Forecasting Space System Threats: A Streamlined Approach

ABSTRACT: The most critical limitations of existing approaches to threat detection and prediction is their inability to support the required knowledge modeling and continuing refinement under realistic constraints (e.g., few historic threat exemplars, limitations on the availability of subject matter experts, and the need for constant adaptation). Stottler Henke proposes to develop a new system, called Synth, that will directly address this shortcoming through three primary techniques. First, we abandon the typical consensus-driven modeling approach in favor of an approach that solicits asynchronous knowledge contributions (in the form of alternative future scenarios and indicators) without burdening the user with endless certainty or probability estimates. Second, Synth will enable knowledge contributions by personnel beyond the typical core decision-making group, thereby casting light on blindspots, mitigating human biases, and maintaining the currency of the developed threat models. Last, we employ novel machine learning techniques to avoid problems related to training and adaptability that plague other common approaches (e.g., neural networks); reasoning over the results and multiple intermediate hypotheses / threat models with a probabilistic model of evidence integration. Phase I development of a limited prototype will provide a solid foundation for the complete implementation of Synth in Phase II, and its eventual commercialization. BENEFIT: In addition to obvious benefits in military situation awareness, Synth will provide corporations with an early warning capability that allows them to monitor their competitors and the markets for changes that may signal impending threats. We are particularly excited about the prospects of integrating the proposed technology with Raytheon in their ongoing development of solutions, such as the Space Fence that is emerging from contracts awarded by the Air Force Electronic Systems Center, as well as other areas of the DoD and the Intelligence Community.