Search Results (825)

Distributed acoustic sensing (DAS), which can provide dense spatial and temporal measurements using optical fibers, is quickly becoming critical for large-scale infrastructure monitoring. However, anomaly detection in DAS data is still challenging owing to the spatial correlations between sensing channels and nonlinear temporal dynamics. Recent approaches often disregard the explicit sensor layout and instead handle DAS data as two-dimensional images or flattened sequences, eliminating the spatial topology. This work proposes GraphDiffusion, a novel generative anomaly-detection model that combines a conditional denoising diffusion probabilistic model (DDPM) and a graph neural network (GNN) to overcome these limitations. By treating each channel as a graph node and building edges based on Euclidean proximity, the GNN explicitly models the spatial arrangement of DAS sensors, allowing the network to capture local interchannel dependencies. The conditional DDPM uses iterative denoising to model the temporal dynamics of standard signals, enabling the system to detect deviations without the need for anomalies. The performance evaluations based on real-world DAS datasets reveal that GraphDiffusion achieves 98.2% and 98.0% based on the area under the curve (AUC) of the F1-score at K different levels (F1_K-AUC), an AUC of receiver operating characteristic (ROC) at K different levels (ROC_K-AUC), outperforming other comparative models. Full article

Accurate estimation of tree diameter at breast height (DBH) from LiDAR point clouds is essential for forest inventory, biomass assessment, and ecological monitoring. This paper presents a perimeter-based DBH estimation framework that achieves competitive accuracy against geometric fitting methods across three datasets. The proposed approach partitions the trunk cross-section into angular sectors and employs Gaussian Mixture Models (GMMs) to identify representative boundary points in each sector, weighted by radial proximity and statistical confidence. To handle occlusion and partial scans, missing sectors are reconstructed using symmetry-aware proxy generation. The final perimeter is modeled via either convex hull or B-spline interpolation, from which DBH is derived. Extensive experiments were conducted on two public TreeScope datasets and a custom mobile LiDAR dataset. Compared to the Density-Based Clustering Ring Extraction (DBCRE) baseline, our method reduced RMSE by 22.7% on UCM-0523M (from 2.60 to 2.01 cm), 34.3% on VAT-0723M (from 3.50 to 2.30 cm), and 29.6% on the Custom Dataset (from 2.16 to 1.52 cm). Ablation studies confirmed the individual and synergistic contributions of GMM clustering, radial consistency filtering, and proxy synthesis. Overall, the method provides a flexible alternative that reduces dependence on strict geometric assumptions, offering improved DBH estimation performance with moderate occlusion and incomplete, uneven boundary coverage. Full article

In the field of mobile crowdsensing (MCS), a large number of tasks rely on the participation of ordinary mobile device users for data collection and processing. This model has shown great potential for applications in environmental monitoring, traffic management, public safety, and other areas. However, the enthusiasm of participants and the quality of uploaded data directly affect the reliability and practical value of the sensing results. Therefore, the design of incentive mechanisms has become a core issue in driving the healthy operation of MCS. The existing research, when optimizing long-term utility rewards for participants, has often failed to fully consider dynamic changes in trustworthiness. It has typically relied on historical data from a single point in time, overlooking the long-term dependencies in the time series, which results in suboptimal decision-making and limits the overall efficiency and fairness of sensing tasks. To address this issue, a credibility-aware incentive mechanism based on long short-term memory and proximal policy optimization (CIM-LP) is proposed. The mechanism employs a Markov decision process (MDP) model to describe the decision-making process of the participants. Without access to global information, an incentive model combining long short-term memory (LSTM) networks and proximal policy optimization (PPO), collectively referred to as LSTM-PPO, is utilized to formulate the most reasonable and effective sensing duration strategy for each participant, aiming to maximize the utility reward. After task completion, the participants’ credibility is dynamically updated by evaluating the quality of the uploaded data, which then adjusts their utility rewards for the next phase. Simulation results based on real datasets show that compared with several existing incentive algorithms, the CIM-LP mechanism increases the average utility of the participants by 6.56% to 112.76% and the task completion rate by 16.25% to 128.71%, demonstrating its significant advantages in improving data quality and task completion efficiency. Full article

The development of new techniques to improve crop management, especially through precision agriculture methods and innovations, is crucial for increasing crop yield and ensuring high-quality production. The horticultural sector is particularly vulnerable to inefficiencies in crop management due to the complex and costly processes required for producing marketable products. Optimal nutritional inputs and effective disease management are crucial for maintaining commercial standards. This two-year study investigated the physiological differences between organic and conventional crop management of the Sardinian `Spinoso sardo’ artichoke ecotype (Cynara cardunculus var. scolymus L.) by integrating a multiplex force-A (MFA) fluorometer and unmanned aerial systems (UASs) equipped with a multispectral camera capable of analysing the NDVI vegetation index. Using both proximal and remote sensing instruments, physiological and nutritional variations in the growth cycle of artichokes were identified, distinguishing between traditional and two organic management practices. The two-year MFA experiment revealed physiological variability and different trends among the three management practices, indicating that MFA proximal sensing is a valuable tool for detecting physiological differences, particularly in chlorophyll activity and nitrogen content. In contrast, the UAS survey was less effective at distinguishing between management types, likely due to its limited use during the second year and the constrained timeframe of the multitemporal analysis. The analysis of the MFA fluorimetric indices suggested significant differences among the plots monitored due to the ANOVA statistical analysis and Tukey test, showing greater adaptability of the conventional system in managing production inputs, unlike the organic systems, which showed higher variability within the plots and across the survey years, indicating aleatory trends due to differences in crop management. Full article

Pesticides play a significant role in agriculture, but their leaching into soil and water poses serious environmental risks. This study examines pesticide contamination in surface and groundwater in northern Tunisia, specifically in Kef governorate, involving a survey of 140 farmers to gather data on agricultural practices and pesticide use. Twenty-four pesticides were monitored and utilized within the Pesticide Environmental Risk Indicator (PERI) model to evaluate environmental risk scores for each substance. Soil and water samples were analyzed using a multi-residue method and liquid chromatography–tandem mass spectrometry. Results showed that 50% of the pesticides assessed had an Environmental Risk Score of 5 or higher. Contamination was identified in water and soil, with 18 and 15 pesticide residues, respectively. Notable concentrations included 7.8 µg/L of linuron and flupyradifurone in water and 1718.4 µg/kg of linuron in soil. Commonly detected substances included the insecticide acetamiprid and fungicides like cyflufenamid and penconazole in water, while soil contamination was linked to fungicides metalaxyl and metalaxyl-m, as well as herbicides linuron and s-metolachlor. Factors such as proximity to treated water points and poor packaging management were discussed as risks. The findings emphasize the need for better monitoring and sustainable agricultural practices to mitigate contamination. Full article

Ensuring the reliable operation of wind turbines is critical for the global transition to sustainable energy, yet it is challenged by faults that are difficult to detect in real-time. Traditional diagnostics rely on centralized data, which raises significant privacy and scalability concerns. To address these limitations, this study introduces a Consensus-Regularized Federated Learning (CR-FL) framework. This framework mathematically formalizes and mitigates the problem of “client drift” caused by heterogeneous data from different turbines by augmenting the local training objective with a proximal regularization term. This forces models to learn generalizable fault features while preserving data privacy. To validate our framework, we implemented a lightweight neural network within a federated paradigm and benchmarked it against a powerful, centralized Light Gradient Boosting Machine (LightGBM) model using real-world SCADA data. The federated training process, through its inherent constraint on local updates, acts as a practical implementation of our consensus-regularization principle. Model performance was comprehensively evaluated using accuracy, precision, F1-score, and Area Under the ROC Curve (AUC) metrics. The results demonstrate that our federated approach not only preserves privacy but also achieves superior performance in key metrics, including AUC and precision. This confirms that the regularizing effect of the federated process enables the global model to generalize better across heterogeneous data distributions than its centralized counterpart. This study provides a practical, scalable, and methodologically superior solution for fault diagnosis in wind turbine systems, paving the way for more collaborative and secure infrastructure monitoring. Full article

Monitoring optically-active water quality (OAWQ) parameters faces key challenges, primarily due to limited in situ measurements and the restricted availability of high-resolution multispectral remote sensing imagery. While deep learning has shown promise for OAWQ estimation, existing approaches such as GeoTile2Vec, which relies on geographic proximity, and SimCLR, a domain-agnostic contrastive learning method, fail to capture land cover-driven water quality patterns, limiting their generalizability. To address this, we present deep meta-connectivity representation (DMCR), which integrates multispectral remote sensing imagery with limited in situ measurements to estimate OAWQ parameters. Our approach constructs meta-feature vectors from land cover images to represent the water quality characteristics of each multispectral remote sensing image tile. We introduce the meta-connectivity concept to quantify the OAWQ similarity between different tiles. Building on this concept, we design a contrastive self-supervised learning framework that uses sets of quadruple tiles extracted from Sentinel-2 imagery based on their meta-connectivity to learn DMCR vectors. After the core neural network is trained, we apply a random forest model to estimate parameters such as chlorophyll-a (Chl-a) and turbidity using matched in situ measurements and DMCR vectors across time and space. We evaluate DMCR on Lake Erie and Lake Ontario, generating a series of Chl-a and turbidity distribution maps. Performance is assessed using the $R^2$ and $RMSE$ metrics. Results show that meta-connectivity more effectively captures water quality similarities between tiles than widely utilized geographic proximity approaches such as those used in GeoTile2Vec. Furthermore, DMCR outperforms baseline models such as SimCLR with randomly cropped tiles. The resulting distribution maps align well with known factors influencing Chl-a and turbidity levels, confirming the method’s reliability. Overall, DMCR demonstrates strong potential for large-scale OAWQ estimation and contributes to improved monitoring of inland water bodies with limited in situ measurements through meta-connectivity-informed deep learning. The temporal-spatial water quality maps can support large-scale inland water monitoring, early warning of harmful algal blooms. Full article

Drones, particularly those designed for indoor inspections, are widely used across various industries for tasks such as infrastructure monitoring, maintenance, and security. This study focuses on developing a robust collision avoidance system for teleoperated indoor drones, ensuring comprehensive 360-degree horizontal safety during flight. By integrating multiple cost-effective and compact Time-of-Flight (ToF) distance sensors, the system enhances real-time obstacle detection and collision prevention. A custom sensor module, strategically installed on the drone, facilitates continuous environmental monitoring and dynamic flight adjustment. This module continuously provides real-time distance data to the collision avoidance algorithm. Additionally, the system receives user control signals from the remote operator, which are then transmitted to the flight controller. Upon detecting an obstacle, the system immediately modifies these control signals to adjust the drone’s motion, thereby avoiding collisions and ensuring the safety of both the drone and its surroundings. The methodology involves initializing and calibrating multiple sensors, collecting and processing ranging data, and dynamically adjusting motion commands based on proximity alerts. This approach significantly improves the safety and operational efficiency of drones in complex indoor environments. Full article

This study presents a 39-year spatiotemporal analysis of shoreline variability at Topocalma Beach (Chile) using satellite-derived data collected between 1985 and 2024. A total of 350 satellite images were processed with CoastSat and DSAS v6.0 to quantify erosional and accretional trends across distinct beach sectors. The results show persistent erosion in the proximal zone near the Topocalma wetland and localized accretion in the distal (southern) segment. These changes are closely associated with the 2010 Maule earthquake and tsunami, strong ENSO phases, and an increase in storm surge activity since 2015. The spatiotemporal beach width model reveals distinct phases of retreat and short-term post-seismic stabilization, followed by a shift to sustained erosion. Overall, this study underscores the limited natural recovery capacity of the beach and highlights the utility of satellite-based monitoring tools for coastal resilience planning in data-limited regions. Full article

This study investigates Bimi^® (Brassica oleracea Italica × Alboglabra), a hybrid between kailan and conventional broccoli, to evaluate its compositional, functional, and sensory properties in relation to industrial sous-vide processing and refrigerated storage. Proximate composition, amino acid and fatty acid profiles, and mineral content were determined in raw samples. Color, chlorophyll content, total polyphenols, and antioxidant capacity (FRAP, ABTS, DPPH) were analyzed before and after sous-vide treatment and following 60 days of storage. Microbiological and physicochemical stability was monitored over 90 days under standard (4 °C) and mildly abusive (6–10 °C) storage conditions. Sensory profiling of Bimi^® and conventional broccoli was performed on sous-vide samples. The results showed an increase in total polyphenols and antioxidant activity after processing, while chlorophylls decreased. Microbiological safety was maintained under all conditions, with stable water activity and only moderate acidification. Bimi^® provided a valuable source of protein (4.32 g/100 g FW, 8.63% RDA), appreciable amounts of dietary fiber (2.96 g/100 g FW, 11.85% RDA), and essential minerals such as potassium (15.59% RDA), phosphorus (14.05% RDA), and calcium (8.09% RDA). Sensory evaluation revealed a milder flavor profile than that of conventional broccoli, accompanied by an asparagus-like aroma. These findings support the suitability of Bimi^® for industrial sous-vide processing and its potential as a nutritious convenience food. Full article

The drying process plays a crucial role in enhancing the shelf life of food products by reducing moisture content. As climate change contributes to rising temperatures, alternative drying methods, such as solar drying, offer promising solutions for sustainable food preservation. This study investigates the solar drying of eggplant (Solanum melongena L.) slices, with a focus on the effect of salting pretreatment on drying efficiency. Eggplant slices were subjected to salting pretreatment for partial moisture removal prior to drying. Drying kinetics were monitored to construct the characteristic drying curve. The dried eggplant slices were evaluated for their proximate composition and rehydration capacity, as well as textural and thermal properties. The results showed that salting pretreatment significantly enhanced the solar drying process by accelerating moisture removal. Notably, water activity (aw) decreased significantly from 0.978 to 0.554 for the control sample and to 0.534 for the saltedsample. Significant differences were observed between the dried and salted dried slices, particularly in rehydration capacity, which decreased following salting. Additionally, the salted dried samples showedreductions in protein, carbohydrate, and potassium contents. In contrast, ash content and hardness increased as a result ofosmotic pretreatment. These findings suggest that while dry salting pretreatment effectively reduces solar drying time, it may adversely affect several nutritional and textural properties. Full article

The growth of urban and industrial areas is accompanied by an increase in vehicle traffic, resulting in rising concentrations of various air pollutants. This is a global issue that causes environmental damage and risks to human health. The dataset presented in this research contains records with measurements of the air pollutants ozone (O₃) and carbon monoxide (CO), as well as meteorological parameters such as temperature (T), relative humidity (RH), and barometric pressure (BP). This dataset was collected using a set of low-cost sensors over a four-month study period (March to June) in 2024. The monitoring of air pollutants and meteorological parameters was conducted in a city with high industrial activity, heavy traffic, and close proximity to a petrochemical refinery plant. The data were subjected to a series of statistical analyses for visualization using plots that allow for the identification of their behavior. Finally, the dataset can be utilized for air quality studies, public health research, and the development of prediction models based on mathematical approaches or artificial intelligence algorithms. Full article

Urban coral reefs in Jakarta Bay and the Thousand Islands, Indonesia, are chronically exposed to land-based pollution and increasing thermal stress. These reefs—including the site of Indonesia’s first recorded coral bleaching event in 1983—remain highly vulnerable to climate-induced disturbances. During the fourth global coral bleaching event (GCBE), we recorded selective bleaching in the region, associated with a Degree Heating Weeks (DHW) value of 4.8 °C-weeks. Surveys conducted in January 2024 across a shelf gradient at four representative islands revealed patchy bleaching, affecting various taxa at depths ranging from 3 to 13 m. A follow-up survey in May 2024, which tracked the fate of 42 tagged bleached colonies, found that 36% had fully recovered, 26% showed partial recovery, and 38% had died. Bleaching responses varied across taxa, depths, and microhabitats, often occurring in close proximity to unaffected colonies. While some corals demonstrated resilience, the overall findings underscore the continued vulnerability of urban reefs to escalating thermal stress. This highlights the urgent need for a comprehensive and coordinated national strategy—not only to monitor bleaching and assess reef responses, but also to strengthen protection measures and implement best-practice restoration. Such efforts are increasingly critical in the face of more frequent and severe bleaching events projected under future climate scenarios. Full article

Overfishing represents one of the most alarming threats to marine conservation in the Mediterranean Sea. In particular, deep-sea trawl fishing can severely damage marine habitats that may take decades to recover due to their slow growth rates. Hence, monitoring the health and subsistence of deep-sea ecosystems in fishing hotspots is vital to understand the impacts of deep-sea fishing. This paper presents a methodological study to prepare an expedition in Sardinian (Italy) deep waters. The methodology is composed of three sections: first, it offers a comparative analysis of the proper technological mix to identify fishing hotspots pre-expedition; second, it simulates an in situ expedition to monitor the state of deep-sea ecosystems in proximity of the fishing hotspots identified; and third, it offers recommendations for data analysis and management post-expedition. This study offers a replicable methodology for advancing knowledge on the state of deep-sea ecosystems affected by trawl fishing. Full article

This research examines the traffic disruptions resulting from the collapse of the Francis Scott Key Bridge in Baltimore, utilizing advanced econometric methods and real-time ClearGuide data. Employing Fixed Effects (FEs), Mixed Effects (MEs), Difference-in-Differences (DiDs), and stratified regression models, the study uniquely examines the impacts of congestion across Immediate, Fall, and Winter periods, distinctly separating AM and PM peak patterns. Significant findings include severe PM peak congestion, up to four times greater than AM peak congestion, particularly on critical corridors such as the Harbor Tunnel Thruway northbound and MD-295 northbound. Initial route-level impacts were heterogeneous, gradually becoming uniform as the network adapted. The causal DiD analysis provides strong evidence that increased congestion is causally linked to proximity to the collapse. It is anticipated that incorporating the suggested framework will yield insightful information for stakeholders and decision-makers, such as targeted freight restriction, peak-hour dynamic pricing, corridor-specific signal adjustments, and investments in real-time traffic monitoring systems to strengthen transportation network resilience. Full article