<div> Space operations from the dawn of the Space Age have resulted in a large, and growing, resident space object population. However, the availability of sensor resources is limited, which presents a challenge to Space Situational Awareness applications. When direct communication with an object is not possible, whether that is due to a lack of access for active satellites or due to the object being characterized as debris, the only independent information source for learning about the resident space object population comes from measurements. Optical measurements are often a cost-effective method for obtaining information about resident space objects.<br></div><div> This work uses observability analysis to investigate the relationship between desired resident space object characteristics and the information resulting from ground-based optical measurements. Observability is a concept developed in modern control theory for evaluating whether the information contained within measurements is sufficient to describe the dynamical progression of a system over time. In this work, observability is applied to Space Situational Awareness applications to determine what object characteristic information can be recovered from ground-based optical measurements and under which conditions these determinations are possible. In addition, the constraints and limitations of applying observability to Space Situational Awareness applications are assessed and quantified.<br></div>

With the increase in space traffic, proliferation of inexpensive launch opportunities, and interest from many countries in utilizing the space domain, threats to existing space assets are likely to increase dramatically in the coming years. The development of a system that can identify potential threats and alert space operators is vital to maintaining asset resiliency and security. The focus of this thesis is the design and evaluation of such a system. The design is comprised of the development of a classification hierarchy and the selection of machine learning models that will enable the identification of anomalous object behavior. The hierarchy is based on previous examples applied to object classification while reconsidering the assumption that a satellite may perform only one mission. The selected machine learning models perform both supervised classification of actively maneuvering objects and unsupervised identification of anomalous behavior within large satellite constellations. The evaluation process considers the independent adjustment of model hyperparameters to achieve optimal model settings. The optimal models perform both classification functions and return moderate accuracy. The system is applied to several case studies examining edge cases and what factors constitute a threatening object and what factors do not. Suggestions for improvement of the system in the future are presented. / Master of Science / The increase in space traffic, proliferation of inexpensive launch opportunities, and interest from many countries in utilizing the space domain represent existential threats to existing spacecraft and operations in low-Earth orbit. Threats to the safe operation of spacecraft are likely to increase dramatically in the coming years. The development of a system that can identify potential threats and alert space operators is vital to maintaining asset resiliency and security. The focus of this thesis is the design and evaluation of such a system. This is accomplished by identifying a system architecture through evaluating current assumptions of what missions satellites are capable of performing. Following the system-level design, modules are proposed that utilize machine learning to identify satellite behavior that is abnormal. These modules are tested and tuned with optimal parameters to deliver improved identification performance. The system is applied to several case studies examining edge cases and what factors constitute a threatening object and what factors do not. Suggestions for improvement of the system in the future are presented.

This thesis investigates using adaptive estimation techniques to determine unknown model parameters such as size and surface material reflectivity, while estimating position, velocity, attitude, and attitude rates of a resident space object. This work focuses on the application of these methods to the space situational awareness problem. This thesis proposes a unique method of implementing a top-level gating network in a dual-layer hierarchical mixture of experts. In addition it proposes a decaying learning parameter for use in both the single layer mixture of experts and the dual-layer hierarchical mixture of experts. Both a single layer mixture of experts and dual-layer hierarchical mixture of experts are compared to the multiple model adaptive estimation in estimating resident space object parameters such as size and reflectivity. The hierarchical mixture of experts consists of macromodes. Each macromode can estimate a different parameter in parallel. Each macromode is a single layer mixture of experts with unscented Kalman filters used as the experts. A gating network in each macromode determines a gating weight which is used as a hypothesis tester. Then the output of the macromode gating weights go to a top level gating weight to determine which macromode contains the most probable model. The measurements consist of astrometric and photometric data from non-resolved observations of the target gathered via a telescope with a charge coupled device camera. Each filter receives the same measurement sequence. The apparent magnitude measurement model consists of the Ashikhmin Shirley bidirectional reflectance distribution function. The measurements, process models, and the additional shape, mass, and inertia characteristics allow the algorithm to predict the state and select the most probable fit to the size and reflectance characteristics based on the statistics of the measurement residuals and innovation covariance. A simulation code is developed to test these adaptive estimation techniques. The feasibility of these methods will be demonstrated in this thesis.