Vessel Movement Prediction via Historical Trip Clustering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current vessel tracking methods using AIS data struggle to accurately predict vessel movements and detect anomalies, due to the lack of formal route definitions, variations caused by weather and other factors, and the computational inefficiency in processing large datasets.
Innovation Solution
The method involves clustering historical trips to determine representative or average trips, which are then used to predict future vessel movements by selecting the closest representative trip based on the current location of the vessel. This approach splits historical location data into trips between stop points, allowing for efficient clustering and accurate anomaly detection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If AIS data from multiple receiving stations is collated to determine accurate vessel locations, then measurement precision is improved, but device complexity increases due to the need to process immense amounts of data
Solution Approach 1:
The patent segments the immense AIS dataset into smaller, manageable subsets based on spatial regions or time periods. By dividing the data processing task into segments, the system can handle large volumes of AIS data from multiple receiving stations without overwhelming computational resources, while still maintaining accurate vessel location determination through aggregated results.
2Measurement precision
If all historical AIS data points are processed to predict vessel routes, then prediction accuracy is improved, but productivity decreases due to computational overload
Solution Approach 1:
The patent extracts only the most relevant features and data points from historical AIS data for route prediction, rather than processing all available data. By identifying and extracting key parameters such as common navigation paths, stop points, and vessel behavior patterns, the system achieves accurate predictions while significantly reducing computational load and improving processing speed.
Solution Approach 2:
The patent applies partial action by processing a representative subset of historical AIS data that captures essential routing patterns without analyzing every single data point. This approach uses clustering algorithms to identify common routes from sample data, which then serves as a basis for predicting vessel movements, achieving good predictive accuracy with reduced computational effort.
3Manufacturing precision
If clustering is performed on complete historical location sequences, then manufacturing precision is improved, but loss of time increases due to computational requirements
Solution Approach 1:
The patent segments historical location sequences into smaller clusters based on spatial proximity or temporal proximity before performing clustering analysis. This segmentation allows the system to compute representative routes more efficiently by working with smaller data subsets, reducing processing time while maintaining the precision needed to identify common navigation patterns and stop points.
Data Source
AI summary
This disclosure relates to a method for predicting vessel movement as performed by a processor. The processor creates historical trip data by receiving historical location data indicative of historical locations of vessels; identifying stop points in the historical locations indicative of ports where the vessels stopped; splitting the historical location data for the vessels into sequences of historical locations between the stop points; and clustering the sequences of historical locations to determine representative sequences, each representative sequence representing one of multiple clusters. The processor then predicts future vessel movement by receiving a current geographical location for a current trip of a tracked vessel, selecting one of the representative sequences that is close to the geographical location, and predicting future movement of the tracked vessel as proceeding along the selected one of the representative trips.