Quantum Algorithms for Space Situational Awareness
Abstract
The space environment, long characterized as congested, contested, and competitive, is steadily growing more so. The number of objects tracked by the US Space Surveillance network grew from approximately 7,000 in 1990 to 13,000 in 2006, and those numbers continue to rise dramatically. The task of identifying and tracking this debris rises in cost as the number and class of objects increases. Conventional machine learning techniques promise admirable short term relief, but recent advances in quantum machine learning suggest systems that could scale more advantageously. While many such algorithms have been suggested and mathematically proven, very few applications of these algorithms to real world problems have been implemented and executed. We propose to investigate the use of modern quantum computing algorithms for image-signal classification and data analysis to explore courses of action that could more effectively scale with increased problem size. The primary problem being addressed will be that of signal classification using satellite glint (reflected radiance) data possibly combined with known orbital data and observation metadata, but we will also investigate other known algorithms such as topological data analysis for their applicability to the SSA problem, and will seek to develop new algorithms for anomaly detection and reporting.
Document Details
- Document Type
- DoD Grant Award
- Publication Date
- Jan 14, 2022
- Source ID
- FA95501917009
Entities
People
- Iordanis Kerenidis
Organizations
- Air Force Office of Scientific Research
- QC Ware
- United States Air Force