, and preservation of capital in automated trading systems. Full article

Monitoring microbial water quality at recreational beaches is essential to safeguard public health, with fecal coliforms serving as key indicators of contamination. This study applies machine learning (ML) techniques to predict fecal coliform concentrations at Montevideo’s urban beaches, aiming to support proactive and data-driven coastal water quality management. Using an extensive monitoring dataset, we developed and calibrated five ML models to predict continuous fecal coliform levels, improving upon traditional threshold-based methods. Among these, Random Forest (RF) and Histogram-based Gradient Boosting (HGB) models showed very good predictive performance, with RF yielding the most consistent estimates of microbial contamination and HGB showing comparable accuracy but higher predictive uncertainty. The models were optimized using cross-validation and Optuna, with mean squared error as the loss function. Feature importance analysis using SHAP values revealed that Enterococcus concentrations were the most influential predictor, followed by water temperature and salinity. Seasonal patterns in coliform levels were also identified, likely linked to fluctuations in water temperature. These findings provide actionable insights into the dynamics of microbial contamination and highlight the potential of ML models for early warning systems, adaptive monitoring, and improved risk communication. This integrative approach not only enhances predictive performance but also advances our understanding of the environmental processes influencing water quality in urban coastal systems. Full article

Sediment accumulation in irrigation channels poses a significant challenge to water resource management, impacting hydraulic efficiency and agricultural sustainability. This study introduces an innovative multidisciplinary framework that integrates advanced image analysis (FIJI/ImageJ 1.54p), statistical validation (RStudio), and vector field modeling with a novel Sinusoidal Morphodynamic Bedload Transport Equation (SMBTE) to predict sediment deposition patterns with high precision. Conducted along the Malacatos River in La Tebaida Linear Park, Loja, Ecuador, the research captured a natural sediment transport event under controlled flow conditions, transitioning from pressurized pipe flow to free-surface flow. Observed sediment deposition reduced the hydraulic cross-section by approximately 5 cm, notably altering flow dynamics and water distribution. The final SMBTE model (Model 8) demonstrated exceptional predictive accuracy, achieving RMSE: 0.0108, R²: 0.8689, NSE: 0.8689, MAE: 0.0093, and a correlation coefficient exceeding 0.93. Complementary analyses, including heatmaps, histograms, and vector fields, revealed spatial heterogeneity, local gradients, and oscillatory trends in sediment distribution. These tools identified high-concentration sediment zones and quantified variability, providing actionable insights for optimizing canal design, maintenance schedules, and sediment control strategies. By leveraging open-source software and real-world validation, this methodology offers a scalable, replicable framework applicable to diverse water conveyance systems. The study advances understanding of sediment dynamics under subcritical (Fr ≈ 0.07) and turbulent flow conditions (Re ≈ 41,000), contributing to improved irrigation efficiency, system resilience, and sustainable water management. This research establishes a robust foundation for future advancements in sediment transport modeling and hydrological engineering, addressing critical challenges in agricultural water systems. Full article

Amid the accelerating pace of global urbanization, the volume of municipal solid garbage has surged dramatically, thereby demanding more efficient and precise garbage management technologies. In this paper, we introduce a novel garbage classification approach that leverages a dynamic graph neural network based on multimodal feature fusion. Specifically, the proposed method employs an enhanced Residual Network Attention Module (RNAM) network to capture deep semantic features and utilizes CIELAB color (LAB) histograms to extract color distribution characteristics, achieving a complementary integration of multimodal information. An adaptive K-nearest neighbor algorithm is utilized to construct the dynamic graph structure, while the incorporation of a multi-head attention layer within the graph neural network facilitates the efficient aggregation of both local and global features. This design significantly enhances the model’s ability to discriminate among various garbage categories. Experimental evaluations reveal that on our self-curated KRHO dataset, all performance metrics approach 1.00, and the overall classification accuracy reaches an impressive 99.33%, surpassing existing mainstream models. Moreover, on the public TrashNet dataset, the proposed method demonstrates equally outstanding classification performance and robustness, achieving an overall accuracy of 99.49%. Additionally, hyperparameter studies indicate that the model attains optimal performance with a learning rate of 2 × 10⁻⁴, a dropout rate of 0.3, an initial neighbor count of 20, and 8 attention heads. Full article

The application of intelligent video monitoring for natural resource protection and management has become increasingly common in recent years. To enhance safety monitoring during the grazing prohibition and rest period of grassland, this paper proposes a multi-object segmentation algorithm based on mid-infrared images for all-weather surveillance. The approach integrates the Image Timing Features–Gaussian Mixture Model (ITF-GMM) and Convolutional-UNet (Con-UNet) to improve the accuracy of target detection. First, a robust background modelling, i.e., the ITF-GMM, is proposed. Unlike the basic Gaussian Mixture Model (GMM), the proposed model dynamically adjusts the learning rate according to the content difference between adjacent frames and optimizes the number of Gaussian distributions through time series histogram analysis of pixels. Second, a segmentation framework based on Con-UNet is developed to improve the feature extraction ability of UNet. In this model, the maximum pooling layer is replaced with a convolutional layer, addressing the challenge of limited training data and improving the network’s ability to preserve spatial features. Finally, an integrated computation strategy is designed to combine the outputs of ITF-GMM and Con-UNet at the pixel level, and morphological operations are performed to refine the segmentation results and suppress noises, ensuring clearer object boundaries. The experimental results show the effectiveness of proposed approach, achieving a precision of 96.92%, an accuracy of 99.87%, an intersection over union (IOU) of 94.81%, and a recall of 97.75%. Furthermore, the proposed algorithm meets real-time processing requirements, confirming its capability to enhance small-target detection in complex outdoor environments and supporting the automation of grassland monitoring and enforcement. Full article

Floods caused by extreme weather events critically impact human and natural systems. Remote sensing can be a very useful tool in mapping these impacts. However, processing and analyzing satellite imagery covering extensive periods is computationally intensive and time-consuming, especially when data from different sensors need to be integrated, hampering its operational use. To address this issue, the present study focuses on mapping flooded areas and analyzing the impacts of the 2023 Storm Daniel flood in the Thessaly region (Greece), utilizing Earth Observation and GIS methods. The study uses multiple Sentinel-1, Sentinel-2, and Landsat 8/9 satellite images based on backscatter histogram statistics thresholding for SAR and Modified Normalized Difference Water Index (MNDWI) for multispectral images to delineate the extent of flooded areas triggered by the 2023 Storm Daniel in Thessaly region (Greece). Cloud computing on the Google Earth Engine (GEE) platform is utilized to process satellite image acquisitions and track floodwater evolution dynamics until the complete drainage of the area, making the process significantly faster. The study examines the usability and transferability of the approach to evaluate flood impact through land cover, linear infrastructure, buildings, and population-related geospatial datasets. The results highlight the vital role of the proposed approach of integrating remote sensing and geospatial analysis for effective emergency response, disaster management, and recovery planning. Full article

In agricultural production, lettuce growth, yield, and quality are impacted by nutrient deficiencies caused by both environmental and human factors. Traditional nutrient detection methods face challenges such as long processing times, potential sample damage, and low automation, limiting their effectiveness in diagnosing and managing crop nutrition. To address these issues, this study developed a lettuce nutrient deficiency detection system using multi-dimensional image analysis and Field-Programmable Gate Arrays (FPGA). The system first applied a dynamic window histogram median filtering algorithm to denoise captured lettuce images. An adaptive algorithm integrating global and local contrast enhancement was then used to improve image detail and contrast. Additionally, a multi-dimensional image analysis algorithm combining threshold segmentation, improved Canny edge detection, and gradient-guided adaptive threshold segmentation enabled precise segmentation of healthy and nutrient-deficient tissues. The system quantitatively assessed nutrient deficiency by analyzing the proportion of nutrient-deficient tissue in the images. Experimental results showed that the system achieved an average precision of 0.944, a recall rate of 0.943, and an F1 score of 0.943 across different lettuce growth stages, demonstrating significant improvements in automation, accuracy, and detection efficiency while minimizing sample interference. This provides a reliable method for the rapid diagnosis of nutrient deficiencies in lettuce. Full article

The precise identification of wheat seedlings in unmanned aerial vehicle (UAV) imagery is fundamental for implementing precision agricultural practices such as targeted pesticide application and irrigation management. This detection task presents significant technical challenges due to two inherent complexities: (1) environmental interference from variable illumination conditions and (2) morphological characteristics of wheat seedlings characterized by slender leaf structures and flexible posture variations. To address these challenges, we propose DHS-YOLO, a novel deep learning framework optimized for robust wheat seedling detection under diverse illumination intensities. Our methodology builds upon the YOLOv11 architecture with three principal enhancements: First, the Dynamic Slender Convolution (DSC) module employs deformable convolutions to adaptively capture the elongated morphological features of wheat leaves. Second, the Histogram Transformer (HT) module integrates a dynamic-range spatial attention mechanism to mitigate illumination-induced image degradation. Third, we implement the ShapeIoU loss function that prioritizes geometric consistency between predicted and ground truth bounding boxes, particularly optimizing for slender plant structures. The experimental validation was conducted using a custom UAV-captured dataset containing wheat seedling images under varying illumination conditions. Compared to the existing models, the proposed model achieved the best performance with precision, recall, mAP50, and mAP50-95 values of 94.1%, 91.0%, 95.2%, and 81.9%, respectively. These results demonstrate our model’s effectiveness in overcoming illumination variations while maintaining high sensitivity to fine plant structures. This research contributes an optimized computer vision solution for precision agriculture applications, particularly enabling automated field management systems through reliable crop detection in challenging environmental conditions. Full article

This study employs both simulation and experimental methodologies to evaluate the effectiveness of bi-sectional horizontal kinetic shading systems (KSS) with horizontal fins in enhancing daylight comfort across various climates. It emphasizes the importance of optimizing daylight levels while minimizing solar heat gain, particularly in the context of increasing energy demands and shifting climatic patterns. The study introduces a custom-designed bi-sectional KSS, simulated in three distinct climates—Wroclaw, Tehran, and Bangkok—using climate-based daylight modeling methods with the Ladybug and Honeybee tools in Rhino v.7 software. Standard daylight metrics, such as Useful Daylight Illuminance (UDI) and Daylight Glare Probability (DGP), were employed alongside custom metrics tailored to capture the unique dynamics of the bi-sectional KSS. The results were statistically analyzed using box plots and histograms, revealing UDI_300–3000 medians of 78.51%, 88.96%, and 86.22% for Wroclaw, Tehran, and Bangkok, respectively. These findings demonstrate the KSS’s effectiveness in providing optimal daylight conditions across diverse climatic regions. Annual simulations based on standardized weather data showed that the KSS improved visual comfort by 61.04%, 148.60%, and 88.55%, respectively, compared to a scenario without any shading, and by 31.96%, 54.69%, and 37.05%, respectively, compared to a scenario with open static horizontal fins. The inclusion of KSS switching schedules, often overlooked in similar research, enhances the reproducibility and clarity of the findings. A physical reduced-scale mock-up of the bi-sectional KSS was then tested under real-weather conditions in Wroclaw (latitude 51° N) during June–July 2024. The mock-up consisted of two Chambers ‘1’ and ‘2’ equipped with the bi-sectional KSS prototype, and the other one without shading. Stepper motors managed the fins’ operation via a Python script on a Raspberry Pi 3 minicomputer. The control Chamber ‘1’ provided a baseline for comparing the KSS’s efficiency. Experimental results supported the simulations, demonstrating the KSS’s robustness in reducing high illuminance levels, with illuminance below 3000 lx maintained for 68% of the time during the experiment (conducted from 1 to 4 PM on three analysis days). While UDI and DA calculations were not feasible due to the limited number of sensors, the E_h1 values enabled the evaluation of the time illuminance to remain below the threshold. However, during the June–July 2024 heat waves, illuminance levels briefly exceeded the comfort threshold, reaching 4674 lx. Quantitative and qualitative analyses advocate for the broader application and further development of KSS as a climate-responsive shading system in various architectural contexts. Full article

This paper presents an analysis of NO₂ emissions in Mashhad City utilizing statistical evaluations and the Cisco Network Model. The present study begins by evaluating NO₂ emissions through statistical analysis, followed by the application of histograms and radar statistical appraisals. Subsequently, a model execution logic is developed using the Cisco Network Model to further understand the distribution and sources of NO₂ emissions in the city. Additionally, the research incorporates managerial insights by employing Petri Net modeling, which enables a deeper understanding of the dynamic interactions within the air quality management system. This approach aids in identifying critical control points and optimizing response strategies, thus enhancing the overall effectiveness of urban air pollution mitigation efforts. The findings of this study provide valuable insights into the levels of NO₂ pollution in Mashhad City and offer a structured approach to modeling NO₂ emissions for effective air quality management strategies which can be extended to the other megacities as well. Full article

JPEG Reversible Data Hiding (RDH) is a method designed to extract hidden data from a marked image and perfectly restore the image to its original JPEG form. However, while existing RDH methods adaptively manage the visual distortion caused by embedded data, they often neglect the concurrent increase in file size. In rectifying this oversight, we have designed a new JPEG RDH scheme that addresses all influential metrics during the embedding phase and a dynamic frequency selection strategy with recoverable frequency order after data embedding. The process initiates with a pre-processing phase of blocks and the subsequent selection of frequencies. Utilizing a two-dimensional (2D) mapping strategy, we then compute the visual distortion and file size increment (FSI) for each image block by examining non-zero alternating current (AC) coefficient pairs (NZACPs) and their corresponding run lengths. Finally, we select appropriate block groups based on the influential metrics of each block group and proceed with data embedding by 2D histogram shifting (HS). Extensive experimentation demonstrates how our method’s efficiently and consistently outperformed existing techniques with a superior peak signal-to-noise Ratio (PSNR) and optimized FSI. Full article

Investigating the spatial distributions and associations of tree populations provides better insights into the dynamics and processes that shape the forest community. Korean pine (Pinus koraiensis) is one of the most important tree species in broad-leaved Korean pine mixed forests (BKMFs), and little is known about the spatial point patterns of and associations between Korean pine and community-level woody species groups such as coniferous and deciduous trees in different developmental stages. This study investigated the spatial patterns of Korean pine (KP) trees and then analyzed how the spatial associations between KP trees and other tree species at the community level vary in different BKMFs. Extensive data collected from five relatively large sample plots, covering a substantial area within the natural distribution range of KP in northeastern China, were utilized. Uni- and bivariate pair correlation functions and mark correlation functions were applied to analyze spatial distribution patterns and spatial associations. The DBH (diameter at breast height) histogram of KP trees in northeastern China revealed that the regeneration process was very poor in the Changbai Mountain (CBS) plot, while the other four plots exhibited moderate or expanding population structures. KP trees were significantly aggregated at scales up to 10 m under the HPP null model, and the aggregation scales decreased with the increase in size classes. Positive or negative spatial associations were observed among different life stages of KP trees in different plots. The life history stages of the coniferous tree group showed positive spatial associations with KP saplings and juvenile trees at small scales, and spatial independence or negative correlations with larger KP trees at greater scales. All broad-leaved tree groups (canopy, middle, and understory layers) exhibited only slightly positive associations with KP trees at small scales, and dominant negative associations were observed at most scales. Our results demonstrate that mature KP trees have strong importance in the spatial patterns of KP populations, and site heterogeneity, limited seed dispersal, and interspecific competition characterize the spatial patterns of KP trees and community-level spatial associations with respect to KP trees, which can serve as a theoretical basis for the management and restoration of BKMFs in northeastern China. Full article