Radio Frequency Spectrum Patterns of Life

As the Electromagnetic Operating Environment (EMOE) becomes more congested, traditional methods of analysis become more and more time-consuming. When entering a new EMOE, Electronic Warfare (EW) Operators must examine a multitude of radar and communications signals of limited tactical relevance which can delay the reporting of new signals of interest. With a firm understanding of this problem, SEACORP proposes the creation of the Spectrum Tracking of Environment using Machine learning Sub-system (STEMS). The STEMS system is a machine learning-based tool that analyzes the historic EMOE received through the Rough Casper system and displays for the operator an easy-to-read pattern of life with anomalous instance indicators. STEMS’ use of anomalous instance indicators allows operators to focus on tactically relevant signals or specific signals of interest and help to prevent a loss of tactical awareness. STEMS is both a mission planning tool and an in situation tactical decision tool that supports the warfighter and mission commander in EMOE dominance.