Validating Space-Based Observation Data Quality through Real-Time Anomaly Detection
The Lumos Data Quality Analyzer combines space observations across many sensors to find and flag anomalies in real time. It processes 75% of all deep space observation data for Space Force’s Space Surveillance Network (SSN) and identifies anomalies such as sensor timing bias errors, bad sensor ephemerides input, or unmodeled Resident Space Objects (RSOs) orbit maneuvers. Lumos detects these anomalies without the need for calibration satellite collects because it employs an Unscented-Schmidt Kalman Filter (USKF).
The Lumos Data Quality Analyzer Offers:
- Observation Data Quality Assessment Without Calibration Satellites: Lumos can perform accurate data quality assessment without requiring sensors to collect calibration satellite observations. The USKF can compare multiple observations of the same target from multiple sensors to determine if sensors or RSOs have data quality anomalies, reducing calibration collection needs and enabling more mission collections.
- Sensor Agnostic Near-Real-Time Processing: Lumos is sensor agnostic and currently performs data quality assessment across all space-based SSN sensors. Sensor specific capabilities are captured in configuration files and adding new constellations only requires configuration updates, and no code updates.
- Autoscaling Microservices: Lumos is a microservice architecture that can autoscale with dynamic cloud resources to match demand. This allows the Data Quality Analyzer to meet the demands of increased observations during critical world events.
- Small Business Innovation and Cost: Lumos was awarded as a part of Space Pitch Day 2019 by General Thomson and Dr. Roper. The Data Quality Analyzer was developed for the standard award value of $750K.
