Ship Route Optimization Using Weather and Circulation Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Shipping routes are inefficient and contribute significantly to greenhouse gas emissions due to uncertainties in weather, ocean conditions, and human factors, leading to delays and increased operational costs.
Innovation Solution
Utilizing machine learning models and ocean circulation models to optimize ship routes based on weather data and historical data, incorporating Monte Carlo sampling and deep learning to account for real-world uncertainties, and employing a control unit to determine optimal routes considering various constraints and objectives.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional pilot charts and historical route patterns are used for navigation, then route planning is simple and based on established paths, but route efficiency is suboptimal and greenhouse gas emissions are high
Solution Approach 1:
The patent replaces traditional mechanical navigation methods (pilot charts, historical routes) with data-driven machine learning models that process weather data, ocean circulation models, and historical ship routes to generate optimized routes dynamically, substituting static mechanical systems with adaptive computational systems
Solution Approach 2:
The system changes navigation parameters by incorporating real-time weather conditions, ocean currents, and wave forecasts into route optimization, allowing routes to adapt dynamically to environmental parameters rather than following fixed historical patterns
2Measurement precision
If high-resolution weather and ocean circulation models are used to improve forecast accuracy, then route optimization precision increases, but computational resource requirements increase significantly
Solution Approach 1:
The patent applies partial action by using selective resolution levels of weather and ocean models - employing higher resolution only in critical decision zones while using coarser resolution in less critical areas, thereby achieving sufficient forecast accuracy without exhaustive computational resources
Solution Approach 2:
The system segments the ocean domain into different resolution zones, applying high-resolution modeling only to specific regions of interest while using lower-resolution models for broader areas, reducing overall computational burden while maintaining local accuracy
3Reliability
If Monte Carlo sampling and deep learning are incorporated to account for real-world uncertainties, then route reliability improves, but system complexity and computational demands increase
Solution Approach 1:
The patent introduces intermediate probabilistic models that mediate between uncertain environmental data and route decisions, using Monte Carlo sampling to create probability distributions that capture uncertainty without requiring the full complexity of all possible scenarios
4Productivity
If ship routes are optimized for shortest time or most energy efficient path, then one performance metric improves, but other metrics such as safety or cost may deteriorate
Solution Approach 1:
The patent creates a universal optimization framework that simultaneously evaluates multiple objectives (time, energy, cost, safety) through a single multi-objective optimization algorithm, allowing the system to adapt to different shipping priorities without requiring separate specialized systems for each metric
Data Source
AI summary
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for determining elements of a shipping network. One of the methods includes obtaining environmental input data, wherein the environmental input data includes weather forecast data; providing the environmental input data to a circulation model; and providing output environmental condition from the circulation model to a machine learning model trained to generate a route for a ship.