Search Results (27)

Conventional multi-object tracking approaches frequently exhibit performance degradation in marine radar (MR) imagery due to complex environmental challenges. To overcome these limitations, this paper proposes ShipMOT, an innovative multi-object tracking framework specifically engineered for robust maritime target tracking. The novel architecture features three principal innovations: (1) A dedicated CNN-based ship detector optimized for radar imaging characteristics; (2) A novel Nonlinear State Augmentation (NSA) filter that mathematically models ship motion patterns through nonlinear state space augmentation, achieving a 41.2% increase in trajectory prediction accuracy compared to conventional linear models; (3) A dual-criteria Bounding Box Similarity Index (BBSI) that integrates geometric shape correlation and centroid alignment metrics, demonstrating a 26.7% improvement in tracking stability under congested scenarios. For a comprehensive evaluation, a specialized benchmark dataset (Radar-Track) is constructed, containing 4816 annotated radar images with scenario diversity metrics, including non-uniform motion patterns (12.7% of total instances), high-density clusters (>15 objects/frame), and multi-node trajectory intersections. Experimental results demonstrate ShipMOT’s superior performance with state-of-the-art metrics of 79.01% HOTA and 88.58% MOTA, while maintaining real-time processing at 32.36 fps. Comparative analyses reveal significant advantages: 34.1% fewer ID switches than IoU-based methods and 28.9% lower positional drift compared to Kalman filter implementations. These advancements establish ShipMOT as a transformative solution for intelligent maritime surveillance systems, with demonstrated potential in ship traffic management and collision avoidance systems. Full article

The Yangtze River Basin serves as a vital ecological barrier in China, with its water conservation function playing a critical role in maintaining regional ecological balance and water resource security. This study takes the Minjiang River Basin (MRB) as a case study, employing fractal theory in combination with the InVEST model and the SWAT-BiLSTM model to conduct an in-depth analysis of the spatiotemporal patterns of regional water conservation. The research aims to uncover the relationship between the spatiotemporal dynamics of watershed water conservation capacity and its ecosystem service functions, providing a scientific basis for watershed ecological protection and management. Firstly, fractal theory is introduced to quantify the complexity and spatial heterogeneity of natural factors such as terrain, vegetation, and precipitation in the Minjiang River Basin. Using the InVEST model, the study evaluates the water conservation service functions of the research area, identifying key water conservation zones and their spatiotemporal variations. Additionally, the SWAT-BiLSTM model is employed to simulate the hydrological processes of the basin, particularly the impact of nonlinear meteorological variables on hydrological responses, aiming to enhance the accuracy and reliability of model predictions. At the annual scale, it achieved NSE and R² values of 0.85 during calibration and 0.90 during validation. At the seasonal scale, these values increased to 0.91 and 0.93, and at the monthly scale, reached 0.94 and 0.93. The model showed low errors (RMSE, RSR, RB). The findings indicate significant spatial differences in the water conservation capacity of the Minjiang River Basin, with the upper and middle mountainous regions serving as the primary water conservation areas, whereas the downstream plains exhibit relatively lower capacity. Precipitation, terrain slope, and vegetation cover are identified as the main natural factors affecting water conservation functions, with changes in vegetation cover having a notable regulatory effect on water conservation capacity. Fractal dimension analysis reveals a distinct spatial complexity in the ecosystem structure of the study area, which partially explains the geographical distribution characteristics of water conservation functions. Furthermore, simulation results based on the SWAT-BiLSTM model show an increasingly significant impact of climate change and human activities on the water conservation functions of the Minjiang River Basin. The frequent occurrence of extreme climate events, in particular, disrupts the hydrological processes of the basin, posing greater challenges for water resource management. Model validation demonstrates that the SWAT model integrated with BiLSTM achieves high accuracy in capturing complex hydrological processes, thereby better supporting decision-makers in formulating scientific water resource management strategies. Full article

Artificial island construction is a multifaceted engineering endeavor that demands precise scheduling to optimize resource allocation, control costs, ensure safety, and minimize environmental impact within dynamic marine environments. This study introduces a comprehensive multi-objective optimization model that integrates critical factors such as resource limitations, task dependencies, environmental variability, safety risks, and regulatory compliance. To effectively address the complexities of this model, we develop and employ the Multi-Objective Adaptive Cooperative Evolutionary Marine Genetic Algorithm (MACEMGA). MACEMGA combines cooperative coevolution, adaptive dynamic weighting, dynamic penalty functions, and advanced genetic operators to navigate the solution space efficiently and identify Pareto optimal schedules. Through extensive computational experiments using data from the Dalian Bay Cross-Sea Traffic Engineering project, MACEMGA is benchmarked against algorithms such as NSGA-II, SPEA2, and MOEA/D. The results demonstrate that MACEMGA achieves a reduction in construction time from 32.8 to 23.5 months and cost savings from CNY 4105.3 million to CNY 3650.0 million while maintaining high-quality outcomes and compliance with environmental standards. Additionally, MACEMGA shows improvements in hypervolume by up to 15% over existing methods and a Convergence Rate that is 8% faster than MOEA/D. Full article

The maritime industry is addressing environmental issues, and “cold ironing” offers a promising solution. This method involves supplying ships at port with energy, reducing fossil fuel dependence and emissions, and aiding in global climate change efforts. It is especially important for islands like Lesvos, which suffer from high energy costs and environmental issues due to imported fossil fuel reliance. However, research gaps exist in using renewable energy sources (RES) for cold ironing, mainly due to insufficient data on power needs and lack of monitoring for precise calculations and the very limited applications for the case of non-interconnected islands. This study uses real data from the port of Lesvos to evaluate power requirements for cold ironing and assesses the viability of a wind power park for an electrified port with the novelty and uniqueness of developing the application on a non-interconnected island. It also examines potential CO₂ emission reductions. Data from Marine Traffic S.A. were used, considering factors like ship arrivals, hoteling duration, and engine types. This study also includes a simulation using RETScreen software for a 20 MW wind park intended for port operations. The findings show that the monthly energy demand at Mytilene port is around 6118 MWh, with an average power demand of 8.2 MW. The simulated wind park could supply about 72,080 MWh yearly, with a significant surplus (14,956 MWh annually) exportable to the grid. However, demand fluctuations mean the port might need an extra 924 MWh from the main grid. This underscores the need for additional strategies like energy storage and demand–response practices to fully transition to 100% RES-powered operations. Full article

As marine traffic is contributing to pollution, and most vessels have predictable routes with repetitive load profiles, to reduce their impact on environment, hybrid systems with proton exchange membrane fuel cells (PEMFC-s) and battery pack are a promising replacement. For this purpose, the new approach takes into consideration an alternative to diesel propulsion with the additional benefit of carbon neutrality and increase of system efficiency. Additionally, in the developed numerical model, control of the PEMFC–battery hybrid energy system with balance of plant is incorporated with repowering existing vessels that have two diesel engines with 300 kWe. The goal of this paper is to develop a numerical model that analyzes and determines an equivalent hybrid ship propulsion system for a known traveling route. The developed numerical model consists of an interconnected system with the PEMFC stack and a battery pack as power sources. The numerical model was developed and optimized to meet the minimal required power demand for a successful route, which has variable loads and sees ships sail daily six times along the same route—in total 54 nautical miles. The results showed that the equivalent hybrid power system consists of a 300 kWe PEMFC stack and battery pack with 424 kWh battery and state of charge varying between 20 and 87%. To power this new hybrid power system, a hydrogen tank of 7200 L holding 284.7 kg at pressure of 700 bar is required, compared to previous system that consumed 1524 kg of diesel and generated 4886 kg of CO₂. Full article

This article takes a close look at the landscape of global navigation satellite system (GNSS) spoofing. It is well known that automated identification system (AIS) spoofing can be used for electronic warfare to conceal military activities in sensitive sea areas; however, recent events suggest that there is a similar interest of spoofing AIS signals for commercial purposes. The shipping industry is currently experiencing an unprecedented period of deceptive practices by tanker operators seeking to evade sanctions. Last year’s announcement of a price cap on Russian crude oil and a new ban on Western companies insuring Russian cargoes is setting the stage for an increase in illegal activity. Our research team identified and documented the AIS position falsification by tankers transporting Russian crude oil in closed ship-to-ship (STS) oil transfers. The identification of the falsified positions is based on the repeated instances of discrepancies between AIS location suggestions and satellite radar imagery indications. Using the data methods at our disposal, we reconstructed the true movements of certain tankers and encountered some surprising behavior. These false ship positions make it clear that we need effective tools and strategies to ensure the reliability and robustness of AISs. Full article

Smart microgrids are being increasingly deployed within the Department of Defense. The microgrid at Marine Corps Air Station (MCAS) Miramar is one such deployment that has fostered the integration of different technologies, including 5G and Advanced Metering Infrastructure (AMI). The objective of this paper is to develop an anomaly detection framework for the smart microgrid system at MCAS Miramar to enhance its cyber-resilience. We implement predictive analytics using machine learning to deal with cyber-uncertainties and threats within the microgrid environment. An autoencoder neural network is implemented to classify and identify specific cyber-attacks against this infrastructure. Both network traffic in the form of packet captures (PCAP) and time series data (from the AMI sensors) are considered. We train the autoencoder model on three traffic data sets: (1) Modbus TCP/IP PCAP data from the hardwired network apparatus of the smart microgrid, (2) experimentally generated 5G PCAP data that mimic traffic on the smart microgrid and (3) AMI smart meter sensor data provided by the Naval Facilities (NAVFAC) Engineering Systems Command. Distributed denial-of-service (DDoS) and false data injection attacks (FDIA) are synthetically generated. We show the effectiveness of the autoencoder on detecting and classifying these types of attacks in terms of accuracy, precision, recall, and F-scores. Full article

To effectively improve the water quality of the Bai River, this paper proposes the use of the ecological replenishment of the South–North Water Transfer as a measure for the integrated allocation of water resources, addressing the impact of complex topography, climate, and human disturbances on the river’s water environment. This measure can alleviate the problem of water shortage and significantly enhance the quality of the Bai River’s water environment. Using the MIKE21 coupled hydrodynamic and water-quality model, this paper analyzes the impact of ecological recharge on river hydrodynamics and simulates the evolution of various water-quality indicators, including dissolved oxygen (DO), permanganate index (COD_Mn), chemical oxygen demand (COD), ammonia nitrogen (NH₃-N), and total phosphorus (TP) under different scenarios. The aim of this paper is to investigate the impact mechanism of ecological recharge on the river’s water environment. The results show that the most significant improvement in river water quality is achieved when the recharge flow is 2Q and the recharge duration is 1/2T (scenario 1), with the river improving from a grade IV water-quality standard to a grade III water-quality standard, and COD and TP indicators improving to a grade II water standard, with the largest improvement rate of 94.67% seen in DO, with the best improvement rate of 94.67% in DO indicators and the best reduction rate of 66.67% in TP indicators. Overall, ecological replenishment can significantly improve the Bai River’s water quality, with scenario 1 being the most effective approach. The results of this study may provide theoretical and technical support for the future management of river water environments. Full article

While many current and potential uses of the Israeli Mediterranean Sea have clearly defined the economic value and apparent benefits to various stakeholders (e.g., energy and raw materials extraction and maritime traffic), the benefits of these local marine ecosystems are still severely underexplored and are not manifested in economic terms. Coupled with ongoing environmental deterioration such as overfishing, climate change, and biological invasion, the need for performing monetary valuations of the benefits derived from this ecosystem is clearly evident. In this study, we evaluated three marine and coastal ecosystem services, namely, food provisioning, wastewater treatment, and coastal protection, in order to better quantify and map their importance to society. Food provisioning was inspected through the fishing sector, and its benefits were analyzed using the bioeconomic model. The results recommend a reduction in fishing efforts to increase overall biomass levels of both local and invasive fish species. However, this may lead to an economic loss in fishery profits due to reduced catch levels. The economic valuation of wastewater treatment as an ecosystem service hint at possible thresholds governed by effluent volumes and environmental conditions, whereby exceedance of Good Environmental Status (GES) standards may lead to a reduction of ~25% in the potential benefit of this ecosystem service. Finally, this study proposes an engineering restoration solution for compromised intertidal abrasion platforms, with estimated costs and potential benefits for the conservation of at-risk areas. The annual economic value of this ecosystem service is NIS 65–209 million (EUR 16.2–52.2 million). Full article

Precipitation prediction is an important technical mean for flood and drought disaster early warning, rational utilization, and the development of water resources. Complementary ensemble empirical mode decomposition (CEEMD) can effectively reduce mode aliasing and white noise interference; extreme learning machines (ELM) can predict non-stationary data quickly and easily; and the fruit fly optimization algorithm (FFOA) has better local optimization ability. According to the multi-scale and non-stationary characteristics of precipitation time series, a new prediction approach based on the combination of complementary ensemble empirical mode decomposition (CEEMD), extreme learning machine (ELM), and the fruit fly optimization algorithm (FFOA) is proposed. The monthly precipitation data measured in Zhengzhou City from 1951 to 2020 was taken as an example to conduct a prediction experiment and compared with three prediction models: ELM, EMD-HHT, and CEEMD-ELM. The research results show that the sum of annual precipitation predicted by the CEEMD-ELM-FFOA model is 577.33 mm, which is higher than the measured value of 572.53 mm with an error of 4.80 mm. The average absolute error is 0.81 and the average relative error is 1.39%. The prediction value of the CEEMD-ELM-FFOA model can closely follow the changing trend of precipitation, which shows a better prediction effect than the other three models and can be used for regional precipitation prediction. Full article

The Xiaolangdi Reservoir is the second largest water conservancy project in China and the last comprehensive water conservancy hub on the mainstream of the Yellow River, playing a vital role in the middle and lower reaches of the Yellow River. To study the effects of the construction of the Xiaolangdi Reservoir (1997–2001) on the runoff and sediment transport in the middle and lower reaches of the Yellow River, runoff and sediment transport data from 1963 to 2021 were based on the hydrological stations of Huayuankou, Gaocun, and Lijin. The unevenness coefficient, cumulative distance level method, Mann-Kendall test method, and wavelet transform method were used to analyze the runoff and sediment transport in the middle and lower reaches of the Yellow River at different time scales. The results of the study reveal that the completion of the Xiaolangdi Reservoir in the interannual range has little impact on the runoff in the middle and lower reaches of the Yellow River and a significant impact on sediment transport. The interannual runoff volumes of Huayuankou station, Gaocun station, and Lijin station were reduced by 20.1%, 20.39%, and 32.87%, respectively. In addition, the sediment transport volumes decreased by 90.03%, 85.34%, and 83.88%, respectively. It has a great influence on the monthly distribution of annual runoff. The annual runoff distribution is more uniform, increasing the runoff in the dry season, reducing the runoff in the wet season, and bringing forward the peak flow. The runoff and Sediment transport have obvious periodicity. After the operation of the Xiaolangdi Reservoir, the main cycle of runoff increases and the second main cycle disappears. The main cycle of Sediment transport did not change obviously, but the closer it was to the estuary, the less obvious the cycle was. The research results can provide a reference for ecological protection and high-quality development in the middle and lower reaches of the Yellow River. Full article

Emissions of marine traffic can be lowered by switching to less polluting fuels or by investing in exhaust aftertreatment. Electrostatic precipitation is a widely used method for particle removal but it is not currently used in combination with marine engines. This study presents the particle filtration characteristics of an emission reduction system designed for marine applications and consisting of a scrubber and a Wet Electrostatic Precipitator (WESP) in series. Partial flow of exhaust from a 1.6 MW marine engine, operated with light and heavy fuel oil, was led to the system. Particle concentrations were measured before the system, after the scrubber and after the WESP. Particle removal characteristics were determined for different engine loads. The scrubber alone removed 15–55% of non-volatile particle number, 30–40% of particle mass and 30–40% of black carbon mass depending on engine load, when HFO fuel was used. By studying particle size distributions, scrubber was found also to generate particles seen as an additional mode in 20–40 nm size range. The system combining the scrubber and WESP removed over 98.5% of particles in number, mass and black carbon metrics when HFO fuel was used. With MDO fuel, 96.5% of PN and 99% of black carbon were removed. Full article

Due to the increasing number of transportation vessels, marine traffic has become more congested. According to the statistics, 89% to 95% of maritime accidents are related to human factors. In order to reduce marine incidents, ship automatic collision avoidance has become one of the most important research issues in the field of ocean engineering. A generalized behavior decision-making (GBDM) model, trained via a reinforcement learning (RL) algorithm, is proposed in this paper, and it can be used for ship autonomous driving in multi-ship encounter situations. Firstly, the obstacle zone by target (OZT) is used to calculate the area of future collisions based on the dynamic information of ships. Meanwhile, a virtual sensor called a grid sensor is taken as the input of the observation state. Then, International Regulations for Preventing Collision at Sea (COLREGs) is introduced into the reward function to make the decision-making fully comply with COLREGs. Different from the previous RL-based collision avoidance model, the interaction between the ship and the environment only works in the collision avoidance decision-making stage. Finally, 60 complex multi-ship encounter scenarios clustered by the COLREGs are taken as the ship’s GBDM model training environments. The simulation results show that the proposed GBDM model and training method has flexible scalability in solving the multi-ship collision avoidance problem complying with COLREGs in different scenarios. Full article

One of the components necessary to determine the width of a safe maneuvering area on two-way fairways is a safe passing distance. Existing methods do not consider modern model studies of interactions between passing vessels, additionally, they ignore the influence of the vessel’s position accuracy and navigators’ qualifications. This paper presents a method to determine the passing distance, which is free of the drawbacks of the methods used so far. The proposed method is based on simulation research carried out using an FMBS-type (Full Mission Bridge) simulator. The tests were carried out for three loaded vessels (bulk carrier, tanker, and sea ferry), on four sections of the fairway with different parameters and aids-to-navigation available. The results obtained allowed the modification of the authors’ previous, but still widely used, deterministic–probabilistic MTE (Marine Traffic Engineering) method for determining the width of a safe maneuvering area. Full article