Learning Assisted Single Satellite Rapid Geolocation of Ground-based EMI Sources

Satellite communications (SATCOM) are facing increasingly diverse physical and electromagnetic interference (EMI) that transmit radio frequency (RF) signals in X/Ku/K/Ka/Q-bands. Interference of satellite communications is a frequent and ongoing concern for both DoD and civilian enterprises. Geolocation of the interfering source is an essential step in mitigating or eliminating the interference and restoring operation of the communications service. In this Phase I project, the Intelligent Fusion Technology, Inc. (IFT) team has developed a rapid and passive single-satellite based 3D meter-level geolocation for ground EMI sources that interfere with the uplinks of SATCOM. The Phase I effort has resulted in a prototype of the proposed blind Doppler estimation and constrained unscented Kalman filter (cUKF) based SSG. In Phase II, IFT team will refine and expand the Phase I technologies to integrate context-aware ML/AI. Context-aware geolocation will be developed to incorporate contextual information of the satellite as well as the potential EMI sources. Deep learning techniques will be incorporated in the SSG framework to predict the optimal design parameters for the blind carrier Doppler estimation and cUKF. The phase II prototype with fully integrated ML/AI enhancements is expected to obtain the meter-level geolocation accuracy.