Haihui Dong

Oil spills at sea pose a serious threat to marine ecosystems and coastal economic development. Therefore, rapid and accurate detection of oil spills is crucial for emergency response and environmental protection. Marine radar offers unique advantages in short-range, continuous, and all-weather monitoring, making it an important supplementary tool for oil spill detection. However, oil film targets in marine radar images exhibit low contrast and a low signal-to-noise ratio, and are easily affected by factors such as clutter and co-frequency interference, making it difficult for traditional detection methods to achieve accurate extraction. To address these issues, this paper proposes a two-stage framework for oil spill detection utilizing marine radar, which consists of candidate region extraction using a QGJO-optimized feature-weighted GRNN and precise segmentation using QHHO-based threshold optimization. The methodology begins with candidate region extraction, wherein pixel-level multidimensional scattering features are designed and scattering priors are leveraged to automate sample collection without manual annotation. A feature-weighted generalized regression neural network (GRNN) is subsequently constructed, with its parameters and feature weights jointly optimized via the Quantum Golden Jackal Optimization (QGJO) algorithm, thereby enabling efficient delineation of oil-film candidate regions. The subsequent object detection stage then formulates oil slick extraction as a single-threshold binary classification problem, for which the Quantum Harris–Hawk Optimization (QHHO) algorithm is adopted to autonomously determine the optimal segmentation threshold. Finally, morphological post-processing is performed to suppress residual noise and produce precise, continuous oil film contours. Results verify that the proposed method effectively reconciles detection completeness with false-alarm control, constituting an efficient and deployable solution for shipborne radar-based oil spill monitoring.

Marine oil spills pose significant threats to ecosystems and coastal economies, making accurate oil film detection from remote sensing data a critical task. This study proposes a two-stage method, GCN-IGJO, for segmenting oil films in challenging X-band radar images. The method first uses a Graph Convolutional Network (GCN) to learn high-order features from pixel data, enabling effective initial region extraction. Subsequently, an Improved Golden Jackal Optimization (IGJO) algorithm is introduced to perform precise threshold segmentation, incorporating specialized strategies to bias the search towards the low-intensity values characteristic of oil slicks. Experimental comparisons demonstrate that the proposed GCN-IGJO method achieves a superior balance between high precision and good recall, outperforming several baseline and alternative methods. The results validate the effectiveness of combining deep graph learning with an enhanced metaheuristic optimizer for the accurate segmentation of weak-target oil films.

Oil slicks pose a severe threat to marine ecosystems, making accurate and real-time detection increasingly urgent. Marine X-band radar has become an essential tool for oil slick monitoring due to its high temporal resolution and its ability to sensitively capture the damping of capillary waves on the sea surface caused by oil films. Building upon this, an unsupervised and lightweight SLIC-KMeans-GJO detection framework is proposed. The method first generates superpixels by using Simple Linear Iterative Clustering (SLIC) and then applies K-means clustering to extract region of interest (ROI). An improved Golden Jackal Optimizer (GJO) is adaptively initialized based on the grayscale distribution and information entropy. To enhance optimization performance, Lévy flight and stochastic perturbation mechanisms are incorporated to improve global exploration and local convergence precision. Experimental results demonstrate that the proposed method significantly outperforms conventional thresholding approaches and other intelligent optimization-based segmentation algorithms in terms of noise suppression, target identification accuracy, and discrimination precision for oil slick targets. It effectively mitigates over-segmentation and false detections while preserving fine edge details and the true spatial extent of oil slicks. The proposed framework offers a novel and practical solution for real-time oil slick monitoring, holding strong potential for operational maritime emergency response.

Offshore oil exploration and the volume of imported crude oil shipping have increased steadily, elevating the risk of oil spills. An advanced offshore oil film identification method is proposed to realize the accurate and robust recognition and segmentation of oil films from marine radar images in offshore oil spill detection. This method integrates feature engineering with an improved Beetle Antennae Search (BAS) optimization algorithm, aiming to address the key issues of low discrimination between oil films and complex marine backgrounds and insufficient spill boundary localization accuracy in radar image analysis. First, the raw radar image was transformed into the Cartesian coordinate system, and a filtering procedure was applied to attenuate interference. Subsequently, the gray distribution and local contrast of the denoised image was further improved. Afterwards, the complexity of the grayscale distribution within each feature map was quantified using Shannon entropy. The Top-K feature maps with the highest entropy values were subsequently used to construct an information-rich subset. The subset was then processed through a pixel-wise averaging strategy to generate a coupled feature image. Then, Otsu threshold was used to refine ocean wave regions. Finally, the oil films were segmented with an improved BAS optimization algorithm. The fitness function of the improved BAS algorithm was augmented through the integration of edge fitting accuracy, and a target-proximity penalization scheme. Through an adaptive step-length modulation paradigm and Perceptual Mechanism, it can achieve a marked improvement in search accuracy and achieving precise segmentation of oil slicks. The detection accuracy of the proposed method is significantly enhanced relative to the traditional BAS algorithm and existing marine radar oil spill detection methods. The IOU, Dice, recall and F1-score reached 81.2%, 89.6%, 85.2%, and 90.1% respectively. This method not only advances the methodological rigor of spill detection but also provides critical data support for the development of more effective control and remediation practices.

To address the urgent need for rapid detection and precise segmentation of oil spill incidents, a cascaded processing framework integrating the YOLOv11 model with an enhanced Northern Goshawk Optimization (NGO) algorithm is proposed. This method effectively utilizes the advantages of deep learning and metaheuristic algorithms. Firstly, the YOLOv11 model was used for preliminary localization and segmentation of oil spill target regions in marine radar images. Subsequently, an improved NGO algorithm based on adaptive weighting factors, Levy flight perturbation, and pinhole imaging perturbation was used to finely segment the region, balancing processing efficiency and accuracy requirements. The experimental results showed that the cascade architecture proposed effectively balances the problems of false detection and missed detection. Compared with other methods, the marine radar oil film detection method based on YOLOv11 combined with improved NGO exhibited strong adaptability in complex scenes. Multiple indicators, such as accuracy, precision, recall, specificity, and Dice similarity coefficient, indicate that this method has good performance in marine radar oil spill detection tasks.

The hydrodynamic performance of a rudder behind a propeller is critical for determining vessel maneuvering stability. During navigation, the coupled effects of the oblique flow angle (β) and the rudder angle (δ) significantly alter the wake velocity field and vortex patterns aft of the rudder. However, the synergistic control mechanism of these two variables requires further quantitative investigation. This study employs the RANS method with the SST k-ε turbulence model to numerically simulate flow under advance coefficients (J) ranging from 0.3 to 0.9, oblique flow angles (β) from 0° to 15°, and rudder angles (δ) from 0° to 35°. Hydrodynamic coefficients, including the lift coefficient, drag coefficient, and lift-to-drag ratio, were calculated for the rudder. The evolution of the horizontal velocity and vortex fields was captured, with the model validated through localized flow field visualization. The results reveal that when β ≤ 3°, δ is the dominant factor influencing rudder hydrodynamics. Conversely, when β ≥ 9°, β becomes the primary regulating factor. The coupling effect induces significant asymmetry in the velocity distribution across the rudder surfaces and pronounced flow separation on the windward side, generating a complex vortex system (including primary and secondary vortices) on the leeward side. This research elucidates the coupled control mechanism of oblique flow and rudder angle, providing insights for enhancing steering margins and a quantitative foundation for optimizing rudder profiles in challenging sea environments characterized by high oblique flow and large rudder angles.

Oil spill accidents pose a grave threat to marine ecosystems, human economy, and public health. Consequently, expeditious and efficacious oil spill detection technology is imperative for the pollution mitigation and the health preservation in the marine environment. This study proposed a marine radar oil spill detection method based on Local Binary Patterns (LBP), Histogram of Oriented Gradient (HOG), and an improved Firefly Optimization Algorithm (IFA). In the stage of image pre-processing, the oil film features were significantly enhanced through three steps. The LBP features were extracted from the preprocessed image. Then, the mean filtering was used to smooth out the LBP features. Subsequently, the HOG statistical features were extracted from the filtered LBP feature map. After the feature enhancement, the oil spill regions were accurately extracted by using K-Means clustering algorithm. Next, an IFA model was used to classify oil films. Compared with traditional Firefly Optimization Algorithm (FA) algorithm, the IFA method is suitable for oil film segmentation tasks in marine radar data. The proposed method can achieve accuracy segmentation and provide a new technical path for marine oil spill monitoring.

Image-based ship monitoring technology has extensive applications, and is widely used in various aspects of port management, including illegal activity surveillance, vessel identification at entry and exit points, channel and berth management, unmanned vessel control, and incident warning and emergency response. However, most current ship identification technologies rely on a single information source, reducing detection accuracy in the complex and variable marine environment. To address this issue, this paper proposes a knowledge transfer-based ship identification system integrating three modules. The system enables synchronized monitoring of visible light coastal images, satellite cloud images, and infrared spectrum images, thereby mitigating problems such as low detection accuracy and poor adaptability of image recognition. Additionally, extensive supplementary experiments were conducted to evaluate the effectiveness of the preprocessing and data augmentation modules as well as the transfer learning module. The study also discusses the limitations of current deep learning-based ship monitoring models, particularly their poor adaptability to image recognition and inability to achieve all-weather, round-the-clock monitoring. Experimental results based on three ship monitoring datasets demonstrate that the proposed system, by integrating three distinct detection conditions, outperforms other models with an F1-score of 98.74%, approximately 10% higher than most existing ship detection systems.

As Arctic sea ice continues to melt and global demand for clean energy rises, Russia’s Liquefied Natural Gas (LNG) exports via the Northern Sea Route (NSR) are rapidly increasing. To ensure the operational safety of LNG carriers and safeguard the economic interests of stakeholders, including shipowners, a thorough assessment of the navigability of various ice-class LNG carriers along this route is essential. This study collected Arctic ice condition data from 2014 to 2023 and applied the Polar Operational Limit Assessment Risk Indexing System (POLARIS) methodology to calculate the Risk Index Outcome (RIO) for LNG carriers with No Ice Class, Arc4, and Arc7 ice classifications in Arctic waters. A navigability threshold of 95% RIO ≥ 0 was established to define navigable windows, and critical waters were identified where sections of the route remain in hazardous or risky conditions year-round. The results indicate that for No Ice Class vessels, Arc4 vessels, and Arc7 vessels, the navigable windows for westbound Route 1 and Route 2 under light, normal, and heavy ice conditions range from 70 to 133 days, 70 to 365 days, and 70 to 365 days, respectively, while for eastbound Route 3, the navigable windows range from 0 to 84 days, 0 to 238 days, and 7 to 365 days, respectively. The critical waters affecting the navigability of No Ice Class vessels, Arc4 vessels, and Arc7 vessels are primarily located in the Kara Sea, Laptev Sea and East Siberian Sea. This study, using the POLARIS methodology, provides valuable insights into the navigability of LNG carriers with different ice classes along the NSR, supporting the development and utilization of Arctic energy and shipping routes while offering decision-making support for stakeholders involved in Arctic maritime operations.

In the midst of a rapidly evolving economic landscape, the global demand for oil is steadily escalating. This increased demand has fueled marine extraction and maritime transportation of oil, resulting in a consequential and uneven surge in maritime oil spills. Characterized by their abrupt onset, rapid pollution dissemination, prolonged harm, and challenges in short-term containment, oil spill accidents pose significant economic and environmental threats. Consequently, it is imperative to adopt effective and reliable methods for timely detection of oil spills to minimize the damage inflicted by such incidents. Leveraging the YOLO deep learning network, this paper introduces a methodology for the automated detection of oil spill targets. The experimental data pre-processing incorporated denoise, grayscale modification, and contrast boost. Subsequently, realistic radar oil spill images were employed as extensive training samples in the YOLOv8 network model. The trained detection model demonstrated rapid and precise identification of valid oil spill regions. Ultimately, the oil films within the identified spill regions were extracted utilizing the simulated annealing particle swarm optimization (SA-PSO) algorithm. The proposed method for offshore oil spill survey presented here can offer immediate and valid data support for regular patrols and emergency reaction efforts.