Target Custody Platform Satellite Imagery Confidence Intervals
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current predictive analytics platforms lack an effective method to compute the confidence level of a target of interest's projected path using artificial intelligence, particularly in intelligent target tracking and path projection applications.
Innovation Solution
A target custody platform is developed, comprising a data acquisition engine, a data analysis engine, and a machine learning engine that tasks satellites for imagery data, calculates satellite footprints, and uses machine learning algorithms to compute confidence scores based on imagery data, metadata, and weather data, to predict the likelihood of a target following a projected path.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional predictive analytics methods are used to track target paths, then the system is simpler to implement, but the confidence level and accuracy of predicted paths are insufficient
Solution Approach 1:
The patent replaces traditional mechanical predictive analytics methods with machine learning algorithms and artificial intelligence systems. The ML engine processes satellite imagery data, metadata, and weather data to generate confidence scores for predicted target paths, substituting conventional statistical methods with more sophisticated AI-based prediction mechanisms that provide higher measurement precision.
Solution Approach 2:
The system integrates multiple data sources (satellite imagery, metadata, weather data) and combines them through a composite analytical framework. The machine learning engine processes this composite data structure to generate predictions with confidence intervals, effectively creating a composite predictive model that leverages the strengths of multiple data types and analytical approaches.
2Reliability
If multiple satellites are tasked for imagery data collection, then the coverage and accuracy of target tracking improve, but the cost and resource requirements increase
Solution Approach 1:
The system tasks satellites selectively based on the projected path of the target of interest. Rather than continuously deploying all available satellites, the system calculates satellite footprints and tasks only those satellites whose coverage areas intersect with the predicted target path sections, providing sufficient tracking accuracy while minimizing the number of satellites required.
Solution Approach 2:
The patent divides the target's projected path into multiple sections and assigns different satellites to monitor specific sections. The system calculates which satellite footprints intersect with which path sections, creating a segmented monitoring approach where each satellite is responsible for specific geographic segments, thereby optimizing resource allocation and reducing the total number of satellites needed.
Data Source
AI summary
A target custody platform comprising a data acquisition engine, a data analysis engine, a machine learning engine, and a data presentation layer configured to task a plurality of satellites for imagery data wherein the imagery data and metadata is used in conjunction with other types of data including identification data and weather data as inputs into a one or more machine and/or deep learning algorithms configured to predict a the likelihood a target of interest will travel along a project path.