Vessel Rendezvous Prediction Using Multi-Source Trajectory Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vessel tracking systems, such as AIS, do not provide vessel rendezvous detection or prediction, leaving ports and authorities vulnerable to illegal activities like human trafficking, drug smuggling, and disease transmission, and there is a need for improved systems to quickly and accurately detect and predict vessel rendezvous at sea.
Innovation Solution
A computer-implemented method and system that utilizes a rendezvous prediction model, constructed vessel trajectories, and classification models to analyze AIS, satellite, and RF data to identify and predict vessel rendezvous, providing outputs like imminent threats or loitering patterns.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If AIS tracking systems are used to monitor vessels, then vessel position and movement data can be collected, but the system cannot detect or predict vessel rendezvous activities
Solution Approach 1:
The system performs preliminary actions by constructing vessel trajectories from historical AIS data and training machine learning models beforehand. The rendezvous prediction model is pre-trained with trajectory data to enable future prediction of rendezvous events, rather than detecting them in real-time from raw AIS data alone.
Solution Approach 2:
The patent introduces an intermediary machine learning pipeline between AIS data collection and rendezvous detection. This includes trajectory construction modules and trained prediction models that act as intermediaries to transform basic vessel position data into actionable rendezvous predictions.
2Measurement precision
If multiple data sources (AIS, satellite, RF) are integrated for comprehensive vessel tracking, then detection accuracy improves, but system complexity and resource requirements increase
Solution Approach 1:
The system merges multiple data sources (AIS, satellite imagery, RF transmissions) into a unified trajectory representation. By combining these diverse data streams and processing them through a common machine learning pipeline, the system achieves comprehensive vessel monitoring while managing complexity through integration rather than separate processing systems.
Solution Approach 2:
The machine learning pipeline serves multiple functions: it processes different data types (AIS messages, satellite images, RF signals), constructs trajectories from various sources, and generates rendezvous predictions. This multi-functional approach reduces overall system complexity by using a single versatile processing framework.
3Loss of time
If vessel trajectories are constructed and analyzed in real-time for rendezvous prediction, then timely detection of illegal activities is achieved, but computational resources and processing time increase
Solution Approach 1:
The system performs computationally intensive tasks in advance, including trajectory construction from historical data and training of machine learning models. This preliminary processing reduces the computational burden during real-time operation, allowing rapid prediction of rendezvous events without excessive energy consumption during critical detection phases.
Solution Approach 2:
The patent replaces traditional mechanical or rule-based trajectory analysis with machine learning-based prediction. The trained models automatically identify patterns and predict rendezvous events without requiring complex real-time computational analysis, significantly reducing processing time and energy requirements during operation.
Data Source
AI summary
Provided are systems, methods, and computer readable media for predicting a vessel rendezvous, and systems, methods, and computer readable media for generating a vessel rendezvous prediction model. The method can include receiving vessel data for a plurality of vessels; constructing a vessel trajectory for each vessel based; identifying one or more identified trajectory segments of the plurality of constructed vessel trajectories based on an unstable speed detection; detecting a rendezvous between a first vessel and a second vessel of the plurality of vessels; storing the detected rendezvous and the determined type of the detected rendezvous in a vessel rendezvous history database; labeling a first vessel trajectory of the first vessel and a second vessel trajectory of the second vessel based on data stored in the vessel rendezvous history database; and generating a rendezvous prediction model based on the labeled dataset, for predicting a rendezvous for a candidate vessel trajectory.