Ship Traffic Research Articles

Accuracy and applicability of ship's fuel consumption prediction models: A comprehensive comparative analysis

The available extensive ship activity data enables employing a complex data-driven resistance-based power model to estimate ship's instantaneous power, and thus the ship's fuel consumption. The Ship Traffic Emissions Assessment Model emerges as a prominent example of such models. However, the performance of the Ship Traffic Emissions Assessment Model in ship's fuel consumption estimation is rarely verified by real fuel consumption data. Hence, this study aims to validate the accuracy of the Ship Traffic Emissions Assessment Model using real fuel consumption data and evaluates its applicability in terms of input features. Situations where the Ship Traffic Emissions Assessment Model shows large errors are identified to analyze its applicability. Furthermore, the Ship Traffic Emissions Assessment Model is compared with other popular fuel consumption prediction models, including the propeller law, the gradient-boosted regression tree model, and two grey box models. A systematical analysis is conducted to evaluate the applicability of various fuel consumption prediction models in different sailing scenarios, providing insights in selecting appropriate models for accurate ship's fuel consumption estimation. The findings contribute to optimizing the ship energy efficiency and facilitating the transition to alternative energy options, ultimately leading to a reduction in greenhouse gas emissions of the maritime industry.

The Spatiotemporal Pattern Evolution Characteristics of Ship Traffic on the Arctic Northeast Passage Based on AIS Data

Warming weather has led to melting sea ice, and increasingly complex global geopolitics has drawn more countries’ attention to the Arctic. The Arctic Northeast Passage, as an emerging route connecting Eurasia, has seen a sharp increase in vessel activity. The period from 2015 to 2020, being a stable and undisturbed data period, is of significant theoretical importance for exploring the natural development of the Arctic Northeast Passage. The study found that the research period can be divided into three stages: from 2015 to 2017, the number of vessels grew slowly. In 2018 and 2019, the number of vessels and vessel activities saw significant growth, but an unexpected reverse growth occurred in 2020. Different types of vessels have unique activity characteristics and evolutionary patterns, influenced by the Arctic’s unique geographical environment, abundant natural resources, deepening Sino-Russian cooperation, and increasing global trade supply and demand. The results of this study aim to provide policymakers with analysis based on the initial development stage of the route, offering data support for future policy formulation, route planning, and research on the navigation safety of vessels on the Arctic Northeast Passage.

Comparing modelled and measured exhaust gas components from two LNG-powered ships

Bottom-up modelling is used frequently to estimate emissions produced by seagoing vessels, and the accuracy of modelling is dependent on the data the model is trained with. Observational studies can be used to increase the model accuracy. Here we compared data from two measuring campaigns conducted on board ships that use Liquefied Natural Gas (LNG) as primary fuel in internal combustion engines (ICE) in a diesel-electric setup with values obtained from the Ship Traffic Emission Assessment Model (STEAM).The power demand for propulsion calculated using Automatic Identification System (AIS) data matched observations reasonably. The root mean square error between the modelled and observed power demand was 759–914 kW (28.6–34.5%) for the measured ropax vessel and 1869–1916 kW (16.7–17.1%) for the large cruise vessel over four voyages while the ships were underway. The discrepancy is largely explained by the auxiliary power demand, which was 4 times higher on the large cruise vessel than the model prediction.Using meteorological data to estimate the increase of resistance did not improve the goodness of fit between modelled and observed engine power demand. STEAM model's base-specific fuel consumption calculation method fits observed values reasonably when the engine load is over 50%, but ICEs used in constant speed mode have increased consumption at lower engine loads compared to variable speed ICEs.The share of pilot fuel of total energy consumption was found to play a significant role in the emission factors for measured exhaust gas compounds. More accurate functions to model fuel consumption and emissions were derived using the observed data.

Methodology for Predicting Maritime Traffic Ship Emissions Using Automatic Identification System Data

This paper develops a methodology to estimate ship emissions using Automatic Identification System data (AIS). The methodology includes methods for AIS message decoding and ship emission estimation based on the ship’s technical and operational characteristics. A novel approach for ship type identification based on the visited port terminal is described. The methodology is implemented in a computational tool, SEA (Ship Emission Assessment). First, the accuracy of the method for ship type identification is assessed and then the methodology is validated by comparing its predictions with those of two other methodologies. The tool is applied to three case studies using AIS data of maritime traffic along the Portuguese coast and in the port of Lisbon for one month. The first case study compares the estimated emissions of a ferry and a cruise ship, with the ferry emitting much less than the cruise ship. The second case study estimates the geographical distribution of emissions in the port of Lisbon, with terminals corresponding to areas with a heavier concentration of exhaust emissions. The third case study focuses on the emissions from a container ship sailing along the continental coast of Portugal, differing considerably from port traffic since it operates exclusively in cruising mode.

Modeled underwater sound levels in the Pan-Arctic due to increased shipping: Analysis from 2013 to 2019.

The loss of Arctic sea ice is one of the most visible signs of global climate change. As Arctic sea ice has retreated, Arctic marine shipping has increased. The Pan-Arctic's unique underwater acoustic properties mean that even small increases in ship traffic can have a significant effect on the ambient soundscape. This study presents the first long-term, basin-scale model of shipping noise in the Pan-Arctic with a focus on a few select sub-regions. The Arctic Ship Traffic Database from the Protection of the Arctic Marine Environment is used in this study to model the locations and source levels from ships operating in the Pan-Arctic between 2013 and 2019. The acoustic footprint of these ships is explored temporally for the entire basin as well as for the select large maritime ecosystems of the Barents Sea, the Northern Bering-Chukchi Sea, and Baffin Bay. From 2013 to 2019, modeled shipping noise propagating underwater broadly increased between 5-20 dB across the Pan-Arctic, but more specific results in sub-regions are presented and discussed.

Research on Ship Traffic Flow Prediction Using CNN-BIGRU and WOA With Multi-Objective Optimization

Research on Ship Traffic Flow Prediction Using CNN-BIGRU and WOA With Multi-Objective Optimization

Interactions Between Lightning and Ship Traffic

AbstractIt is important to understand connections between society and the natural environment for anticipating hazards and anthropogenic effects on the Earth system. In this study, we conduct a detailed exploration of interactions between oceanic thunderstorms and maritime traffic. Shipping traffic produces aerosols that perturb the otherwise “clean” ocean environment. Prior work proposed these aerosol effects as the cause of increased lightning over certain shipping lanes. However, introducing tall grounded objects into a high electric field environment might also facilitate lightning discharges, as we see with upward lightning over land. We consider both possibilities. Our analyses of the thunderstorms responsible for enhanced lightning activity over the shipping lane with the clearest anthropogenic signal indicate that the enhancement results from an increased frequency of lightning‐producing storms. Observed variations in thunderstorm microphysics between the shipping lane and nearby oceans are small compared to natural factors such as the Indian monsoon, and are on the same scale as the local variability in the data. By contrast, matching lightning stroke data with ship transponder events in oceanic regions where public data are available reveals a strong signal from direct ship interactions. Lightning is 15× (66×) more likely to occur at a ship location compared to 2 km (25 km) away. These results highlight the central role of direct ship interactions in explaining lightning enhancements over shipping lanes. We also document the frequency of these direct lightning interactions across various categories of vessels and on individual ships present in the public data.

Ship Detection under Low-Visibility Weather Interference via an Ensemble Generative Adversarial Network

Maritime ship detection plays a crucial role in smart ships and intelligent transportation systems. However, adverse maritime weather conditions, such as rain streak and fog, can significantly impair the performance of visual systems for maritime traffic. These factors constrain the performance of traffic monitoring systems and ship-detection algorithms for autonomous ship navigation, affecting maritime safety. The paper proposes an approach to resolve the problem by visually removing rain streaks and fog from images, achieving an integrated framework for accurate ship detection. Firstly, the paper employs an attention generation network within an adversarial neural network to focus on the distorted regions of the degraded images. The paper also utilizes a contextual encoder to infer contextual information within the distorted regions, enhancing the credibility of image restoration. Secondly, a weighted bidirectional feature pyramid network (BiFPN) is introduced to achieve rapid multi-scale feature fusion, enhancing the accuracy of maritime ship detection. The proposed GYB framework was validated using the SeaShip dataset. The experimental results show that the proposed framework achieves an average accuracy of 96.3%, a recall of 95.35%, and a harmonic mean of 95.85% in detecting maritime traffic ships under rain-streak and foggy-weather conditions. Moreover, the framework outperforms state-of-the-art ship detection methods in such challenging weather scenarios.

Evaluation of ship emission intensity and the inaccuracy of exhaust emission estimation model

Atmospheric pollution from maritime traffic is rising sharply and has brought great challenges to maritime management. The purpose of the study aims to establish a reliable approach to estimate the number of pollutants emitted by ships. The temporal, spatial and voluminal emission intensity of CO2, NOX, CO, NMVOC, PM2.5 and SO2 are investigated using the Ship Traffic Emission Assessment Model. Then, the inaccuracy of the Ship Traffic Emission Assessment Model is evaluated by calculating the emission fluctuations at switch points between different operation modes. The results revealed that ship speed could significantly affect the temporal, spatial and voluminal emission intensities of ships. Compared to temporal and voluminal emission, the intensity of spatial emission increases dramatically when the speed is close to 0. In addition, it was also shown that the Ship Traffic Emission Assessment Model induces an inaccuracy whenever the ship changes the operation mode. The research results provide guidance to plan the operation and management strategies to reduce pollutants from ships.

Trajectory planning for unmanned surface vehicles in multi-ship encounter situations

Unmanned surface vehicles (USVs) can encounter traffic ships while navigating toward the target location. For the USVs, collision avoidance (CA) trajectories need to be planned according to the international regulations for preventing collisions at sea (COLREGS). A novel trajectory planning approach is proposed for the collision-free trajectories planning of USVs in the case of multiship encounters. Unlike the existing trajectory planning approaches, the proposed approach uses the holistic thinking to simplify the analysis of encounter situations. Ships approaching from all sides of the USV are treated as one or two equivalent obstacles based on consistent offset velocity direction (COVD) method. Furthermore, planned velocity is designed using the proposed CA strategy and kinematic constraints. This strategy is compliant with COLREGS and includes an emergency CA module to further ensure a safe distance between the USV and traffic ships. The performance of the proposed trajectory planning approach is verified through physical simulations using an existing simulator. The simulation results show that the proposed trajectory planning approach can implement multiple USVs to simultaneously avoid collisions and reach their respective target positions. Moreover, the approach remains effective when other USVs do not follow the COLREGS protocols.

Research on Multi-Port Ship Traffic Prediction Method Based on Spatiotemporal Graph Neural Networks

The intelligent maritime transportation system has emerged as a pivotal component in port management, owing to the rapid advancements in artificial intelligence and big data technology. Its essence lies in the application of digital modeling techniques, which leverage extensive ship data to facilitate efficient operations. In this regard, effective modeling and accurate prediction of the fluctuation patterns of ship traffic in multiple port regions will provide data support for trade analysis, port construction planning, and traffic safety management. In order to better express the potential interdependencies between ports, inspired by graph neural networks, this paper proposes a data-driven approach to construct a multi-port network and designs a spatiotemporal graph neural network model. The model incorporates graph attention networks and a dilated causal convolutional architecture to capture the temporal and spatial dimensions of traffic variation patterns. It also employs a gated-mechanism-based spatiotemporal bi-dimensional feature fusion strategy to handle the potential unequal relationships between the two dimensions of features. Compared to existing methods for port traffic prediction, this model fully considers the network characteristics of the overall port and fills the research gap in multi-port scenarios. In the experiments, real port ship traffic datasets were constructed using data from the Automatic Identification System (AIS) and port geographical information data for model validation. The results demonstrate that the model exhibits outstanding robustness and performs well in predicting traffic in multiple sub-regional port clusters.

Analyzing the Relationship between Cargo Throughput and Total Ship Traffic in Lagos, Lomé, and Tema Seaports using TOMS: A Comparative Study

Analyzing the Relationship between Cargo Throughput and Total Ship Traffic in Lagos, Lomé, and Tema Seaports using TOMS: A Comparative Study

Prediction of Ship Traffic Flow and Congestion Based on Extreme Learning Machine with Whale Optimization Algorithm and Fuzzy c-Means Clustering

Accurately predicting short-term congestions in ship traffic flow is important for water traffic safety and intelligent shipping. We propose a method for predicting the traffic flow of ships by applying the whale optimization algorithm to an extreme learning machine. The method considers external environmental uncertainty and complexity of ships navigating in traffic-intensive waters. First, the parameters of ship traffic flow are divided into multiple modal components using variational mode decomposition and extreme learning machine. The machine and the whale optimization algorithm constitute a hybrid modelling approach for predicting individual modal components and integrating the results of individual components. Considering a map between ship traffic flow parameters and congestion, fuzzy c-means clustering is used to predict the level of ship traffic congestion. To verify the effectiveness of the proposed method, ship traffic flow data of the Yangtze River estuary were selected for evaluation. Results from the proposed method for predicting ship traffic flow parameters are consistent with measurements. Specifically, the prediction accuracy of the ship traffic congestion reaches 76.04%, which is reasonable and practical for predicting ship traffic congestion.

Modeling Sediment Resuspension and Transport Processes Induced by Propeller Wash from Ship Traffic

Resuspension and redistribution of sediments induced by propeller wash may significantly influence aquatic ecosystems at contaminated sediment sites. This study describes a numerical modeling method developed to predict the sediment resuspension and subsequent transport processes resulting from ship traffic, with a fully coupled simulation of hydrodynamics, sediment transport, and propeller wash. By including propeller momentum effects in the flow field computation, the advection and dispersion of resuspended sediments are better represented than in previously available methods. To achieve this improvement, a computational algorithm was first developed to calculate the propeller wash effects from one or more ships (e.g., erosion rate and momentum flux); these results were then dynamically linked to a hydrodynamic and sediment transport computation using Environmental Fluid Dynamics Code Plus (EFDC+). This modeling framework was evaluated using a field experiment conducted by the US Navy. The model was calibrated with flow velocities and sediment erosion depths, and then validated with resuspended sediment concentrations in the water column. The model results reproduced the horizontal and vertical distributions of resuspended sediments better when the propeller-induced momentum was incorporated into the flow field computation. The sensitivity test indicated that the increased flow energy from propeller momentum resulted in significant dispersion of resuspended sediments in both longitudinal and lateral directions. The maximum scour was dependent on the propeller revolution speed, the ship engine power, and the distance between the propellers and the sediment bed.

Cumulative environmental risk assessment of metals and polycyclic aromatic hydrocarbons from ship activities in ports

Marine environmental risk assessments rarely consider the cumulative risk from multiple contaminants and sources. Ships give rise to a range of contaminants, originating from different onboard sources, resulting in contaminant loads to the marine environment. Here, the Ship Traffic Emission Assessment Model (STEAM), in combination with the hydrodynamic and chemical fate model MAMPEC, was used to calculate loads and predicted environmental concentrations (PECs) of metals and polycyclic aromatic hydrocarbons, in four ports. PECs were compared to the predicted no effect concentrations (PNEC) to assess environmental risk from the different onboard sources, both separately and cumulatively. The results show that three out of four ports were subject to unacceptable risk. This study highlights the importance of accounting for multiple contaminant sources when assessing the marine environmental risks of shipping and challenges the suitability of the proposed new international guidelines on how to assess risk of scrubber water discharge.

Potential impact of shipping on air pollution in the Mediterranean region – a multimodel evaluation: comparison of photooxidants NO2 and O3

Abstract. Shipping has a significant share in the emissions of air pollutants such as NOx and particulate matter (PM), and the global maritime transport volumes are projected to increase further in the future. The major route for short sea shipping within Europe and the main shipping route between Europe and East Asia are found in the Mediterranean Sea. Thus, it is a highly frequented shipping area, and high levels of air pollutants with significant potential impacts from shipping emissions are observed at monitoring stations in many cities along the Mediterranean coast. The present study is part of the EU H2020 project SCIPPER (Shipping contribution to Inland Pollution Push for the Enforcement of Regulations). Five different regional chemistry transport models (CAMx – Comprehensive Air Quality Model with Extensions, CHIMERE, CMAQ, EMEP – European Monitoring and Evaluation Programme, LOTOS-EUROS) were used to simulate the transport, chemical transformation and fate of atmospheric pollutants in the Mediterranean Sea for 2015. Shipping emissions were calculated with the Ship Traffic Emission Assessment Model (STEAM) version 3.3.0, and land-based emissions were taken from the CAMS-REG v2.2.1 dataset for a domain covering the Mediterranean Sea at a resolution of 12 km × 12 km (or 0.1∘×0.1∘). All models used their standard setup for further input. The potential impact of ships was calculated with the zero-out method. The model results were compared to each other and to measured background data at monitoring stations. The model results differ regarding the time series and pattern but are similar concerning the overall underestimation of NO2 and overestimation of O3. The potential impact from ships on the total NO2 concentration was especially high on the main shipping routes and in coastal regions (25 % to 85 %). The potential impact from ships on the total O3 concentration was lowest in regions with the highest NO2 impact (down to −20%). CAMx and CHIMERE simulated the highest potential impacts of ships on the NO2 and O3 air concentrations. Additionally, the strongest correlation was found between CAMx and CHIMERE, which can be traced back to the use of the same meteorological input data. The other models used different meteorological input due to their standard setup. The CMAQ-, EMEP- and LOTOS-EUROS-simulated values were within one range for the NO2 and O3 air concentrations. Regarding simulated deposition, larger differences between the models were found when compared to air concentration. These uncertainties and deviations between models are caused by deposition mechanisms, which are unique within each model. A reliable output from models simulating ships' potential impacts can be expected for air concentrations of NO2 and O3.

Modern Approach to Data Collection and Processing from Automatic Identification System for Ship Traffic Organization

The article is devoted to the collection and generalization of automatic identification system (AIS) data on the movement of ships, both on inland waterways and in coastal marine areas. The list of information necessary for the further carrying out of researches on the organization of movement is defined. Attention is paid to the peculiarities of obtaining data from technical means of communication and open online resources. The approach to statistical data accumulation from AIS receiver using Raspberry Pi single-board microcomputer has been offered. The application, which reads data from the serial port and transfers them to the library and then to the PostgreSQL database management system server, is implemented. It is concluded that the proposed approach is constructive and potentially effective.

A Prediction Method of Ship Traffic Accidents Based on Grey GM(1,1) Model

In order to improve the inaccuracy of the GM(1,1) model in the prediction of ship traffic accidents caused by large data fluctuations, a weighted average weakening buffer operator is applied to the GM(1,1) residual error correction model to improve the prediction accuracy. This method is based on the modeling principle of the GM(1,1) residual error correction model. Firstly, GM(1,1) model is established based on the original data sequence to obtain the simulated value, predicted value, and residual tail sequence. Then, the residual tail sequence of the oscillation fluctuation is processed by positive value and weighted average weakening buffer operator, so as to establish the residual GM(1,1) model and correct the original prediction value with the residual prediction value; Finally, this method is applied to the prediction of British merchant shipping traffic accidents to verify its effectiveness. The results show that this method has high prediction accuracy in the short-term prediction of ship traffic accidents.

Cetacean Mortality Related to Ship Traffic in the Mexican Central Pacific

Cetacean Mortality Related to Ship Traffic in the Mexican Central Pacific

Implementation of African Satellite Augmentation System (ASAS) for Maritime Applications

This paper introduces implementation of the new project known as African Satellite Augmentation System (ASAS) for Africa and Middle East, designed by the CNS Systems Company and its research group supported by partners. The ASAS project as Regional Satellite Augmentation Systems (RSAS) will provide service for maritime, land (road and rail), and aeronautical applications. Thus, with existing and other newly designed RSAS networks, it will be integrated in Global Satellite Augmentation System (GSAS) with new Satellite Communication, Navigation and Surveillance (CNS) for improved Ship Traffic Control (STC) and Ship Traffic Management (STM). This System also enhances safety and emergency systems, transport security and control of ocean shipping freight, logistics and the security of the crew and passengers onboard ships and fishing vessels as well. The current CNS infrastructures of the first generation of Global Navigation Satellite System (GNSS-1) applications are represented by old fundamental solutions for Position, Velocity, and Time (PVT) of the satellite navigation and determination systems, such as the US GPS and Russian (former USSR) GLONASS military requirements, respectively. The establishment of Space, Ground, and User segment, including Local Satellite Augmentation System (LSAS), are discussed as a new basic infrastructures for maritime and other mobile applications, which will be integrated with RSAS in the future GSAS network.