Motivating the inclusion of meteorological indicators in the CTBT feature-space

Abstract

Abstract-Verification of the Comprehensive Test-Ban-Treaty (CTBT), as a Pattern Recognition (PR) problem, has been proposed based on four radioxenon features. It has been noted, however, that in many cases this limited feature set is insufficient to distinguish radioxenon levels effected by an explosion from those that are solely products of industrial activities. As a means of improving the detectability of low-yield clandestine nuclear explosions, this paper motivates the inclusion of meteorological indicators in the CTBT feature-space, promotes further research into which meteorological indicators are most informative, and how they may be acquired. In doing so, we present classification results from four simulated scenarios. These results demonstrate that the inclusion of a simple wind direction feature can significantly increase the prospect of classifying challenging detonation events, and suggests the predictive power of meteorological features in general.

Learning over subconcepts: Strategies for 1‐class classification

“…Stocki et al 4 used several binary classifiers to discriminate between the background and synthesized explosion data and demonstrated that these methods outperformed simple linear discriminators. Following this study, Bellinger et al [21][22][23] noted the "unnatural" a priori class probabilities that were inherent in the publicly available Health Canada CTBT data set, highlighting that the domain clearly fits into a 1-class classification problem. This motivated them to develop a stochastically episodic event modeling and simulation framework; the data used for our work were based on this framework.…”