Search Results (565)

This study introduces an enhanced Intrusion Detection System (IDS) framework for Denial-of-Service (DoS) attacks, utilizing network traffic inter-arrival time (IAT) analysis. By examining the timing between packets and other statistical features, we detected patterns of malicious activity, allowing early and effective DoS threat mitigation. We generate real DoS traffic, including normal, Internet Control Message Protocol (ICMP), Smurf attack, and Transmission Control Protocol (TCP) classes, and develop nine predictive algorithms, combining traditional machine learning and advanced deep learning techniques with optimization methods, including the synthetic minority sampling technique (SMOTE) and grid search (GS). Our findings reveal that while traditional machine learning achieved moderate accuracy, it struggled with imbalanced datasets. In contrast, Deep Neural Network (DNN) models showed significant improvements with optimization, with DNN combined with GS (DNN-GS) reaching 89% accuracy. However, we also used Recurrent Neural Networks (RNNs) combined with SMOTE and GS (RNN-SMOTE-GS), which emerged as the best-performing with a precision of 97%, demonstrating the effectiveness of combining SMOTE and GS and highlighting the critical role of advanced optimization techniques in enhancing the detection capabilities of IDS models for the accurate classification of various types of network traffic and attacks. Full article

In the global energy sector, water-bearing reservoir-typed gas storage accounts for about 30% of underground gas storage (UGS) reservoirs and is vital for natural gas storage, balancing gas consumption, and ensuring energy supply stability. However, when constructing the UGS in the M gas reservoir, selecting suitable areas poses a challenge due to the complicated gas–water distribution in the multi-layered water-bearing gas reservoir with a long production history. To address this issue and enhance energy storage efficiency, this study presents an integrated geomechanical-hydraulic assessment framework for choosing optimal UGS construction horizons in multi-layered water-bearing gas reservoirs. The horizons and sub-layers of the gas reservoir have been quantitatively assessed to filter out the favorable areas, considering both aspects of geological characteristics and production dynamics. Geologically, caprock-sealing capacity was assessed via rock properties, Shale Gouge Ratio (SGR), and transect breakthrough pressure. Dynamically, water invasion characteristics and the water–gas distribution pattern were analyzed. Based on both geological and dynamic assessment results, the favorable layers for UGS construction were selected. Then, a compositional numerical model was established to digitally simulate and validate the feasibility of constructing and operating the M UGS in the target layers. The results indicated the following: (1) The selected area has an SGR greater than 50%, and the caprock has a continuous lateral distribution with a thickness range from 53 to 78 m and a permeability of less than 0.05 mD. Within the operational pressure ranging from 8 MPa to 12.8 MPa, the mechanical properties of the caprock shale had no obvious changes after 1000 fatigue cycles, which demonstrated the good sealing capacity of the caprock. (2) The main water-producing formations were identified, and the sub-layers with inactive edge water and low levels of water intrusion were selected. After the comprehensive analysis, the I-2 and I-6 sub-layer in the M 8 block and M 14 block were selected as the target layers. The numerical simulation results indicated an effective working gas volume of 263 million cubic meters, demonstrating the significant potential of these layers for UGS construction and their positive impact on energy storage capacity and supply stability. Full article

Traditional intrusion detection systems (IDS) based on packet signatures are widely used in network security but often fail to detect previously unseen attacks. To overcome this limitation, machine learning-based methods have been explored to identify anomalous patterns in network traffic indicative of unknown intrusions. In this study, we propose an IDS model based on the Long Short-Term Memory Autoencoder (LSTM-AE), specifically a Convolutional Neural Network Bidirectional LSTM Autoencoder (CNN-BiLSTM-AE). The model integrates convolutional layers for spatial feature extraction and bidirectional LSTM layers to capture temporal dependencies in both directions. By leveraging CNNs to extract key spatial features and BiLSTM to model sequential patterns, the proposed architecture enables effective differentiation between normal and malicious traffic. Anomalies are detected by computing reconstruction loss during inference and applying a predefined threshold to classify traffic. The experimental results demonstrate that the CNN-BiLSTM-AE model achieves high detection performance, with an accuracy of 98.1% and an F1-score of 98.3%, highlighting its effectiveness in identifying previously unknown intrusions. Full article

The South Shetland Islands and Antarctic Peninsula (SHETPENANT region) constitute a geodynamically active area shaped by the interaction of major tectonic plates and active magmatic systems. This study analyzes GNSS time series spanning from 2017 to 2024 to investigate surface deformation associated with the 2020–2021 seismic swarm near the Orca submarine volcano. Horizontal and vertical displacement velocities were estimated for the preseismic, coseismic, and postseismic phases using the CATS method. Results reveal significant coseismic displacements exceeding 20 mm in the horizontal components near Orca, associated with rapid magmatic pressure release and dike intrusion. Postseismic velocities indicate continued, though slower, deformation attributed to crustal relaxation. Stations located near the Orca exhibit nonlinear, transient behavior, whereas more distant stations display stable, linear trends, highlighting the spatial heterogeneity of crustal deformation. Stress and strain fields derived from the velocity models identify zones of extensional dilatation in the central Bransfield Basin and localized compression near magmatic intrusions. Maximum strain rates during the coseismic phase exceeded 200 $\mathrm{\nu }$strain/year, supporting a scenario of crustal thinning and fault reactivation. These patterns align with the known structural framework of the region. The integration of GNSS-based displacement and strain modeling proves essential for resolving active volcano-tectonic interactions. The findings enhance our understanding of back-arc deformation processes in polar regions and support the development of more effective geohazard monitoring strategies. Full article

Modern network infrastructures have significantly improved global connectivity while simultaneously escalating network security challenges as sophisticated cyberattacks increasingly target vital systems. Intrusion Detection Systems (IDSs) play a crucial role in identifying and mitigating these threats, and recent advances in machine-learning-based IDSs have shown promise in detecting evolving attack patterns. Notably, IDSs employing Graph Neural Networks (GNNs) have proven effective at modeling the dynamics of network traffic and internal interactions. However, these systems suffer from Catastrophic Forgetting (CF), where the incorporation of new attack patterns leads to the loss of previously acquired knowledge. This limits their adaptability and effectiveness in evolving network environments. In this study, we introduce the Elastic Graph Neural Network for Intrusion Detection Systems (EL-GNNs), a novel approach designed to enhance the continual learning (CL) capabilities of GNN-based IDSs. This approach enhances the performance of the GNN-based Intrusion Detection System (IDS) by significantly improving its capability to preserve previously learned knowledge from past cyber threats while simultaneously enabling it to effectively adapt and respond to newly emerging attack patterns in dynamic and evolving network environments. Experimental evaluations on trusted datasets across multiple task scenarios demonstrate that our method outperforms existing approaches in terms of accuracy and F1-score, effectively addressing CF and enhancing adaptability in detecting new network attacks. Full article

The coastal zone presents complex hydrodynamic interactions among inland groundwater, reservoir water, and intruding seawater, with important implications for ecosystem functioning and water quality. However, the relative roles of hydraulic connectivity and seawater-driven salinity gradients in shaping microbial communities at the aquifer–reservoir interface remain unclear. Here, we integrated hydrochemical analyses with high-throughput 16S rRNA gene sequencing to investigate bacterial community composition, assembly processes, and co-occurrence network patterns across groundwater_in (entering the reservoir), groundwater_out (exiting the reservoir), and reservoir water in a coastal system. Our findings reveal that seawater intrusion exerts a stronger influence on groundwater_out, leading to distinct chemical profiles and salinity-driven environmental filtering, whereas hydraulic connectivity promotes greater microbial similarity between groundwater_in and reservoir water. Groundwater samples exhibited higher alpha and beta diversity compared to the reservoir, with dominant taxa such as Comamonadaceae, Flavobacteriaceae, and Rhodobacteraceae serving as indicators of seawater intrusion. Community assembly analyses showed that homogeneous selection predominated, especially under strong salinity gradients, while dispersal limitation and spatial distance also contributed in areas of reduced connectivity. Key chemical factors, including TDS, Na⁺, Cl⁻, Mg²⁺, and K⁺, strongly shaped groundwater communities. Additionally, groundwater bacterial networks were more complex and robust than those in reservoir water, suggesting enhanced resilience to salinity stress. Collectively, this study demonstrates that salinity gradients can override the effects of hydraulic connectivity in structuring bacterial communities and their networks at coastal interfaces. Our findings provide novel microbial insights relevant for understanding biogeochemical processes and support the use of microbial indicators for more sensitive monitoring and management of coastal groundwater resources. Full article

Non-active current in the time domain is considered for application to the diagnostics and classification of loads in power grids based on waveform-distortion characteristics, taking as a working example several recordings of the pantograph current in an AC railway system. Data are processed with a deep autoencoder for feature extraction and then clustered via k-means to allow identification of patterns in the latent space. Clustering enables the evaluation of the relationship between the physical meaning and operation of the system and the distortion phenomena emerging in the waveforms during operation. Euclidean distance (ED) is used to measure the diversity and pertinence of observations within pattern groups and to identify anomalies (abnormal distortion, transients, …). This approach allows the classification of new data by assigning data to clusters based on proximity to centroids. This unsupervised method exploiting non-active current is novel and has proven useful for providing data with labels for later supervised learning performed with the 1D-CNN, which achieved a balanced accuracy of 96.46% under normal conditions. ED and 1D-CNN methods were tested on an additional unlabeled dataset and achieved 89.56% agreement in identifying normal states. Additionally, Grad-CAM, when applied to the 1D-CNN, quantitatively identifies the waveform parts that influence the model predictions, significantly enhancing the interpretability of the classification results. This is particularly useful for obtaining a better understanding of load operation, including anomalies that affect grid stability and energy efficiency. Finally, the method has been also successfully further validated for general applicability with data from a different scenario (charging of electric vehicles). The method can be applied to load identification and classification for non-intrusive load monitoring, with the aim of implementing automatic and unsupervised assessment of load behavior, including transient detection, power-quality issues and improvement in energy efficiency. Full article

Wireless Sensor Networks (WSNs) consist of distributed sensor nodes that collect and transmit environmental data, often in resource-constrained and unsecured environments. These characteristics make WSNs highly vulnerable to various security threats. To address this, the objective of this research is to design and evaluate a deep learning-based Intrusion Detection System (IDS) that is both accurate and efficient for real-time threat detection in WSNs. This study proposes a hybrid IDS model combining one-dimensional Convolutional Neural Networks (Conv1Ds), Gated Recurrent Units (GRUs), and Self-Attention mechanisms. A Conv1D extracts spatial features from network traffic, GRU captures temporal dependencies, and Self-Attention emphasizes critical sequence components, collectively enhancing detection of subtle and complex intrusion patterns. The model was evaluated using the WSN-DS dataset and demonstrated superior performance compared to traditional machine learning and simpler deep learning models. It achieved an accuracy of 98.6%, precision of 98.63%, recall of 98.6%, F1-score of 98.6%, and an ROC-AUC of 0.9994, indicating strong predictive capability even with imbalanced data. In addition to centralized training, the model was tested under cooperative, node-based learning conditions, where each node independently detects anomalies and contributes to a collective decision-making framework. This distributed approach improves detection efficiency and robustness. The proposed IDS offers a scalable and resilient solution tailored to the unique challenges of WSN security. Full article

The El Bola mafic–ultramafic intrusion (EBMU) in Egypt’s Northern Eastern Desert represents an example of Neoproterozoic post-collisional layered mafic–ultramafic magmatism in the Arabian–Nubian Shield (ANS). The intrusion is composed of pyroxenite, olivine gabbro, pyroxene gabbro, pyroxene–hornblende gabbro, and hornblende-gabbro, exhibiting adcumulate to heter-adcumulate textures. Mineralogical and geochemical analyses reveal a coherent trend of fractional crystallization. Compositions of whole rock and minerals indicate a parental magma of ferropicritic affinity, derived from partial melting of a hydrous, metasomatized spinel-bearing mantle source, likely modified by subduction-related fluids. Geothermobarometric calculations yield crystallization temperatures from ~1120 °C to ~800 °C and pressures from ~5.2 to ~3.1 kbar, while oxygen fugacity estimates suggest progressive oxidation (log fO₂ from −17.3 to −15.7) during differentiation. The EBMU displays Light Rare Earth element (LREE) enrichment, trace element patterns marked by Large Ion Lithophile Element (LILE) enrichment, Nb-Ta depletion and high LILE/HFSE (High Field Strength Elements) ratios, suggesting a mantle-derived source that remained largely unaffected by crustal contribution and was metasomatized by slab-derived fluids. Tectonic discrimination modeling suggests that EBMU magmatism was triggered by asthenospheric upwelling and slab break-off. Considering these findings alongside regional geologic features, we propose that the mafic–ultramafic intrusion from the ANS originated in a tectonic transition between subduction and collision (slab break-off) following the assembly of Gondwana. Full article

A vital step for any hydrochemical assessment is properly carrying out quality assurance and quality control (QA/QC) techniques to evaluate data confidence before performing the assessment. Understanding the processes governing groundwater evolution in coastal aquifers is critical for managing freshwater resources under increasing anthropogenic and climatic pressures. This study reassesses the hydrochemical and isotopic data from the Deep Confined Aquifer System (DCAS) in the Jiangsu Coastal Plain, China, by firstly applying QA/QC protocols. Anomalously high Fe and Mn concentrations in several samples were identified and excluded, yielding a refined dataset that enabled a more accurate interpretation of hydrogeochemical processes. Using hierarchical cluster analysis (HCA), principal component analysis (PCA), and stable and radioactive isotope data (δ²H, δ¹⁸O, ³H, and ¹⁴C), we identify three dominant drivers of groundwater evolution: water–rock interaction, evaporation, and seawater intrusion. In contrast to earlier interpretations, we present clear evidence of active seawater intrusion into the DCAS, supported by salinity patterns, isotopic signatures, and local hydrodynamics. Furthermore, inconsistencies between tritium- and radiocarbon-derived residence times—modern recharge indicated by ³H versus Pleistocene ages from ¹⁴C—highlight the unreliability of previous paleoclimatic reconstructions based on unvalidated datasets. These findings underscore the crucial role of robust QA/QC and integrated tracer analysis in groundwater studies. Full article

Leveraging Data Processing Units (DPUs) deployed at network interfaces, the DPU-accelerated Intrusion Detection System (IDS) enables microsecond-latency initial traffic inspection through hardware offloading. However, while generating high-throughput alerts, this mechanism amplifies the inherent redundancy and noise issues of traditional IDS systems. This paper proposes an alert correlation method using multi-similarity factor aggregation and a suffix tree model. First, alerts are preprocessed using LFDIA, employing multiple similarity factors and dynamic thresholding to cluster correlated alerts and reduce redundancy. Next, an attack intensity time series is generated and smoothed with a Kalman filter to eliminate noise and reveal attack trends. Finally, the suffix tree models attack activities, capturing key behavioral paths of high-severity alerts and identifying attacker patterns. Experimental evaluations on the CPTC-2017 and CPTC-2018 datasets validate the proposed method’s effectiveness in reducing alert redundancy, extracting critical attack behaviors, and constructing attack activity sequences. The results demonstrate that the method not only significantly reduces the number of alerts but also accurately reveals core attack characteristics, enhancing the effectiveness of network security defense strategies. Full article

The rapid expansion of Edge and Industrial Internet of Things (IIoT) systems has intensified the risk and complexity of cyberattacks. Detecting advanced intrusions in these heterogeneous and high-dimensional environments remains challenging. As the IIoT becomes integral to critical infrastructure, ensuring security is crucial to prevent disruptions and data breaches. Traditional IDS approaches often fall short against evolving threats, highlighting the need for intelligent and adaptive solutions. While deep learning (DL) offers strong capabilities for pattern recognition, single-model architectures often lack robustness. Thus, hybrid and optimized DL models are increasingly necessary to improve detection performance and address data imbalance and noise. In this study, we propose an optimized hybrid DL framework that combines a transformer, generative adversarial network (GAN), and autoencoder (AE) components, referred to as Transformer–GAN–AE, for robust intrusion detection in Edge and IIoT environments. To enhance the training and convergence of the GAN component, we integrate an improved chimp optimization algorithm (IChOA) for hyperparameter tuning and feature refinement. The proposed method is evaluated using three recent and comprehensive benchmark datasets, WUSTL-IIoT-2021, EdgeIIoTset, and TON_IoT, widely recognized as standard testbeds for IIoT intrusion detection research. Extensive experiments are conducted to assess the model’s performance compared to several state-of-the-art techniques, including standard GAN, convolutional neural network (CNN), deep belief network (DBN), time-series transformer (TST), bidirectional encoder representations from transformers (BERT), and extreme gradient boosting (XGBoost). Evaluation metrics include accuracy, recall, AUC, and run time. Results demonstrate that the proposed Transformer–GAN–AE framework outperforms all baseline methods, achieving a best accuracy of 98.92%, along with superior recall and AUC values. The integration of IChOA enhances GAN stability and accelerates training by optimizing hyperparameters. Together with the transformer for temporal feature extraction and the AE for denoising, the hybrid architecture effectively addresses complex, imbalanced intrusion data. The proposed optimized Transformer–GAN–AE model demonstrates high accuracy and robustness, offering a scalable solution for real-world Edge and IIoT intrusion detection. Full article

Morocco’s Témara Plain relies heavily on its aquifer system as a critical resource for drinking water, irrigation, and industrial activities. However, this essential groundwater reserve is increasingly threatened by over-extraction, seawater intrusion, and complex hydrogeochemical processes driven by the region’s geological characteristics and anthropogenic pressures. This study aims to assess groundwater quality and its vulnerability to pollution risks and map the spatial distribution of key hydrochemical processes through an integrated approach combining Geographic Information System (GIS) techniques and multivariate statistical analysis, as well as applying the DRASTIC model to evaluate water vulnerability. A total of fifty-eight groundwater samples were collected across the plain and analyzed for major ions to identify dominant hydrochemical facies. Spatial interpolation using Inverse Distance Weighting (IDW) within GIS revealed distinct patterns of sodium chloride (Na-Cl) facies near the coastal areas with chloride concentrations exceeding the World Health Organization (WHO) drinking water guideline of 250 mg/L—indicative of seawater intrusion. In addition to marine intrusion, agricultural pollution constitutes a major diffuse pressure across the aquifer. Shallow groundwater zones in agricultural areas show heightened vulnerability to salinization and nitrate contamination, with nitrate concentrations reaching up to 152.3 mg/L, far surpassing the WHO limit of 45 mg/L. Furthermore, other anthropogenic pollution sources—such as wastewater discharges from septic tanks in peri-urban zones lacking proper sanitation infrastructure and potential leachate infiltration from informal waste disposal sites—intensify stress on the aquifer. Principal Component Analysis (PCA) identified three key factors influencing groundwater quality: natural mineralization due to carbonate rock dissolution, agricultural inputs, and salinization driven by seawater intrusion. Additionally, The DRASTIC model was used within the GIS environment to create a vulnerability map based on seven key parameters. The map revealed that low-lying coastal areas are most vulnerable to contamination. Full article

Copper is typically acknowledged as a critical mineral and one of the vital components of various of today’s fast-growing green technologies. Porphyry copper systems, which are an important source of copper and molybdenum, typically consist of large volumes of hydrothermally altered rocks, mainly around porphyry copper intrusions. Mapping hydrothermal alteration zones associated with porphyry copper systems is one of the most important indicators for copper exploration, especially using advanced satellite remote sensing technology. This paper presents a sophisticated remote sensing-based method that uses ASTER satellite imagery (SWIR bands 4 to 9) to identify hydrothermal alteration zones by combining the discrete wavelet transform (DWT) and the median absolute deviation (MAD) algorithms. All six SWIR bands (bands 4–9) were analyzed independently, and band 9, which showed the most consistent spatial patterns and highest validation accuracy, was selected for final visualization and interpretation. The MAD algorithm is effective in identifying spectral anomalies, and the DWT enables the extraction of features at different scales. The Urmia–Dokhtar magmatic arc in central Iran, which hosts the Zafarghand porphyry copper deposit, was selected as a case study. It is a hydrothermal porphyry copper system with complex alteration patterns that make it a challenging target for copper exploration. After applying atmospheric corrections and normalizing the data, a hybrid algorithm was implemented to classify the alteration zones. The developed classification framework achieved an accuracy of 94.96% for phyllic alteration and 89.65% for propylitic alteration. The combination of MAD and DWT reduced the number of false positives while maintaining high sensitivity. This study demonstrates the high potential of the proposed method as an accurate and generalizable tool for copper exploration, especially in complex and inaccessible geological areas. The proposed framework is also transferable to other porphyry systems worldwide. Full article

The demand for maritime–coastal tourism has been intensifying, but its offerings are sometimes limited to a few activities. Some of these activities do not require specific skills or certifications, while others do. This study aimed to investigate what type of activities are carried out by tourism and recreational vessels in the coastal area of the central Algarve (Portugal). To this end, data from the automatic identification system (AIS) of recreational vessels was used to monitor and categorise these activities in a non-intrusive manner. A model (TORMA) was defined to facilitate the analysis of AIS data and relate them to five independent variables (distance from the coast, boat speed, bathymetry, seabed type, and number of pings). The results of the analysis of more than 11 thousand hourly AIS records for passenger, sailing, and charter vessels showed that the 14 most regular ones had strong seasonal patterns, greater intensity in summer, and spatial patterns with more records near some coastal cliffs. This study provides valuable information on the management of motorised nautical activities near the coast and at sea, contributing to more informed and effective tourism regulation and planning. Full article