Radioactive Anomaly Detection and Identification Algorithm Suite (RADIAS) for Enhanced Radiological Search

Physical Sciences Inc. (PSI) proposes to develop advanced machine learning (ML) algorithms to detect and identify radiological and nuclear threats in gamma-ray spectra in real-time. The Radiation Anomaly Detector (RAD) will be packaged with an improved version of PSI’s award winning Poisson Clutter Split (PCS) algorithm, which represents the state-of-the-art capability for real-time (1Hz) isotope identification. Supervisory algorithms will maximize sensitivity to both known threats with a priori available signatures and unknown threats that can only be identified as anomalies. The combined Radioactive Anomaly Detection and Identification Algorithm Suite (RADIAS) will significantly improve the performance of current and future sensor systems used by US Armed Forces and Law Enforcement Agencies in the search for radioactive threats, especially Special Nuclear Material (SNM). The algorithms will be optimized for long range detection and identification. RADIAS will be developed to support low-power operation when executing on embedded computational devices during long-term battery powered deployments. RADIAS will integrate with NGA and DoD sensor systems and with PSI’s other commercial radiological/nuclear products such as the PCS-Enabled Radiation Monitor (PERM), the Mobile Urban Radiation Search (MURS) and PERM-Mobile.