Expedition Technology, Inc. (EXP) announces a Phase II Small Business Innovation Research (SBIR) award to continue the Improved Geolocation for Over the Horizon Radar (IGOR) program for the National Geospatial-Intelligence Agency. This effort seeks to develop and demonstrate a prototype system that processes Over the Horizon Radar (OTHR) returns to produce improved geolocation estimates for targets illuminated in the radar’s surveillance region.
To accomplish this objective, EXP will enhance the IGOR Deep Learning (DL) algorithms developed during Phase I and evaluate geolocation performance improvements using both high-fidelity surrogate data and collected operational OTHR data. The IGOR DL model directly learns a parameterized implicit representation of the ionospheric channel from the radar measurements themselves, using objects with known locations (such as islands or transponders) as reference points. Once trained, the inference speed of the DL solution can be orders of magnitude faster than typical forward-model driven iterative solutions.
“We’re excited to continue the research started in the first phase of this SBIR,” said EXP Chief Scientist Mike Tinston. “Traditionally, significant effort is invested in modelling the ionosphere explicitly with physics-based forward models requiring large amounts of computation. IGOR will expand the capabilities of OTHR using machine learning to benefit both NGA and the warfighter.”
