Rapid Deployment, Calibration, and Training of Optical Observatories for Space Domain Awareness

The proliferation of maneuverable satellites in Earth orbit\((-)\) and the expansion of organizations controlling them\((-)\)demands a proliferation of ground based space domain awareness (SDA) infrastructure to maintain safe access to\((-)\) and operations in\((-)\)space. The requirement for mass-produced 0.5-1.5 meter optical telescopes has never been greater. These systems must be rapidly deployable, useful within days of deployment, and provide precise metric observations autonomously. Acquisition of commercial telescopes optimized for cost and quality solves hardware needs. We focus on algorithms for calibration and precision star detection enabling measurements of satellite positions for orbit determination and tracking. We propose a three part solution. First, we demonstrate a toolset (``Burr'') for automatic calibration, including the generation of star streak datasets. Second, we describe a new concept of operations using both rate and sidereal tracking ( S idereal EN riched P recision A strometric I ntelligence, ``SENPAI'') which returns \((\sim1\arcsec)\) astrometric residuals on calibration satellites in right ascension and declination. Finally, we introduce a custom lightweight neural network (Star Center and Scale Prediction, ``StarCSP''), inspired by the crowd counting literature enabling rapid operations. In combination, this set of tools provide the necessary framework to convert an optical telescope into a high precision SDA asset within days of deployment. We demonstrate this on multiple 0.35m observatories.