Search Results (18)

This work presents the development of an intelligent system designed to support the predictive maintenance of the Colombian Navy’s maritime vessels through the estimation of remaining useful life and unsupervised anomaly detection, within the framework of the project called “Colombian Integrated Platform Supervision and Control System” (SISCP-C). This project seeks to guarantee the sustainability of the vessels over time, increase their operational availability, and optimize their life cycle cost, in accordance with the institution’s strategic direction established in the Naval Development Plan 2042. The system provides useful information to the crew, enabling informed decision-making for intelligent and efficient maintenance strategies. To address the limited availability of normal operating data, synthetic data generation techniques with seeding are implemented, including tabular variational autoencoders, conditional tabular generative adversarial networks, and Gaussian copulas. Among these, tabular variational autoencoders achieved the best performance and are used to generate synthetic datasets under normal conditions for the Wärtsilä 6L26 diesel engine (manufactured by Wärtsilä Italia S.p.A., Trieste, Italy). These datasets are used to train several unsupervised anomaly detection models, including one-class support vector machines, classical autoencoders, and long short-term memory-based autoencoders. The long short-term memory autoencoders outperformed the others in terms of detection metrics. Dedicated multivariate long short-term memory autoencoders are subsequently trained for each engine subsystem. By calculating the mean absolute error of the reconstructions, a subsystem-specific health index is computed, which is used to estimate the remaining useful life. Full article

Gravity and gravity gradient data serve as fundamental inputs for geophysical resource exploration and geological structure analysis. However, traditional denoising methods—including wavelet transforms, moving averages, and low-pass filtering—exhibit signal loss and limited adaptability under complex, non-stationary noise conditions. To address these challenges, this study proposes an improved U-Net deep learning framework that integrates multi-scale feature extraction and attention mechanisms. Furthermore, a Laplace consistency constraint is introduced into the loss function to enhance denoising performance and physical interpretability. Notably, the datasets used in this study are generated by the authors, involving simulations of subsurface prism distributions with realistic density perturbations (±20% of typical rock densities) and the addition of controlled Gaussian noise (5%, 10%, 15%, and 30%) to simulate field-like conditions, ensuring the diversity and physical relevance of training samples. Experimental validation on these synthetic datasets and real field datasets demonstrates the superiority of the proposed method over conventional techniques. For noise levels of 5%, 10%, 15%, and 30% in test sets, the improved U-Net achieves Peak Signal-to-Noise Ratios (PSNR) of 59.13 dB, 52.03 dB, 48.62 dB, and 48.81 dB, respectively, outperforming wavelet transforms, moving averages, and low-pass filtering by 10–30 dB. In multi-component gravity gradient denoising, our method excels in detail preservation and noise suppression, improving Structural Similarity Index (SSIM) by 15–25%. Field data tests further confirm enhanced identification of key geological anomalies and overall data quality improvement. In summary, the improved U-Net not only delivers quantitative advancements in gravity data denoising but also provides a novel approach for high-precision geophysical data preprocessing. Full article

Generative adversarial networks (GANs) have significantly advanced synthetic image generation, yet ensuring topological coherence remains a challenge. This paper introduces TopoSinGAN, a topology-aware extension of the SinGAN framework, designed to enhance the topological accuracy of generated images. TopoSinGAN incorporates a novel, differentiable topology loss function that minimizes terminal node counts along predicted segmentation boundaries, thereby addressing topological anomalies not captured by traditional losses. We evaluate TopoSinGAN using agricultural and dendrological case studies, demonstrating its capability to maintain boundary continuity and reduce undesired loop openness. A novel evaluation metric, Node Topology Clustering (NTC), is proposed to assess topological attributes independently of geometric variations. TopoSinGAN significantly improves topological accuracy, reducing NTC index values from 15.15 to 3.94 for agriculture and 14.55 to 2.44 for dendrology, compared to the baseline SinGAN. Modified FID evaluations also show improved realism, with lower FID scores: 0.1914 for agricultural fields compared to 0.2485 for SinGAN, and 0.0013 versus 0.0014 for dendrology. The topology loss enables end-to-end training with direct topological feedback. This new framework advances the generation of topologically accurate synthetic images, with applications in fields requiring precise structural representations, such as geographic information systems (GIS) and medical imaging. Full article

When using traditional Euler deconvolution optimization strategies, it is difficult to distinguish between anomalies and their corresponding Euler tails (those solutions are often distributed outside the anomaly source, forming “tail”-shaped spurious solutions, i.e., misplaced Euler solutions, which must be removed or marked) with only the structural index. The nonparametric estimation method based on the normalized B-spline probability density (BSS) is used to separate the Euler solution clusters and mark different anomaly sources according to the similarity and density characteristics of the Euler solutions. For display purposes, the BSS needs to map the samples onto the estimation grid at the points where density will be estimated in order to obtain the probability density distribution. However, if the size of the samples or the estimation grid is too large, this process can lead to high levels of memory consumption and excessive computation times. To address this issue, a fast linear binning approximation algorithm is introduced in the BSS to speed up the computation process and save time. Subsequently, the sample data are quickly projected onto the estimation grid to facilitate the discrete convolution between the grid and the density function using a fast Fourier transform. A method involving multivariate B-spline probability density estimation based on the FFT (BSSFFT), in conjunction with fast linear binning appropriation, is proposed in this paper. The results of two random normal distributions show the correctness of the BSS and BSSFFT algorithms, which is verified via a comparison with the true probability density function (pdf) and Gaussian kernel smoothing estimation algorithms. Then, the Euler solutions of the two synthetic models are analyzed using the BSS and BSSFFT algorithms. The results are consistent with their theoretical values, which verify their correctness regarding Euler solutions. Finally, the BSSFFT is applied to Bishop 5X data, and the numerical results show that the comprehensive analysis of the 3D probability density distributions using the BSSFFT algorithm, derived from the Euler solution subset of $\left\{x_0,y_0,z_0\right\}$, can effectively separate and locate adjacent anomaly sources, demonstrating strong adaptability. Full article

Electrical resistivity (ER), induced polarization (IP), and self-potential (SP) are three geophysical methods that have been broadly used in the realm of mineral exploration. These geophysical methods provide complementary information, each exhibiting a distinct sensitivity to various types of mineral deposits. Considering the relationship among these three methods, we propose an integrated approach that merges their respective information to offer an improved localization technique for ore bodies. First, we invert the electrical conductivity distribution through electrical resistance tomography (ERT). Then, we use the inverted conductivity distribution to invert the IP and SP data in terms of chargeability and source current density distributions. Then, we normalize the inverted chargeability and source current density distributions and we combine them to obtain an ore body index (ORI) $\chi$ used to delineate the potential locations of ore deposits. We design this index to be sensitive to the presence of ore bodies, which are reflected by either strong and localized source current density (SP) and/or strong chargeability values (IP). The proposed method is first validated using a synthetic model with two distinct anomalies characterized by different properties. The results show the limitation of individual inversion, as each method exclusively detects one of these anomalies. The combined approach allows a better characterization of the target. Then, the approach is applied to a sandbox experiment in which two metallic bodies are buried in water-saturated sand used as the background. Again, the proposed methodology is successfully applied to the detection of the metallic targets, improving their localization compared with individual methods. Full article

With advancements in remote sensing technology and the increasing availability of remote sensing platforms, the capacity to monitor droughts using multiple satellite remote sensing observations has significantly improved. This enhanced capability facilitates a comprehensive understanding of drought conditions and early warnings for extreme drought events. In this study, multiple satellite datasets, including Gravity Recovery and Climate Experiment (GRACE), the Global Precipitation Measurement (GPM) precipitation dataset, and the Global Land the Data Assimilation System (GLDAS) dataset, were used to conduct an innovative in-depth characteristic analysis and identification of the extreme drought event in the Poyang Lake Basin (PLB) in 2022. Furthermore, the drought characteristics were also supplemented by processing the synthetic aperture radar (SAR) image data to obtain lake water area changes and integrating in situ water level data as well as the Moderate Resolution Imaging Spectroradiometer (MODIS) vegetation index dataset, which provided additional instances of utilizing multi-source remote sensing satellite data for feature analysis on extreme drought events. The extreme drought event in 2022 was identified by the detection of non-seasonal negative anomalies in terrestrial water storage derived from the GRACE and GLDAS datasets. The Mann–Kendall (M-K) test results for water levels indicated a significant abrupt decrease around July 2022, passing a significance test with a 95% confidence level, which further validated the reliability of our finding. The minimum area of Poyang Lake estimated by SAR data, corresponding to 814 km², matched well with the observed drought characteristics. Additionally, the evident lower vegetation index compared to other years also demonstrated the severity of the drought event. The utilization of these diverse datasets and their validation in this study can contribute to achieving a multi-dimensional monitoring of drought characteristics and the establishment of more robust drought models. Full article

Training-anomaly-based, machine-learning-based, intrusion detection systems (AMiDS) for use in critical Internet of Things (CioT) systems and military Internet of Things (MioT) environments may involve synthetic data or publicly simulated data due to data restrictions, data scarcity, or both. However, synthetic data can be unrealistic and potentially biased, and simulated data are invariably static, unrealistic, and prone to obsolescence. Building an AMiDS logical model to predict the deviation from normal behavior in MioT and CioT devices operating at the sensing or perception layer due to adversarial attacks often requires the model to be trained using current and realistic data. Unfortunately, while real-time data are realistic and relevant, they are largely imbalanced. Imbalanced data have a skewed class distribution and low-similarity index, thus hindering the model’s ability to recognize important features in the dataset and make accurate predictions. Data-driven learning using data sampling, resampling, and generative methods can lessen the adverse impact of a data imbalance on the AMiDS model’s performance and prediction accuracy. Generative methods enable passive adversarial learning. This paper investigates several data sampling, resampling, and generative methods. It examines their impacts on the performance and prediction accuracy of AMiDS models trained using imbalanced data drawn from the UNSW_2018_IoT_Botnet dataset, a publicly available IoT dataset from the IEEEDataPort. Furthermore, it evaluates the performance and predictability of these models when trained using data transformation methods, such as normalization and one-hot encoding, to cover a skewed distribution, data sampling and resampling methods to address data imbalances, and generative methods to train the models to increase the model’s robustness to recognize new but similar attacks. In this initial study, we focus on CioT systems and train PCA-based and oSVM-based AMiDS models constructed using low-complexity PCA and one-class SVM (oSVM) ML algorithms to fit an imbalanced ground truth IoT dataset. Overall, we consider the rare event prediction case where the minority class distribution is disproportionately low compared to the majority class distribution. We plan to use transfer learning in future studies to generalize our initial findings to the MioT environment. We focus on CioT systems and MioT environments instead of traditional or non-critical IoT environments due to the stringent low energy, the minimal response time constraints, and the variety of low-power, situational-aware (or both) things operating at the sensing or perception layer in a highly complex and open environment. Full article

Ephemeral rivers are characterized by brief episodic flood events, which recharge subterraean alluvial aquifers that sustain humans, riparian vegetation, and wildlife in the hyper-arid Namib Desert. Yet we only have a poor understanding of the dynamics and feedback mechanisms in these hydrological systems as arid and semi-arid zones are typically poorly equipped with reliable in situ monitoring stations to provide necessary information. The main objective of our study is to show the potential of satellite data to monitor the dynamics of ephemeral rivers, such as the Kuiseb located in Namibia, since remotesensing offers the advantage of adapted spatial and temporal resolutions. For this study, multi-spectral imagery (Sentinel-2), Synthetic Aperture Radar (SAR, Sentinel-1), and SAR interferometry (Sentinel-1) data were used to produce Normalized Difference Vegetation Index (NDVI) maps, backscattering maps (as σ₀), and interferograms, respectively. These parameters provide information on the hydrologic and vegetation dynamics of the river. Strong variations in NDVI, σ₀, and interferograms are observed during March–April 2017 and June–July 2018 in a tributary of the Kuiseb in the central Namib Desert. In those years, rain events caused the reactivation of the tributary. However, during a major flood in 2021, when no rain occured, no variations in NDVI were detected in this tributary, unlike the σ₀ and interferogram anomalies after the flood. Thus, these variations cannot be explained by rains, which were non-existent during this period, but seem to be linked to the dynamics of the aquifer of the Kuiseb River, wherein floods recharge the alluvial aquifers and the rising water table levels produce a signal that is measurable by satellite radar sensors. All these results present a preliminary work that might be used by water resource managers to automate the processing and methods used to create an ephemeral river monitoring tool. Full article

In modern industrial systems, high-dimensional process data provide rich information for process monitoring. To make full use of local information of industrial process, a distributed robust dictionary pair learning (DRDPL) is proposed for refined process monitoring. Firstly, the global system is divided into several sub-blocks based on the reliable prior knowledge of industrial processes, which achieves dimensionality reduction and reduces process complexity. Secondly, a robust dictionary pair learning (RDPL) method is developed to build a local monitoring model for each sub-block. The sparse constraint with $l_{2,1}$ norm is added to the analytical dictionary, and a low rank constraint is applied to the synthetical dictionary, so as to obtain robust dictionary pairs. Then, Bayesian inference method is introduced to fuse local monitoring information to global anomaly detection, and the block contribution index and variable contribution index are used to realize anomaly isolation. Finally, the effectiveness of the proposed method is verified by a numerical simulation experiment and Tennessee Eastman benchmark tests, and the proposed method is then successfully applied to a real-world aluminum electrolysis process. Full article

This study develops a fault detection device for the fiber Bragg grating (FBG) sensing system and a fault detection method to realize the rapid detection of the FBG sensing system on airplanes. According to the distribution of FBG sensors on airplanes, the FBG sensing system is built based on wavelength division multiplexing (WDM) and space division multiplexing (SDM) technologies. Furthermore, the hardware and software of the fault detection device and the relevant FBG demodulator are studied in detail. Additionally, in view of the similar features of the healthy FBG sensor in the same measuring point, a rapid fault diagnosis method based on a synthetical anomaly index is proposed. The features (light intensity I, signal length L, standard deviation of original sample $\sigma$ and energy value in time-domain P) of FBG sensors are extracted. The aggregation center value of the above feature values is obtained through the loop iteration method. Furthermore, the separation degrees of features are calculated and then form the synthetical anomaly index so as to make an effective diagnosis of the state of the FBG sensor. Finally, the designed fault detection instrument and proposed fault detection method are used to monitor the 25 FBG sensors on the airplane, the results indicated that three faulty and two abnormal FBG sensors on the airplane are identified, showing the effectiveness of the proposed fault detection method. Full article

Timely and reliable estimations of crop yield are essential for crop management and successful food trade. In previous studies, remote sensing data or climate data are often used alone in statistical yield estimation models. In this study, we synthetically used agrometeorological indicators and remote sensing vegetation parameters to estimate maize yield in Jilin and Liaoning Provinces of China. We applied two methods to select input variables, used the random forest method to establish yield estimation models, and verified the accuracy of the models in three disaster years (1997, 2000, and 2001). The results show that the R² values of the eight yield estimation models established in the two provinces were all above 0.7, Lin’s concordance correlation coefficients were all above 0.84, and the mean absolute relative errors were all below 0.14. The mean absolute relative error of the yield estimations in the three disaster years was 0.12 in Jilin Province and 0.13 in Liaoning Province. A model built using variables selected by a two-stage importance evaluation method can obtain a better accuracy with fewer variables. The final yield estimation model of Jilin province adopts eight independent variables, and the final yield estimation model of Liaoning Province adopts nine independent variables. Among the 11 adopted variables in two provinces, ATT (accumulated temperature above 10 °C) variables accounted for the highest proportion (54.54%). In addition, the GPP (gross primary production) anomaly in August, NDVI (Normalized Difference Vegetation Index) anomaly in August, and standardized precipitation index with a two-month scale in July were selected as important modeling variables by all methods in the two provinces. This study provides a reference method for the selection of modeling variables, and the results are helpful for understanding the impact of climate on potential yield. Full article

Underground coal fires have become a worldwide disaster, which brings serious environmental pollution and massive energy waste. Xinjiang is one of the regions that is seriously affected by the underground coal fires. After years of extinguishing, the underground coal fire areas in Xinjiang have not been significantly reduced yet. To extinguish underground coal fires, it is critical to identify and monitor them. Recently, remote sensing technologies have been showing great potential in coal fires’ identification and monitoring. The thermal infrared technology is usually used to detect thermal anomalies in coal fire areas, and the Differential Synthetic Aperture Radar Interferometry (DInSAR) technology for the detection of coal fires related to ground subsidence. However, non-coal fire thermal anomalies caused by ground objects with low specific heat capacity, and surface subsidence caused by mining and crustal activities have seriously affected the detection accuracy of coal fire areas. To improve coal fires’ detection accuracy by using remote sensing technologies, this study firstly obtains temperature, normalized difference vegetation index (NDVI), and subsidence information based on Landsat8 and Sentinel-1 data, respectively. Then, a multi-source information strength and weakness constraint method (SWCM) is proposed for coal fire identification and analysis. The results show that the proposed SWCM has the highest coal fire identification accuracy among the employed methods. Moreover, it can significantly reduce the commission and omission error caused by non-coal fire-related thermal anomalies and subsidence. Specifically, the commission error is reduced by 70.4% on average, and the omission error is reduced by 30.6%. Based on the results, the spatio-temporal change characteristics of the coal fire areas have been obtained. In addition, it is found that there is a significant negative correlation between the time-series temperature and the subsidence rate of the coal fire areas (R² reaches 0.82), which indicates the feasibility of using both temperature and subsidence to identify and monitor underground coal fires. Full article

This paper studies the detection of anomalous crop development at the parcel-level based on an unsupervised outlier detection technique. The experimental validation is conducted on rapeseed and wheat parcels located in Beauce (France). The proposed methodology consists of four sequential steps: (1) preprocessing of synthetic aperture radar (SAR) and multispectral images acquired using Sentinel-1 and Sentinel-2 satellites, (2) extraction of SAR and multispectral pixel-level features, (3) computation of parcel-level features using zonal statistics and (4) outlier detection. The different types of anomalies that can affect the studied crops are analyzed and described. The different factors that can influence the outlier detection results are investigated with a particular attention devoted to the synergy between Sentinel-1 and Sentinel-2 data. Overall, the best performance is obtained when using jointly a selection of Sentinel-1 and Sentinel-2 features with the isolation forest algorithm. The selected features are co-polarized (VV) and cross-polarized (VH) backscattering coefficients for Sentinel-1 and five Vegetation Indexes for Sentinel-2 (among us, the Normalized Difference Vegetation Index and two variants of the Normalized Difference Water). When using these features with an outlier ratio of 10%, the percentage of detected true positives (i.e., crop anomalies) is equal to 94.1% for rapeseed parcels and 95.5% for wheat parcels. Full article

With sea level rise accelerating and coastal populations increasing, the requirement of coastal managers and scientists to produce accurate predictions of shoreline change is becoming ever more urgent. Waves are the primary driver of coastal evolution, and much of the interannual variability of the wave conditions in the Northeast Atlantic can be explained by broadscale patterns in atmospheric circulation. Two of the dominant climate indices that capture the wave climate in western Europe’s coastal regions are the ‘Western Europe Pressure Anomaly’ (WEPA) and ‘North Atlantic Oscillation’ (NAO). This study utilises a shoreline prediction model (ShoreFor) which is forced by synthetic waves to investigate whether forecasts can be improved when the synthetic wave generation algorithm is informed by relevant climate indices. The climate index-informed predictions were tested against a baseline case where no climate indices were considered over eight winter periods at Perranporth, UK. A simple adaption to the synthetic wave-generating process has allowed for monthly climate index values to be considered before producing the 10³ random waves used to force the model. The results show that improved seasonal predictions of shoreline change are possible if climate indices are known a priori. For NAO, modest gains were made over the uninformed ShoreFor model, with a reduction in average root mean square error (RMSE) of 7% but an unchanged skill score. For WEPA, the gains were more significant, with the average RMSE 12% lower and skill score 5% higher. Highlighted is the importance of selecting an appropriate index for the site location. This work suggests that better forecasts of shoreline change could be gained from consideration of a priori knowledge of climatic indices in the generation of synthetic waves. Full article

Central Asian mountain regions are prone to multiple types of natural hazards, often causing damage due to the impact of mass movements. In spring 2017, Kyrgyzstan suffered significant losses from a massive landslide activation event, during which also two of the largest deep-seated mass movements of the former mining area of Mailuu-Suu—the Koytash and Tektonik landslides—were reactivated. This study consists of the use of optical and radar satellite data to highlight deformation zones and identify displacements prior to the collapse of Koytash and to the more superficial deformation on Tektonik. Especially for the first one, the comparison of Digital Elevation Models of 2011 and 2017 (respectively, satellite and unmanned aerial vehicle (UAV) imagery-based) highlights areas of depletion and accumulation, in the scarp and near the toe, respectively. The Differential Synthetic Aperture Radar Interferometry analysis identified slow displacements during the months preceding the reactivation in April 2017, indicating the long-term sliding activity of Koytash and Tektonik. This was confirmed by the computation of deformation time series, showing a positive velocity anomaly on the upper part of both landslides. Furthermore, the analysis of the Normalized Difference Vegetation Index revealed land cover changes associated with the sliding process between June 2016 and October 2017. In addition, in situ data from a local meteorological station highlighted the important contribution of precipitation as a trigger of the collapse. The multidirectional approach used in this study demonstrated the efficiency of applying multiple remote sensing techniques, combined with a meteorological analysis, to identify triggering factors and monitor the activity of landslides. Full article