Machine learning for radioxenon event classification for the Comprehensive Nuclear-Test-Ban Treaty

A method of weapon detection for the Comprehensive nuclear-Test-Ban-Treaty (CTBT) consists of monitoring the amount of radioxenon in the atmosphere by measuring and sampling the activity concentration of ^131mXe, ¹³³Xe, ^133mXe, and ¹³⁵Xe by radionuclide monitoring. Several explosion samples were simulated based on real data since the measured data of this type is quite rare. These data sets consisted of different circumstances of a nuclear explosion, and are used as training data sets to establish an effective classification model employing state-of-the-art technologies in machine learning. A study was conducted involving classic induction algorithms in machine learning including Naïve Bayes, Neural Networks, Decision Trees, k-Nearest Neighbors, and Support Vector Machines, that revealed that they can successfully be used in this practical application. In particular, our studies show that many induction algorithms in machine learning outperform a simple linear discriminator when a signal is found in a high radioxenon background environment.     

Automated radioxenon monitoring for the comprehensive nuclear-test-ban treaty in two distinctive locations: Ottawa and Tahiti

In preparation for verification of the Comprehensive Nuclear-Test-Ban-Treaty, automated radioxenon monitoring is performed in two distinctive environments: Ottawa and Tahiti. These sites are monitored with SPALAX (Systeme de Prelevement d'air Automatique en Ligne avec l'Analyse des radioXenons) technology, which automatically extracts radioxenon from the atmosphere and measures the activity concentrations of (131m,133m,133,135)Xe. The resulting isotopic concentrations can be useful to discern nuclear explosions from nuclear industry xenon emissions. Ambient radon background, which may adversely impact analyser sensitivity, is discussed. Upper concentration limits are reported for the apparently radioxenon free Tahiti environment. Ottawa has a complex radioxenon background due to proximity to nuclear reactors and medical isotope facilities. Meteorological models suggest that, depending on the wind direction, the radioxenon detected in Ottawa can be characteristic of the normal radioxenon background in the Eastern United States, Europe, and Japan or distinctive due to medical isotope production.     

Measurement and modelling of radioxenon plumes in the Ottawa Valley

Since 2001 a real-time radiation monitoring network of Canadian nuclear facilities and major population centres has been implemented for response to nuclear incidents including a possible terrorist attack. Unshielded NaI(Tl) spectroscopic detectors are employed to measure gamma radiation from airborne radioactivity and radioactivity deposited on the ground. These detectors are composed of a standard 3'x3' cylindrical NaI(Tl) spectrometers with data storage and integrated telemetry. Some of the detectors have been deployed in the Ottawa Valley near Chalk River Laboratories and Ottawa, which has a complex radioxenon environment due to the proximity of nuclear power reactors, and medical isotope facilities. Although not a health threat, these releases have provided an opportunity for the Canadian Meteorological Centre and the Commissariat à l'Energie Atomique to validate their meteorological models. The meteorological models of the two organizations are in good agreement on the origin and the source terms of these releases.