Onboard Hyperspectral RSO Identification Under Downlink Limits
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Hyperspectral imaging for space situational awareness faces challenges due to data downlink bottlenecks created by the large volume of hypercube data produced by HSI sensors, necessitating an improved system and method for resident space object characterization.
Innovation Solution
A combined onboard and ground-based machine learning approach for hyperspectral data processing, involving onboard data reduction and compression, followed by ground-based enrichment and fusion, to optimize RSO and component spectra identification, using calibration and correction techniques to enhance data accuracy and reduce transmission requirements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If hyperspectral imaging sensors are used to collect data of resident space objects, then identification accuracy and spectral information quality are improved, but data volume increases causing downlink bottlenecks
Solution Approach 1:
The patent segments the hyperspectral data processing workflow into onboard processing (spectral unmixing, endmember identification, initial classification) and ground-based processing (refined classification, verification). This segmentation allows critical spectral analysis to be performed in space with reduced data transmission requirements, while ground-based systems handle less demanding tasks.
Solution Approach 2:
The patent extracts only the most essential spectral features and classification results from the full hyperspectral cube for downlink transmission. By performing spectral unmixing and endmember identification onboard, the system extracts key information (material composition, spectral signatures) while leaving the full raw data volume on the spacecraft or processing it locally.
2Quantity of substance
If onboard processing is implemented to reduce data transmission, then data downlink requirements are reduced, but computational resources on spacecraft are consumed
Solution Approach 1:
The patent performs preliminary spectral processing tasks (calibration, dark field subtraction, spectral unmixing, endmember identification) onboard before data transmission. These preliminary actions prepare the data in advance, extracting essential spectral features and reducing the volume of data requiring downlink, while ground-based systems handle less computationally intensive verification and refined classification.
Solution Approach 2:
The patent changes the computational parameter distribution between onboard and ground systems. Onboard processing focuses on spectral parameter extraction (wavelength calibration, spectral signatures, material identification) while ground-based processing handles spatial parameter refinement and verification. This parameter specialization optimizes the energy-computation tradeoff.
3Reliability
If ground-based processing is used for verification and refinement, then identification reliability is improved, but processing time increases
Solution Approach 1:
The patent performs preliminary classification and spectral analysis onboard before ground-based verification, so that when data arrives at ground stations, the initial identification is already complete. Ground-based processing then performs verification and refinement on pre-processed data, reducing the overall processing time compared to performing all analysis on the ground.
Solution Approach 2:
The patent implements a feedback loop where ground-based verification results are used to refine and update onboard processing algorithms. Ground stations verify classifications against additional data sources and feedback mechanisms, then transmit refined models back to the spacecraft for improved onboard processing in subsequent operations, progressively improving reliability over time.
Data Source
AI summary
Systems and methods for characterizing resident space objects (RSOs) including collecting hyperspectral data of an RSO using a hyperspectral imaging sensor onboard a spacecraft, processing the data using an ML RSO classification and identification model to obtain RSO and component spectra identification data, transmitting the identification data and the hyperspectral data to a ground station, processing the hyperspectral data at the ground station using an image processing algorithm or technique other than the ML-based RSO classification and identification model to obtain enriched RSO and component spectra identification data, optimizing identification of the RSO and spectra in the hyperspectral data using an output of a comparison of identification data and the enriched identification data to obtain optimized identification data; transmitting the optimized RSO and component spectra identification data to a user device; and displaying the optimized RSO and component spectra identification data in a graphical user interface at the user device.