Marine Surveillance Research Articles

Ocean Space Surveillance and Real-Time Event Characterization Using Distributed Acoustic Sensing on Submarine Networks

Abstract Distributed acoustic sensing (DAS) can be deployed on existing submarine fiber-optic cables to add long-range sensor capability to the cable infrastructure. In this article, we present the following: (1) observations and analysis of impulsive source events from long-term DAS measurements on a North Sea submarine telecommunications cable. The observations include local earthquakes originating in the crust below the cable, underwater explosions originating in the water column, an onshore explosion from the nearby coast, and examples of sonic booms from supersonic aircraft and a suspected meteor from the atmosphere. The analysis reveals how the signals from earthquakes and underwater/aerial explosions can be distinguished in the data domain based on their frequency and apparent velocity characteristics. (2) A processing workflow enabling real-time marine surveillance including detection and location of explosions in the water column. The processing is verified by corroborating local earthquakes and underwater explosions with independent data sources. We show that different types of waves can be identified including seismic body waves, hydroacoustic waves, and atmospheric infrasound waves coupled through the water column. Tracking the travel-time moveout along the nonstraight cable route allows for positioning of the source, which we demonstrate by migration stacking of the recorded signal. Signal processing suitable for real-time classification and source location is applied to the recorded data and shows how ocean space surveillance at scale can be realized.

Effect of multiple appendages on maritime surveillance ship resistance at various ship speeds

Resistance is a critical factor affecting the operational performance and economic efficiency of marine surveillance ships. To enhance the enforcement efficiency of marine surveillance ships, this study investigates the impact of five types of appendages on ship resistance performance. In this study, resistance experiments and numerical simulation calculation on the ship model were carried out. Based on Computational Fluid Dynamics (CFD) and the Volume of Fluid (VOF) method, the study captures the variations in ship resistance and the free surface Cases around the hull. A comparative analysis was then conducted on the resistance effects of different appendages installed on the ship model. It was found that the installation of stern shaft brackets, bilge keels, and ductkeel increased the ship's resistance. In contrast, the installation of spray rails reduced resistance by approximately 2.5%. However, the effectiveness of the spray rails diminished at high speeds due to their inability to prevent wave overtopping. Since stern flaps are commonly used drag-reducing appendages, this study improved the original design. Comparative analysis revealed that the modified curved structural design of the stern flaps exhibited enhanced drag reduction capabilities.

The Impact of China's Coast Guard on Indo‐Pacific Security from the Perspective of a Maritime Power

In 2024, the China Coast Guard (CCG) invoked China Coast Guard Regulation No. 3 to detain Taiwanese fishing boats twice in disputed waters. The positive actions of the CCG can be looked back to 2019. The CCG entered the waters of the Diaoyu islands in Japan twelve times and carried out cruises on the Diaoyu islands. It is necessary to study the follow-up actions of the CCG and their impact on Indo-Pacific security. This study examines the effect of the CCG's maritime rights protection on the security of the Indo-Pacific region when the People's Republic of China (China) becomes a maritime power. It was changed to the Maritime Police Corps of the Chinese People's Armed Police Force to integrate the business of marine surveillance, fishery administration, customs, border defense, and other units. The reason for the gradual expansion of powers and the impact of its strong protection of maritime rights and interests on neighboring countries. The research results can help us understand the current situation of the CCG and further evaluate China's ability to achieve maritime power. This paper finds that China intends to implement regular patrols in disputed waters by increasing the tonnage of coast guard ships, strengthening rights protection, and militarizing organizations to demonstrate maritime power. On the other hand, this move triggered a maritime police competition among neighboring countries, and even a naval and air force arms race, intensified disputes between China and neighboring countries, especially the East China Sea and South China Sea issues, and made the security of the Indo-Pacific region more turbulent and complicated.

Advancing Marine Surveillance: A Hybrid Approach of Physics Infused Neural Network for Enhanced Vessel Tracking Using Automatic Identification System Data

In the domain of maritime surveillance, the continuous tracking and monitoring of vessels are imperative for the early detection of potential threats. The Automatic Identification System (AIS) database, which collects vessel movement data over time, including timestamps and other motion details, plays a crucial role in real-time maritime monitoring. However, it frequently exhibits irregular intervals of data collection and intricate, intersecting trajectories, underscoring the importance of analyzing long-term temporal patterns for effective vessel tracking. While Kalman Filters and other physics-based models have been employed to tackle these issues, their effectiveness is limited by their inability to capture long-term dependence and non-linearity in the historical data. This paper introduces a novel approach that leverages Long Short-Term Memory (LSTM), a type of recurrent neural network, renowned for its proficiency in recognizing patterns over extended periods. Recognizing the strengths and limitations of the LSTM model, we propose a hybrid machine-learning algorithm that integrates LSTM with a physics-based model. This combination harnesses the physical laws governing vessel movements alongside data driven pattern mining, thereby enhancing the predictive accuracy of vessel locations. To assess the performance of standalone and hybrid models, various scenarios with different levels of complexity are generated. Furthermore, to simulate real-world data loss conditions often encountered in maritime tracking, temporal data gaps are randomly introduced into the scenarios. The competing approaches are then evaluated using both with time gap and without time gap conditions. Our results show that, although the LSTM model performs better than the physics-based model, the hybrid model consistently outperforms both standalone models across all scenarios. Furthermore, while data gaps negatively impact the accuracy of all models, the performance reduction is minimal for the physics-infused model. In summary, this study not only demonstrates the potential of combining data-driven and physics-based approaches but also sets a new benchmark for maritime vessel tracking.

Unveiling spatiotemporal distribution, partitioning, and transport mechanisms of tire additives and their transformation products in a highly urbanized estuarine region

Numerous tire additives are high-production volume chemicals that are used extensively worldwide. However, their presence and partitioning behavior remain largely unknown, particularly in marine environments. This study is the first to reveal the spatiotemporal distribution, multimedia partitioning, and transport processing of 22 tire additives and their transformation products (TATPs) in a highly urbanized estuary (n = 166). Nineteen, 18, and 20 TATPs were detectable in water, suspended particulate matter (SPM), and sediments, respectively, with total levels of 59.7–2021 ng/L, 164–6935 ng/g, and 4.66–58.4 ng/g, respectively. The multimedia partitioning mechanisms of TATPs are governed by their molecular weight, hydrophobicity, and biodegradation rate. Mass inventories coupled with model simulations have revealed that substantial quantities of TATPs accumulate within estuarine environments, and these compounds can be continuously transported into the ocean, particularly during the wet season. According to the multi-criteria evaluation approach, four and three TATPs were identified as high-priority pollutants during the dry and wet seasons, respectively. Unexpectedly, N-(1,3-dimethylbutyl)-N′-phenyl-p-phenylenediamine quinone was only listed as a medium-priority pollutant. This study underscores the importance of marine surveillance and advocates for particular attention to these ubiquitous but underexplored TATPs in future studies.

Self-Supervised Marine Noise Learning with Sparse Autoencoder Network for Generative Target Magnetic Anomaly Detection

As an effective physical field feature to perceive ferromagnetic targets, magnetic anomaly is widely used in covert marine surveillance tasks. However, its practical usability is affected by the complex marine magnetic noise interference, making robust magnetic anomaly detection (MAD) quite a challenging task. Recently, learning-based detectors have been widely studied for the discrimination of magnetic anomaly signal and achieve superior performance than traditional rule-based detectors. Nevertheless, learning-based detectors require abundant data for model parameter training, which are difficult to access in practical marine applications. In practice, target magnetic anomaly data are usually expensive to acquire, while rich marine magnetic noise data are readily available. Thus, there is an urgent need to develop effective models to learn discriminative features from the abundant marine magnetic noise data for newly appearing target anomaly detection. Motivated by this, in this paper we formulate MAD as a single-edge detection problem and develop a self-supervised marine noise learning approach for target anomaly classification. Specifically, a sparse autoencoder network is designed to model the marine noise and restore basis geomagnetic field from the collected noisy magnetic data. Subsequently, reconstruction error of the network is used as a statistical decision criterion to discriminate target magnetic anomaly from cluttered noise. Finally, we verify the effectiveness of the proposed approach on real sea trial data and compare it with seven state-of-the-art MAD methods on four numerical indexes. Experimental results indicate that it achieves a detection accuracy of 93.61% and has a running time of 21.06 s on the test dataset, showing superior MAD performance over its counterparts.

Comparative Legal Analysis of Maritime Technology Utilization in Indonesia and China

Managing maritime borders is a vital issue that needs special attention from coastal nations such as Indonesia and China. Both designed and deployed various systems to monitor marine activity as declared in UNCLOS 1982. The goal of this study is to give a comparison of marine surveillance technologies and to analyze the legality of their usage under international law. The research methods include literature review and analysis of material from official sources, scientific publications, and relevant reports. This study discovered that Indonesia has created an integrated maritime surveillance system based on satellite, radar, and Automatic Identification System (AIS) technologies. Besides that, China is deploying more advanced and extensive maritime surveillance and monitoring technologies, such as a modern fleet of patrol vessels, aircraft, and remote monitoring equipment. Indonesia and China have generally employed marine surveillance technologies in compliance with international law principles such as territorial sovereignty, freedom of navigation, and maritime law enforcement. However, there are indications of limits on access to information and potential privacy concerns that should primarily concern the Chinese. Stronger regional coordination and collaboration are required to guarantee that the deployment of marine surveillance technologies complies with international law and current maritime security concepts.

Underwater Wireless Sensor Networks (Review)

Underwater wireless sensor networks (UWSNs) are becoming increasingly popular among researchers due to their potential for real-world applications such as marine surveillance, sea monitoring, deep sea archaeology, oil monitoring, and more. With almost 70% of the earth’s surface covered in water, it is challenging for humans to gather valuable information from the seabed without advanced technology. In UWSNs, sensor nodes are placed to sense the underwater environment, and the data collected is sent to a sink node, which then transfers the data to a base station for processing. The deployment of sensor nodes in UWSNs is difficult due to the harsh underwater environment, and the routing of data is complicated by the nodes’ limited communication range and high energy consumption. This study provides a comprehensive overview of UWSNs, including their applications, deployment methods, and routing algorithms. A comparative analysis of deployment techniques and routing algorithms is presented to help researchers identify research gaps in these areas. The study also reviews some UWSN applications, which offer valuable insights into the approach. The study covers the conventional technologies used in UWSNs and highlights significant research approaches towards UWSNs’ applications, deployment techniques, and routing processes. The insights provided in this study will assist researchers in understanding the present state of UWSNs and identifying future research directions in this exciting field.

Artisanal fisher knowledge on the impacts of destructive and illegal practices on the Southern Coast of Bahia, Brazil

Destructive fishing practices (DFP) and illegal, unreported, and unregulated (IUU) activities result in significant marine ecosystem effects, such as habitat destruction, biomass reduction, bycatch, and waste of resources. They also generate socioeconomic impacts on artisanal fisher coastal populations. Both DFP and IUU are linked to fisheries management system failures and the impossibility of marine surveillance. In this context, from an Ethnoecological approach, the aim of this study was to analyze the local ecological knowledge of fishers from Ilhéus (Bahia), Northeastern Brazil, regarding DFP and IUU fisheries. A total of 59 interviewees pointed to decreased resource catches in recent years, citing increasing fishing efforts and certain types of gear as the main reasons. They also claim that local fishers and fishers from other Brazilian regions have been using banned equipment, such as compressors and lobster nets. In turn, although permitted by law, shrimp trawling and gillnet fishing were reported as being excessively applied and identified as destructive fisheries. Surprisingly, longline fishing was one of the most reported as responsible for excessive catches and for causing decreases in Common dolphinfish catches. This study reinforces the importance of including the knowledge of local fishers and their participation to contribute to fisheries management and resource conservation. In this context, some recommendations are highlighted to reduce the impacts of harmful practices and improve regional fisheries management, summarized as: (i) policy improvement; (ii) fishing monitoring; (iii) incentives; and (iv) enforcement.

PlasPi TDM: Augmentation of a low-cost camera platform for advanced underwater physical-ecological observations

Marine ecosystem dynamics in the context of climate change is a growing scientific, political and social concern requiring regular monitoring through appropriate observational technologies and studies. Thus, a wide range of tools comprising chemical, biogeochemical, physical, and biological sensors, as well as other platforms exists for marine monitoring. However, their high acquisition and maintenance costs are often a major obstacle, especially in low-income developing countries. We designed an advanced low-cost synoptic marine ecosystem observation system that operates at relatively high temporal frequencies, named PlasPi TDM. This instrument is an improved version of the camera system (PlasPI marine cameras) developed in 2020 by Autun Purser from the Alfred Wegener Institute Helmholtz Center for Polar and Marine Research (Germany), and collaborators. It incorporates several innovative developments such as multispectral (records the spectrum of any object photographed), temperature and pressure sensors. The PlasPi TDM operates to a depth of 200 m. The various field deployments demonstrate the operational capability of the PlasPi TDM for different applications and illustrate its considerable potential for in-situ observations and marine surveillance in Africa. This device is intended as an open-source project and its continued development is encouraged for a more integrated, sustainable and low-cost ocean observing system.

A transfer learning-based approach to maritime warships re-identification

Marine vessel re-identification technology is an important component of intelligent shipping systems and an important part of the visual perception tasks required for marine surveillance. However, unlike the situation on land, the maritime environment is complex and volatile, and ships are prone to different degrees of swaying. Warships, as a class of ships, are characterized by fewer image samples and high similarity, and it is more difficult to re-identify warships at sea. Therefore, this paper proposes a dynamic alignment re-identification network model incorporating transfer learning methods. Various types of ships are used as source domain data to assist the network in learning the target domain warships so as to improve the recognition accuracy of warships. At the same time, the swaying situation of warships at sea is simulated and tested to improve the recognition difficulty so as to cope with the impact caused by complex sea conditions. The effect of different types of ships as transfer objects is also discussed. The experimental results show that the improved algorithm improves the mean average accuracy (mAP) by 10.2% and the first hit rate (Rank1) by 4.9% on average.

A CNN-LSTM Architecture for Marine Vessel Track Association Using Automatic Identification System (AIS) Data.

In marine surveillance, distinguishing between normal and anomalous vessel movement patterns is critical for identifying potential threats in a timely manner. Once detected, it is important to monitor and track these vessels until a necessary intervention occurs. To achieve this, track association algorithms are used, which take sequential observations comprising the geological and motion parameters of the vessels and associate them with respective vessels. The spatial and temporal variations inherent in these sequential observations make the association task challenging for traditional multi-object tracking algorithms. Additionally, the presence of overlapping tracks and missing data can further complicate the trajectory tracking process. To address these challenges, in this study, we approach this tracking task as a multivariate time series problem and introduce a 1D CNN-LSTM architecture-based framework for track association. This special neural network architecture can capture the spatial patterns as well as the long-term temporal relations that exist among the sequential observations. During the training process, it learns and builds the trajectory for each of these underlying vessels. Once trained, the proposed framework takes the marine vessel's location and motion data collected through the automatic identification system (AIS) as input and returns the most likely vessel track as output in real-time. To evaluate the performance of our approach, we utilize an AIS dataset containing observations from 327 vessels traveling in a specific geographic region. We measure the performance of our proposed framework using standard performance metrics such as accuracy, precision, recall, and F1 score. When compared with other competitive neural network architectures, our approach demonstrates a superior tracking performance.

Aggregate Channel Features and Fast Regions CNN Approach for Classification of Ship and Iceberg

Detection and classification of icebergs and ships in synthetic aperture radar (SAR) images play a vital role in marine surveillance systems even though available adaptive threshold methods give satisfying results on detection and classification for ships and icebergs, including techniques of convolutional neural networks (CNNs), but need more accuracy and precision. An efficient and accurate method was developed to detect and classify the ship and icebergs. Hence, the research method proposed locating and classifying both ships and icebergs in a given SAR image with the help of deep learning (DL) and non-DL methods. A non-DL method utilized here was the aggregate channel features (ACF) detector, which extracts region proposals from huge SAR images. The DL object detector called fast regions CNN (FRCNN) detects objects accurately from the result of ACF since the ACF method avoids unwanted regions. The novelty of this study was that ACF-FRCNN concentrates only on accurately classifying ships and icebergs. The proposed ACF-FRCNN method gave a better performance in terms of loss (18.32%), accuracy (96.34%), recall (98.32%), precision (95.97%), and the F1 score (97.13%). Compared to other conventional methods, the combined effect of ACF and FRCNN increased the speed and quality of the detection of ships and icebergs. Thus, the ACF-FRCNN method is considered a novel method for over 75 × 75 resolution ship and iceberg SAR images.

A Marine Small-Targets Classification Algorithm Based on Improved Convolutional Neural Networks

Deep learning, especially convolutional neural network (CNN) techniques, has been shown to have superior performance in ship classification, as have small-target recognition studies in safety inspections of hydraulic structures such as ports and dams. High-resolution synthetic aperture radar (SAR)-based maritime ship classification plays an increasingly important role in marine surveillance, marine rescue, and maritime ship management. To improve ship classification accuracy and training efficiency, we proposed a CNN-based ship classification method. Firstly, the image characteristics of different ship structures and the materials of ship SAR images were analyzed. We then constructed a ship SAR image dataset and performed preprocessing operations such as averaging. Combined with a classic neural network structure, we created a new convolutional module, namely, the Inception-Residual Controller (IRC) module. A convolutional neural network was built based on the IRC module to extract image features and establish a ship classification model. Finally, we conducted simulation experiments for ship classification and analyzed the experimental results for comparison. The experimental results showed that the average accuracy of ship classification of the model in this paper reached 98.71%, which was approximately 3% more accurate than the traditional network model and approximately 1% more accurate compared with other recently improved models. The new module also performed well in evaluation metrics, such as the recall rate, with accurate classifications. The model could satisfactorily describe different ship types. Therefore, it could be applied to marine ship classification management with the possibility of being extended to hydraulic building target recognition tasks.

Improved Radar Detection of Small Drones Using Doppler Signal-to-Clutter Ratio (DSCR) Detector

The detection of drones using radar presents challenges due to their small radar cross-section (RCS) values, slow velocities, and low altitudes. Traditional signal-to-noise ratio (SNR) detectors often fail to detect weak radar signals from small drones, resulting in high “Missed Target” rates due to the dependence of SNR values on RCS and detection range. To overcome this issue, we propose the use of a Doppler signal-to-clutter ratio (DSCR) detector that can extract both amplitude and Doppler information from drone signals. Theoretical calculations suggest that the DSCR of a target is less dependent on the detection range than the SNR. Experimental results using a Ku-band pulsed-Doppler surface surveillance radar and an X-band marine surveillance radar demonstrate that the DSCR detector can effectively extract radar signals from small drones, even when the signals are similar to clutter levels. Compared to the SNR detector, the DSCR detector reduces missed target rates by utilizing a lower detection threshold. Our tests include quad-rotor, fixed-wing, and hybrid vertical take-off and landing (VTOL) drones, with mean SNR values comparable to the surrounding clutter but with DSCR values above 10 dB, significantly higher than the clutter. The simplicity and low radar requirements of the DSCR detector make it a promising solution for drone detection in radar engineering applications.

Unsupervised Maritime Vessel Re-Identification With Multi-Level Contrastive Learning

Re-identification (re-ID) of maritime vessels plays an important role in marine surveillance, but remains highly unexplored due to the lack of large-scale annotated datasets. In vessel re-ID, contrastive methods are supposed to learn discriminative representation from unlabeled vessel images in an unsupervised manner. However, directly introducing classical instance-level contrastive methods to maritime vessel re-ID suffers from the difficulty of finding vessel images with the same pseudo label as positive images, which potentially leads to inefficient training and unsatisfactory performance. This paper proposes a simple but effective method to solve such a hard positive problem. Our method takes all images in an intra-batch cluster as positives and excludes them from the set of negative samples when computing instance-level contrastive loss. Based on this strategy, we construct a multi-level contrastive learning (MCL) framework for vessel re-ID trained with the specifically designed intra-batch cluster-level contrastive loss along with the instance-level one. Experiments on a newly proposed dataset consisting of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$1,248$</tex-math> </inline-formula> vessel identities show that MCL achieves the state-of-the-art performance compared with other unsupervised methods.

YOLOv5s-CA: A Modified YOLOv5s Network with Coordinate Attention for Underwater Target Detection

Underwater target detection techniques have been extensively applied to underwater vehicles for marine surveillance, aquaculture, and rescue applications. However, due to complex underwater environments and insufficient training samples, the existing underwater target recognition algorithm accuracy is still unsatisfactory. A long-term effort is essential to improving underwater target detection accuracy. To achieve this goal, in this work, we propose a modified YOLOv5s network, called YOLOv5s-CA network, by embedding a Coordinate Attention (CA) module and a Squeeze-and-Excitation (SE) module, aiming to concentrate more computing power on the target to improve detection accuracy. Based on the existing YOLOv5s network, the number of bottlenecks in the first C3 module was increased from one to three to improve the performance of shallow feature extraction. The CA module was embedded into the C3 modules to improve the attention power focused on the target. The SE layer was added to the output of the C3 modules to strengthen model attention. Experiments on the data of the 2019 China Underwater Robot Competition were conducted, and the results demonstrate that the mean Average Precision (mAP) of the modified YOLOv5s network was increased by 2.4%.

Improved Ship Detection Algorithm from Satellite Images Using YOLOv7 and Graph Neural Network

One of the most critical issues that the marine surveillance system has to address is the accuracy of its ship detection. Since it is responsible for identifying potential pirate threats, it has to be able to perform its duties efficiently. In this paper, we present a novel deep learning approach that combines the capabilities of a Graph Neural Network (GNN) and a You Only Look Once (YOLOv7) deep learning framework. The main idea of this method is to provide a better understanding of the ship’s presence in harbor areas. The three hyperparameters that are used in the development of this system are the learning rate, batch sizes, and optimization selection. The results of the experiments show that the Adam optimization achieves a 93.4% success rate when compared to the previous generation of the YOLOv7 algorithm. The High-Resolution Satellite Image Dataset (HRSID), which is a high-resolution image of a synthetic aperture radar, was used for the test. This method can be further improved by taking into account the various kinds of neural network architecture that are commonly used in deep learning.

Satellite tracking and field assessment highlight major foraging site for green turtles in the Banc d'Arguin, Mauritania

There is a remarkable paucity of estimates of the numeric importance of sea turtles at foraging grounds. The Banc d'Arguin (BA) is a vast shallow marine area off the coast of Mauritania, known as a site of world importance for coastal migratory birds and other biodiversity, including extensive seagrass beds. We sampled foraging green turtles on the BA, and extensively tracked adult female green turtles from the Bijagós archipelago, the only significant nesting aggregation within 3000 km of the BA, to estimate the abundance of this foraging aggregation. Additionally, we used a demographic simulation to support our findings. Based on satellite tracking of adult females (n = 46), we estimate that 50 % of the nesting population from the Bijagós migrate to the BA post-nesting. We combine data on numbers nesting in the Bijagós with information on proportion migrating to the BA in the same years to conservatively estimate that 8285 adult female green turtles forage at this site. We also estimate that adult females represent only 5.6 % of the green turtles in the BA, implying that the number of turtles there is of the order of 150,000 individuals. Most of the BA enjoys effective protection as part of the Parc National du Banc d'Arguin where significant fisheries regulations are well enforced by a marine surveillance program. We show that the BA is one of the major foraging sites for green turtles nesting in the Bijagós and a site of critical importance for immature and adult green turtles in a global context.

Optimization of the Electrical System on the Hiu Macan 3 Surveillance Vessels in Support of Supervision in Eastern Indonesia

Hiu Macan 3 surveillance vessel is one of the Directorate General of Marine and Fisheries Resources Surveillance's supervisory vessels which plays an important role in marine surveillance in Eastern Indonesia. In support of monitoring activities, a reliable electrical system is needed and very careful maintenance methods are needed. To support these activities, a generator usage schedule is applied, either during operation or while leaning at the port. The main generator can be used to supply all the ship's electrical needs. The use of the main generator can be optimized to supply all the ship's electricity needs because the daily load percentage is still 33.79%, although this is still within the normal limits. If there is a problem with the main generator, a backup generator can be used, but only for lighting, navigation, and auxiliary engines. The maintenance schedule is required by performing daily, weekly, monthly, and overhaul maintenance. From the analysis carried out, the largest total daily electric power is 41.56 kVA and electrical energy is 310,676 kWh.