Search Results (191)

The contamination of marine ecosystems by oil spills poses a significant threat to the marine environment, necessitating the prompt and effective implementation of measures to mitigate the associated damage. Satellites offer a spatial and temporal advantage over aircraft and unmanned aerial vehicles (UAVs) in oil spill detection due to their wide-area monitoring capabilities. While oil spill detection has traditionally relied on synthetic aperture radar (SAR) images, the combined use of optical satellite sensors alongside SAR can significantly enhance monitoring capabilities, providing improved spatial and temporal coverage. The advent of deep learning methodologies, particularly convolutional neural networks (CNNs) and Transformer models, has generated considerable interest in their potential for oil spill detection. In this study, we conducted a comprehensive and objective comparison to evaluate the suitability of CNN and Transformer models for marine oil spill detection. High-resolution optical satellite images were used to optimize DeepLabV3+, a widely utilized CNN model; Swin-UPerNet, a representative Transformer model; and Mask2Former, which employs a Transformer-based architecture for both encoding and decoding. The results of cross-validation demonstrate a mean Intersection over Union (mIoU) of 0.740, 0.840 and 0.804 for all the models, respectively, indicating their potential for detecting oil spills in the ocean. Additionally, we performed a histogram analysis on the predicted oil spill pixels, which allowed us to classify the types of oil. These findings highlight the considerable promise of the Swin Transformer models for oil spill detection in the context of future marine disaster monitoring. Full article

Monitoring crude oil spills in coastal areas is challenging due to limitations in traditional in situ methods. Electrical resistivity imaging (ERI) offers a high-resolution approach to monitoring the subsurface spatial distribution of crude oil, but its effectiveness in highly-resistive, unsaturated coastal sands with varying salinity remains unexplored. This study assessed the effectiveness of ERI for monitoring crude oil spills in sandy soil using a 200 × 60 × 60 cm 3D sandbox filled with medium-fine-grained sand under unsaturated conditions. Two liters of crude oil were spilled under controlled conditions and monitored for 48 h using two surface ERI transects with 98 electrodes spaced every 2 cm and a dipole–dipole electrode array. The influence of varying salinity was simulated by varying the pore-fluid conductivities at four levels (0.6, 20, 50, and 85 mS/cm). After 48 h, the results show a percentage resistivity increase of 980%, 280%, 142%, and 70% for 0.6, 20, 50, and 85 mS/cm, respectively. The crude oil migration patterns varied with porewater salinity as higher salinity enhanced the crude oil retention at shallow depth. High salinity produces a smaller resistivity contrast, thus limiting the sensitivity of ERI in detecting the crude oil contaminant. These findings underscore the need to account for salinity variations when designing remediation strategies, as elevated salinity may restrict crude oil migration, resulting in localized contaminations. Full article

Neural networks (NNs) have proven their ability to deal with many computer vision tasks, including image-based remote sensing such as the identification and segmentation of hyperspectral images captured by satellites. Often, NNs run on a ground system upon receiving the data from the satellite. On the one hand, this approach introduces a considerable latency due to the time needed to transmit the satellite-borne images to the ground station. On the other hand, it allows the employment of computationally intensive NNs to analyze the received data. Low-budget missions, e.g., CubeSat missions, have computation capability and power consumption requirements that may prevent the deployment of complex NNs onboard satellites. These factors represent a limitation for applications that may benefit from a low-latency response, e.g., wildfire detection, oil spill identification, etc. To address this problem, in the last few years, some missions have started adopting NN accelerators to reduce the power consumption and the inference time of NNs deployed onboard satellites. Additionally, the harsh space environment, including radiation, poses significant challenges to the reliability and longevity of onboard hardware. In this review, we will show which hardware accelerators, both from industry and academia, have been found suitable for onboard NN acceleration and the main software techniques aimed at reducing the computational requirements of NNs when addressing low-power scenarios. Full article

The detection of complex formations, initially suspected to be oil spills, is investigated using atmospherically corrected multispectral satellite images and deep learning techniques. Several formations have been detected in an inland lake in Northern Greece. Four atmospheric corrections (ACOLITE, iCOR, Polymer, and C2RCC) that are specifically designed for water applications are examined and implemented on Sentinel-2 multispectral satellite images to eliminate the influence of the atmosphere. Out of the four algorithms, iCOR and ACOLITE are able to depict the formations sufficiently; however, the latter is chosen for further processing due to fewer uncertainties in the depiction of these formations as anomalies across the multispectral range. Furthermore, a number of formations are annotated at the pixel level for the 10 m bands (red, green, blue, and NIR), and a deep neural network (DNN) is trained and validated. Our results show that the four-band configuration provides the best model for the detection of these complex formations. Despite not being necessarily related to oil spills, studying these formations is crucial for environmental monitoring, pollution detection, and the advancement of remote sensing techniques. Full article

This study proposed an improved full-scale aggregated MobileUNet (FA-MobileUNet) model to achieve more complete detection results of oil spill areas using synthetic aperture radar (SAR) images. The convolutional block attention module (CBAM) in the FA-MobileUNet was modified based on morphological concepts. By introducing the morphological attention module (MAM), the improved FA-MobileUNet model can reduce the fragments and holes in the detection results, providing complete oil spill areas which were more suitable for describing the location and scope of oil pollution incidents. In addition, to overcome the inherent category imbalance of the dataset, label smoothing was applied in model training to reduce the model’s overconfidence in majority class samples while improving the model’s generalization ability. The detection performance of the improved FA-MobileUNet model reached an mIoU (mean intersection over union) of 84.55%, which was 17.15% higher than that of the original U-Net model. The effectiveness of the proposed model was then verified using the oil pollution incidents that significantly impacted Taiwan’s marine environment. Experimental results showed that the extent of the detected oil spill was consistent with the oil pollution area recorded in the incident reports. Full article

It is of the utmost importance for every country to monitor and control maritime pollution within its exclusive economic zone (EEZ). The European Maritime Safety Agency (EMSA) has developed and implemented the CleanSeaNet (CSN) satellite monitoring system to aid in the surveillance and control of hydrocarbon and hazardous substance spills in the ocean. This system’s primary objective is to alert European Union (EU) coastal states to potential spills within their EEZs, enabling them to take the necessary legal and operational actions. To reduce operational costs and increase response capability, the feasibility of implementing a national network (NN) of unmanned vehicles (UVs), both surface and aerial, was explored using a Portuguese case study. The following approach and analysis can be easily generalized to other case studies, bringing essential knowledge to the field. Analyzing oil spill alert events in the Portuguese EEZ between 2017 and 2021 and performing a strengths, weaknesses, opportunities, and threats (SWOT) analysis, essential information has been proposed for the optimal location of an NN of UVs. The study results demonstrate that integrating spill alerts at sea with UVs may significantly improve response time, costs, and personnel involvement, making maritime pollution combat actions more effective. Full article

Microbial fuel cells (MFCs) represent a promising technology for sustainable energy generation, which leverages the metabolic activities of microorganisms to convert organic substrates into electrical energy. In oil spill scenarios, hydrocarbonoclastic biofilms naturally form at the water–oil interface, creating a distinct environment for microbial activity. In this work, we engineered a novel MFC that harnesses these biofilms by strategically positioning the positive electrode at this critical junction, integrating the biofilm’s natural properties into the MFC design. These biofilms, composed of specialized hydrocarbon-degrading bacteria, are vital in supporting electron transfer, significantly enhancing the system’s power generation. Next-generation sequencing and scanning electron microscopy were used to characterize the microbial community, revealing a significant enrichment of hydrocarbonoclastic Gammaproteobacteria within the biofilm. Notably, key genera such as Paenalcaligenes, Providencia, and Pseudomonas were identified as dominant members, each contributing to the degradation of complex hydrocarbons and supporting the electrogenic activity of the MFCs. An electrochemical analysis demonstrated that the MFC achieved a stable power output of 51.5 μW under static conditions, with an internal resistance of about 1.05 kΩ. The system showed remarkable long-term stability, which maintained consistent performance over a 5-day testing period, with an average daily energy storage of approximately 216 mJ. Additionally, the MFC effectively recovered after deep discharge cycles, sustaining power output for up to 7.5 h before requiring a recovery period. Overall, the study indicates that MFCs based on hydrocarbonoclastic biofilms provide a dual-functionality system, combining renewable energy generation with environmental remediation, particularly in wastewater treatment. Despite lower power output compared to other hydrocarbon-degrading MFCs, the results highlight the potential of this technology for autonomous sensor networks and other low-power applications, which required sustainable energy sources. Moreover, the hydrocarbonoclastic biofilm-based MFC presented here offer significant potential as a biosensor for real-time monitoring of hydrocarbons and other contaminants in water. The biofilm’s electrogenic properties enable the detection of organic compound degradation, positioning this system as ideal for environmental biosensing applications. Full article

Contamination of soil by spills of crude oil and oilfield brine is known to affect the species composition and functioning of soil microbial communities. However, the effect of such contamination on nitrogen cycling, an important biogeochemical cycle in tallgrass prairie soil, is less well known. Detecting nitrate-reducing (NR) and denitrifying (DN) bacteria via PCR amplification of the genes essential for these processes depends on how well PCR primers match the sequences of these bacteria. In this study, we enriched for NR and DN bacteria from oil/brine tallgrass prairie soil contaminated 5–10 years previously versus those cultured from uncontaminated soil, confirmed the capacity of 75 strains isolated from the enrichments to reduce nitrate and/nitrite, then screened the strains with primers specific to seven nitrogen cycle functional genes. The strains comprised a phylogenetically diverse group of NR and DN bacteria, with proportionately more γ-Proteobacteria in oil-contaminated sites and more Bacilli in brine-contaminated sites, suggesting some residual effect of the contaminants on the NR and DN species distribution. Around 82% of the strains shown to reduce nitrate/nitrite would not be identified as NR and DN bacteria by the battery of NR and DN primers used. Our results indicate an urgent need to expand the NR/DN functional gene primer database by first identifying novel NR/DN strains through their capacity to reduce nitrate/nitrite. Full article

Anning Refinery, a large-scale joint venture in southern China, possesses significant potential in regard to polluting local groundwater environments due to its extensive petroleum raw materials. This study aims to mitigate the substantial risks associated with oil spills and prevent consequential groundwater pollution by developing a robust groundwater flow model using the MODFLOW module in GMS software that aligns closely with natural and pumping test conditions. Furthermore, by integrating the MT3DMS model, a groundwater solute transport model is constructed and calibrated using sodium chloride tracer dispersion data. Notably, the wax hydrocracking unit and aviation coal finished product tank area are identified as key pollution sources warranting attention. By considering local constraints such as karst collapse, ground subsidence, and single-well water output capacity, the study introduces a tailored groundwater pollution management model. The research simulates various scenarios of petroleum pollutant migration in groundwater and proposes multi-objective emergency response optimization plans. In Scenario 1, simulations show that petroleum pollutants migrate within the unconfined aquifer and enter the karst aquifer as low-concentration plumes over an extended period. Detection of these plumes in karst water monitoring wells indicates upstream unconfined aquifer contamination at higher concentrations, necessitating immediate activation of the nearest monitoring or emergency wells in both layers. Conversely, in Scenario 2, pollutants reside briefly in the unconfined aquifer before entering the karst aquifer at relatively higher concentrations. Here, low-efficiency pollutant discharge through unconfined aquifer monitoring wells prompts the activation of nearby karst aquifer monitoring or emergency wells for effective pollution control. This model underscores the necessity for proactive monitoring and validates the efficacy of coupled numerical modeling in understanding pollutant behavior, offering valuable insights into pollution control scenario assessments. In summary, the study emphasizes the importance of targeted monitoring and emergency protocols, demonstrating the benefits of integrated modeling approaches in industrial areas prone to pollution risks, and provides critical theoretical and practical guidance for groundwater protection and pollution management, offering transferable insights for similar industrial settings worldwide. Full article

Oil spill SAR images are characterized by high noise, low contrast, and irregular boundaries, which lead to the problems of overfitting and insufficient capturing of detailed features of the oil spill region in the current method when processing oil spill SAR images. An improved DeepLabV3+ model is proposed to address the above problems. First, the original backbone network Xception is replaced by the lightweight MobileNetV2, which significantly improves the generalization ability of the model while drastically reducing the number of model parameters and effectively addresses the overfitting problem. Further, the spatial and channel Squeeze and Excitation module (scSE) is introduced and the joint loss function of Bce + Dice is adopted to enhance the sensitivity of the model to the detailed parts of the oil spill area, which effectively solves the problem of insufficient capture of the detailed features of the oil spill area. The experimental results show that the mIOU and F1-score of the improved model in an oil spill region in the Gulf of Mexico reach 80.26% and 88.66%, respectively. In an oil spill region in the Persian Gulf, the mIOU and F1-score reach 81.34% and 89.62%, respectively, which are better than the metrics of the control model. Full article

Monitoring oil drift by integrating multi-source satellite imagery has been a relatively underexplored practice due to the limited time-sampling of datasets. However, this limitation has been mitigated by the emergence of new satellite constellations equipped with both Synthetic Aperture Radar (SAR) and optical sensors. In this manuscript, we take advantage of multi-temporal and multi-source satellite imagery, incorporating SAR (Sentinel-1 and ICEYE-X) and optical data (Sentinel-2/3 and Landsat-8/9), to provide insights into the spatio-temporal variations of oil spills. We also analyze the impact of met–ocean conditions on oil drift, focusing on two specific scenarios: marine floating oil slicks off the coast of Qatar and oil spills resulting from a shipwreck off the coast of Mauritius. By overlaying oils detected from various sources, we observe their short-term and long-term evolution. Our analysis highlights the finding that changes in oil structure and size are influenced by strong surface winds, while surface currents predominantly affect the spread of oil spills. Moreover, to detect oil slicks across different datasets, we propose an innovative unsupervised algorithm that combines a Bayesian approach used to detect oil and look-alike objects with an oil contours approach distinguishing oil from look-alikes. This algorithm can be applied to both SAR and optical data, and the results demonstrate its ability to accurately identify oil slicks, even in the presence of oil look-alikes and under varying met–ocean conditions. Full article

Detecting oil spills in marine environments is crucial for avoiding environmental damage and facilitating rapid response efforts. In this study, we propose a robust method for oil spill detection leveraging state-of-the-art (SOTA) deep learning techniques. We constructed an extensive dataset comprising images and frames extracted from video sourced from Google, significantly augmenting the dataset through frame extraction techniques. Each image is meticulously labeled to ensure high-quality training data. Utilizing the Yolov8 segmentation model, we trained our oil spill detection model to accurately identify and segment oil spills in ocean environments. K-means and Truncated Linear Stretching algorithms are combined with trained model weight to increase model detection accuracy. The model demonstrated exceptional performance, yielding high detection accuracy and precise segmentation capabilities. Our results indicate that this approach is highly effective for real-time oil spill detection, offering a promising tool for environmental monitoring and disaster management. In training metrics, the model reached over 97% accuracy in 100 epochs. In evaluation, model achieved its best detection rates by 94% accuracy in F1, 93.9% accuracy in Precision, and 95.5% [email protected] accuracy in Recall curves. Full article

With the development of the marine oil industry, leakage accidents are one of the most serious problems threatening maritime and national security. The spilt crude oil can float and sink in the water column, posing a serious long-term threat to the marine environment. High-frequency sonar detection is currently the most efficient method for identifying sunken oil. However, due to the complicated environment of the deep seabed and the interference of the sunken oil signals with homogeneous information, sonar detection data are usually difficult to interpret, resulting in low efficiency and a high failure rate. Previous works have focused on features designed by experts according to the detection environments and the identification of sunken oil targets regardless of the feature extraction step. To automatically identify sunken oil targets without a prior knowledge of the complex seabed conditions during the image acquisition process for sonar detection, a systematic framework is contrived for identifying sunken oil targets that combines image enhancement with a convolutional neural network (CNN) classifier for the final decision on sunken oil targets examined in this work. Case studies are conducted using datasets obtained from a sunken oil release experiment in an outdoor water basin. The experimental results show that (i) the method can effectively distinguish between the sunken oil target, the background, and the interference target; (ii) it achieved an identification accuracy of 83.33%, outperforming feature-based recognition systems, including SVM; and (iii) it provides important information about sunken oil such as the location of the leak, which is useful for decision-making in emergency response to oil spills at sea. This line of research offers a more robust and, above all, more objective option for the difficult task of automatically identifying sunken oils under complex seabed conditions. Full article

Oil spillages on a sea’s or an ocean’s surface are a threat to marine and coastal ecosystems. They are mainly caused by ship accidents, illegal discharge of oil from ships during cleaning and oil seepage from natural reservoirs. Synthetic-Aperture Radar (SAR) has proved to be a useful tool for analyzing oil spills, because it operates in all-day, all-weather conditions. An oil spill can typically be seen as a dark stretch in SAR images and can often be detected through visual inspection. The major challenge is to differentiate oil spills from look-alikes, i.e., low-wind areas, algae blooms and grease ice, etc., that have a dark signature similar to that of an oil spill. It has been noted over time that oil spill events in Pakistan’s territorial waters often remain undetected until the oil reaches the coastal regions or it is located by concerned authorities during patrolling. A formal remote sensing-based operational framework for oil spills detection in Pakistan’s Exclusive Economic Zone (EEZ) in the Arabian Sea is urgently needed. In this paper, we report the use of an encoder–decoder-based convolutional neural network trained on an annotated dataset comprising selected oil spill events verified by the European Maritime Safety Agency (EMSA). The dataset encompasses multiple classes, viz., sea surface, oil spill, look-alikes, ships and land. We processed Sentinel-1 acquisitions over the EEZ from January 2017 to December 2023, and we thereby prepared a repository of SAR images for the aforementioned duration. This repository contained images that had been vetted by SAR experts, to trace and confirm oil spills. We tested the repository using the trained model, and, to our surprise, we detected 92 previously unreported oil spill events within those seven years. In 2020, our model detected 26 oil spills in the EEZ, which corresponds to the highest number of spills detected in a single year; whereas in 2023, our model detected 10 oil spill events. In terms of the total surface area covered by the spills, the worst year was 2021, with a cumulative 395 sq. km covered in oil or an oil-like substance. On the whole, these are alarming figures. Full article

Oil spill detection plays an important role in marine environment protection. The technique of global navigation satellite system-reflectometry (GNSS-R) has the advantage of a short revisit time, which could help with timely cleanup of marine oil pollution. The conventional GNSS-R oil spill detection algorithm can resolve only the dielectric constant of oil based on power ratio measurements, while that of water cannot be realized. This is because the dielectric constant of water is much larger than that of oil such that the range of the equation used in the conventional algorithm is inadequate. To resolve this problem, we proposed a new algorithm containing a new equation with a larger scope, which has never been applied previously to GNSS-R oil spill detection. We derived a lookup method to resolve the dielectric constant of both oil and water. To validate our method, a drone-borne GNSS-R experiment based on dual-frequency QZSS reflection signals was conducted on 17 July 2023 using experimental pools simulating oil spills. Raw IF data in the L1 and L5 bands, collected using dual antennas and a data recorder, were processed using a software-defined receiver to deduce the power ratios and SNR of the GNSS signals. Results showed that the proposed algorithm is capable of resolving the dielectric constants of the reflected surface. In addition, the L5 signal was found to provide more detail and better contrast than the L1 C/A signal. Full article