APOLLO: Adaptive Pattern-of-Life Learning Operations

With the increase in new foreign launches and the number of agile or potentially separable satellites being placed into orbit, it is critical that the U.S. Air Force not only maintain custody of these satellites, but also quickly identify and interpret unusual behavior in complex and evolving multi-domain situations. To support decision making processes and enable rapid situational awareness, Numerica proposes to develop an Adaptive Pattern-of-Life Learning Operations system (APOLLO) that exploits multiple intelligence (multi-INT) data streams to provide automated indications and warnings (I&Ws), event predictions, and associated confidence measures. APOLLO will build upon Numericas multi-INT event detection system, Athena, and be matured using historical and real-time data sources including data being produced by Numericas global telescope network. Through an innovative high-dimensional feature space representation of a satellites multi-INT spatial-temporal pattern of life, together with the application of powerful unsupervised machine learning techniques, APOLLO will support a number of use cases of interest to the Space Battle Management Command and Control (BMC2) community. Particular attention will be given to developing and implementing approaches that adapt to changes in the baseline to reduce false alarms and missed detections, and that are robust to variability in data quality, quantity, and cadence.