Satellite imagery has become a fundamental part for maritime monitoring and safety. Correctly estimating a ship's identity is a vital tool. We present a method based on facial recognition for identifying ships in satellite images. A large ship dataset is constructed from Sentinel-2 multispectral images and annotated by matching to the Automatic Identification System. Our dataset contains 7.000 unique ships, for which a total of 16.000 images are acquired. The method uses a convolutional neural network to extract a feature vector from the ship images and embed it on a hypersphere. Distances between ships can then be calculated via the embedding vectors. The network is trained using a triplet loss function, such that minimum distances are achieved for identical ships and maximum distances to different ships. Comparing a ship image to a reference set of ship images yields a set of distances. Ranking the distances provides a list of the most similar ships. The method correctly identifies a ship on average 60 % of the time as the first in the list. Larger ships are easier to identify than small ships, where the image resolution is a limitation.
Each year maritime accidents occur at sea causing human casualties. Training facilities serve to reduce the risk of human error by allowing maritime teams to train safety procedures in cooperative real-size immersive simulators. However, they are expensive and only few maritime professionals have access to such simulators. Virtual Reality (VR) can provide a digital all-immersive learning environment at a reduced cost allowing for increased access. However, a key ingredient of what makes all-immersive physical simulators effective is that they allow for multiple participants to engage in cooperative social interaction. Social interaction which allows trainees to develop skills and competencies in navigating situational awareness essential for safety training. Social interaction requires social fidelity. Moving from physical simulators into digital simulators based upon VR technology thus challenges us as HCI researchers to figure out how to design social fidelity into immersive training simulators. We explore social fidelity theoretically and technically by combining core conceptual work from CSCW research to the design experimentation of social fidelity for maritime safety training. We argue that designing for social fidelity in VR simulators requires designers to contextualize the VR experience in location, artifacts, and actors structured through dependencies in work allowing trainees to perform situational awareness, coordination, and communication which are all features of social fidelity. Further, we identify the risk of breaking the social fidelity immersion related to the intent and social state of the participants entering the simulation. Finally, we suggest that future designs of social fidelity should consider not only trainees in the design, but also the social relations created by the instructors’ guidance as part of the social fidelity immersion.
Since the late 70s, much research activity has taken place on the class of dynamic vehicle routing problems (DVRP), with the time period after year 2000 witnessing a real explosion in related papers. Our paper sheds more light into work in this area over more than 3 decades by developing a taxonomy of DVRP papers according to 11 criteria. These are (1) type of problem, (2) logistical context, (3) transportation mode, (4) objective function, (5) fleet size, (6) time constraints, (7) vehicle capacity constraints, (8) the ability to reject customers, (9) the nature of the dynamic element, (10) the nature of the stochasticity (if any), and (11) the solution method. We comment on technological vis-à-vis methodological advances for this class of problems and suggest directions for further research. The latter include alternative objective functions, vehicle speed as decision variable, more explicit linkages of methodology to technological advances and analysis of worst case or average case performance of heuristics.
This report is in the context of the DMA-DTU project on Market Based Measures (MBMs) The aim of this project is to provide an overview and discussion of potential Market Based Measures under the Initial IMO Strategy for the reduction of green house gas (GHG) emissions from ships. In this context, some related developments are also seen as directly relevant to the scope of the project, mainly in the context of the possible inclusion of shipping into the EU Emissions Trading System (ETS). In 2010 an Expert Group was appointed by the IMO’s Secretary General after solicitation of member states and was tasked to evaluate as many as eleven (11) separate MBM proposals, submitted by various member states and other organizations. All MBM proposals described programs and procedures that would target GHG reductions through either ‘in-sector’ emissions reductions from shipping, or ‘out-of-sector’ reductions via the collection of funds to be used for mitigation activities in other sectors that would contribute towards global reduction of GHG emissions.
The real-time provision of high-quality estimates of the ocean wave parameters at appropriate spatial resolutions are essential for the sustainable operations of marine structures. Machine learning affords considerable opportunity for providing additional value from sensor networks, fusing metocean data collected by various platforms. Exploiting the ship-as-a-wave-buoy concept, this article proposes the integration of vessel-based observations into a wave-nowcasting framework. Surrogate models are trained using a high-fidelity physics-based nearshore wave model to learn the spatial correlations between grid points within a computational domain. The performance of these different models are evaluated in a case study to assess how well wave parameters estimated through the spectral analysis of ship motions can perform as inputs to the surrogate system, to replace or complement traditional wave buoy measurements. The benchmark study identifies the advantages and limitations inherent in the methodology incorporating ship-based wave estimates to improve the reliability and availability of regional sea state information.
This paper presents a study focused on wave spectrum estimation in practical scenarios where multiple ships operate in the same geographical area, potentially forming a network of wave recorders. A novel methodology is proposed to improve the accuracy and precision of the wave spectrum estimates, by combining sea state estimation methods and techniques for tuning the wave-to-motion transfer functions. The framework of the wave buoy analogy is used to derive estimates for each ship through the use of measured ship motion data and available initial estimates of transfer functions. Simultaneously, the wave-to-motion transfer functions of the individual ship are tuned by utilizing a weighted version of the wave data inferred on board the other ships in the network. The overall architecture of the procedure is modular, in the sense that various approaches may be implemented for obtaining sea state estimates and tuned transfer functions. The methodology is demonstrated through two case studies, one based on simulated vessel responses, and the other using model test data of ship motions in a wave tank. Both case studies consider a network of three ships in long-crested waves equipped with a dynamic positioning system. It is shown that the procedure provides good wave spectrum estimates, and leads to reduced uncertainty in the estimates via tuning of the vessel transfer functions.
Unmanned surface vehicles (USVs) are increasingly appealing for gathering metocean data, including directional sea spectra. This paper presents new developments towards estimating the response amplitude operators (RAOs) of surface vehicles equipped with inertial sensors. The novel approach undertakes the data-driven estimation of vehicle models of the wave-induced heave, roll, and pitch motion dynamics, as required to perform subsequent seakeeping computations. Specifically, a genetic algorithm executes the calibration of available closed-form RAOs for a simplified geometry. The algorithm makes a population of model-fitting parameters evolve towards minimising discrepancies between the predicted and measured response spectra in stationary operational conditions. Trust in the model is eventually increased by screening and merging the best-fitting solutions. Resulting response predictions using high-resolution spectral wave data for the AutoNaut USV demonstrate satisfactory accuracy and robustness in heave and pitch but a worse fidelity in roll, thereby motivating follow-up studies to improve the estimation of roll RAOs.
In this paper speed optimization of an existing liner shipping network is solved by adjusting the port berth times. The objective is to minimize fuel consumption while retaining the customer transit times including the transhipment times. To avoid too many changes to the time table, changes of port berth times are only accepted if they lead to savings above a threshold value. Since the fuel consumption of a vessel is a non-linear convex function of the speed, it is approximated by a piecewise linear function. The developed model is solved using exact methods in less than two minutes for large instances. Computational experiments on real-size liner shipping networks are presented showing that fuels savings in the magnitude 2–10% can be obtained. The work has been carried out in collaboration with Maersk Line and the tests instances are confirmed to be representative of real-life networks.
In transportation of goods in large container ships, shipping industries need to minimize the time spent at ports to load/unload containers. An optimal stowage of containers on board minimizes unnecessary unloading/reloading movements, while satisfying many operational constraints. We address the basic container stowage planning problem (CSPP). Different heuristics and formulations have been proposed for the CSPP, but finding an optimal stowage plan remains an open problem even for small-sized instances. We introduce a novel formulation that decomposes CSPPs into two sets of decision variables: the first defining how single container stacks evolve over time and the second modeling port-dependent constraints. Its linear relaxation is solved through stabilized column generation and with different heuristic and exact pricing algorithms. The lower bound achieved is then used to find an optimal stowage plan by solving a mixed-integer programming model. The proposed solution method outperforms the methods from the literature and can solve to optimality instances with up to 10 ports and 5,000 containers in a few minutes of computing time.
This study addresses a critical gap in environmental assessments by focusing on petrochemical port operations, an area traditionally overlooked in life cycle assessments (LCAs) of material supply chains. This study investigates various methods of loading for 22 petrochemical products i.e., gas, liquid, container, tanker, and bulk loading; at the biggest petrochemical port in the world situated in the Persian Gulf with a loading capacity of 35 MMt/yr. Twelve scenarios were developed to enhance environmental efficiency based on hotspots defined in LCAs of port loading operations of petrochemicals in their present state. Scenarios 1 through 5 consider electricity savings of 2%–10%, scenarios 6 through 10 consider renewable photovoltaic energy mix of 10%–50%, and scenarios 11 and 12 consider no flaring and rejection of ash waste from ships.
To prioritize these scenarios based on environmental efficiency gains, a comprehensive LCA-GRM hybrid model has been introduced. This integrated model combines life cycle assessment and gray relational modeling, providing a robust framework for evaluating and ranking the scenarios. The Best Worst Method (BWM) is implemented for weighing multiple environmental criteria, contributing to informed decision-making.
The findings underscore the substantial impact of electricity consumption and gas flaring in petrochemical port operations, prompting the identification of the 'no flaring' scenario (S11) as the most preferred option. Implementing this scenario could lead to significant reductions in climate change impacts (22.14%), ozone formation and human health impacts (16.73%), and photochemical oxidant formation (15.98%).
The study's significance lies in emphasizing the environmental implications of port operations and urging policymakers to integrate port impacts into broader supply chain assessments. We advocate for targeted strategies to enhance electricity efficiency and reduce gas flaring in petrochemical ports, aligning with global sustainability goals. The Comprehensive LCA-GRM hybrid approach offers valuable insights for decision-makers involved in the global transportation of goods through ports.