Marine Vessel Position Forecasting via Spatial Index Bins
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current satellite-based AIS systems for tracking marine vessels suffer from significant delays and incompleteness in data delivery, leading to gaps in vessel location awareness, as they can only update positions intermittently and detect a limited percentage of vessels due to distance and signal interference issues.
Innovation Solution
A system and method that utilizes a forecasting algorithm to estimate the position of marine vessels by dividing a body of water into 'bins' of location and direction information, building a spatial index based on previous paths, and generating a dynamic probability cloud to represent the current and future position of vessels, incorporating additional factors like ship type, weather, and ocean currents.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If satellite-based AIS systems are used to track vessels globally, then the coverage area is vast, but the data delivery is delayed and incomplete
Solution Approach 1:
The system performs preliminary actions by collecting and storing vessel trajectory data, weather patterns, and ocean current information in advance. When a vessel's position needs to be forecast, the system already has pre-processed historical data and environmental models ready, enabling rapid position estimation without waiting for satellite data delivery
Solution Approach 2:
The system introduces an intermediary forecasting mechanism that acts between the satellite AIS data source and the end user. Instead of directly relying on delayed satellite data, the intermediary system uses machine learning models to predict vessel positions, effectively bridging the time gap and providing near-real-time tracking information
2Device complexity
If satellite AIS systems update vessel positions intermittently, then the system complexity is reduced, but the position data becomes outdated
Solution Approach 1:
The system replaces the mechanical satellite-based periodic update mechanism with a computational forecasting approach. Instead of relying on physical satellite passes and intermittent data collection, the system uses machine learning models to continuously predict vessel positions, transforming a physically constrained system into a computationally intensive one that provides continuous position estimates
3Area of stationary object
If the distance between vessels and receiving satellites is great, then the coverage area increases, but signal interference increases and detection completeness decreases
Solution Approach 1:
The system implements feedback mechanisms where predicted vessel positions are continuously compared with actual satellite AIS data when received. The machine learning models are trained on historical data and continuously refined based on prediction accuracy, creating a feedback loop that improves detection reliability over time while maintaining vast coverage areas
Data Source
AI summary
There is disclosed a system and method for forecasting the positions of marine vessels. In an aspect, the present system is adapted to execute a forecasting algorithm to forecast the positions of one or a great many marine vessel(s) based on one or more position reporting systems including coastal and satellite AIS (S-AIS) signals or LRIT received from the vessel. The forecasting algorithm utilizes location and direction information for the vessel, and estimates one or more possible positions based on previous paths taken by vessels from that location, and heading in substantially the same direction. Thus, a body of water can be divided into “bins” of location and direction information, and a spatial index can be built based on the previous paths taken by other vessels after passing through that bin. Other types of information may also be taken into account, such as ship-specific data, nearby weather, ocean currents, the time of year, and other spatial variables specific to that bin.