Maritime Autonomous Surface Ships (MASS) are in the development stage and they play an important role in the upcoming future. Present generation ships are semi-autonomous and controlled by the ship crew. The performance of the ship is predicted using the data collected from the ship with the help of machine learning and deep learning methods. Path planning for an autonomous ship is necessary for estimating the best possible route with minimum travel time and it depends on the weather. However, even during the navigation, there will be changes in weather and it should be predicted in order to reroute the ship. The weather information such as wave height, wave period, seawater temperature, humidity, atmospheric pressure, etc., is collected by ship external sensors, weather stations, buoys, and satellites. The present paper investigates the ensemble machine learning approaches and seasonality approach for wave data prediction. The historical meteorological data is collected from six stations near Puerto Rico offshore and Hawaii offshore. We explore ensemble machine learning techniques on the data collected. The collected data is divided into training and testing data and apply machine learning models to predict the test data. The hyperparameter optimization is performed to find the best parameters before fitting on train data, this is essential to find the best results. Multivariate analysis is performed with all the methods and errors are computed to find the best models.

This study presents a novel statistical trajectory-distance metric specialized for nautical route clustering analysis. Based on the dynamic time warping (DTW) metric, one of the most used metrics for trajectory-distance, the statistical trajectory-distance metric was defined by replacing the distance term in DTW with a linear combination of the Jensen–Shannon divergence and Wasserstein distance. Each waypoint from a nautical route was modelled as a discrete and asymmetric binomial normal distribution defined by the cross-track distance (XTD) of the waypoint. The model was then used to compute the statistical distance between waypoints. Nautical route clustering was performed using density-based spatial clustering of applications with noise and the statistical trajectory-distance metric. The nautical route for the clustering analysis, including the XTD information, was extracted from automatic identification system data from the southern sea of the Korean Peninsula. The clustering results were evaluated by comparing them with the results of other popular trajectory-distance metrics. The proposed method was more effective compared to other trajectory-distance when the trajectories pass on both sides of a small island, which is frequent case in coastal route clustering.

No abstract

This research proposes an integrated voyage optimization algorithm that combines quadtree graph generation, visibility graph simplification, Dijkstra’s algorithm, and a 3D dynamic programming method. This approach enables the determination of a minimum distance initial reference route and the creation of a 2D navigational graph for efficient route optimization. We effectively store and process complex terrain information by transforming the GEBCO uniform grid into a quadtree structure. By utilizing a nearest neighbor search algorithm, edges are connected between adjacent ocean nodes, facilitating the generation of a quadtree graph. Applying Dijkstra’s algorithm to the quadtree graph, we derive the shortest initial route and construct a visibility graph based on the waypoints. This results in a simplified reference route with reduced search distance, allowing for more efficient navigation. For each waypoint along the reference route, a boundary is defined angled at 90 degrees to the left and right, based on the waypoint’s reference bearing. A line segment formed by the waypoint and both boundaries is defined as a navigational stage. A navigational graph is defined by connecting adjacent stages. Employing a 3D dynamic programming method on the navigational graph, and incorporating weather forecasting data, including wind, wave, and currents, we search for a route that minimizes fuel oil consumption with ETA restrictions. Our approach is tested on several shipping routes, demonstrating a fuel consumption reduction compared to other voyage optimization routes. This integrated algorithm offers a potential solution for tackling complex voyage optimization problems in marine environments while considering various weather factors.

No abstract