Wide Area Distributed Algorithms for Cooperative Source Identification, Characterization, and Localization

Current radiation detection algorithms are based on the concept that each detector operates independently. The Probitas Project, Inc. (Probitas) and the Lawrence Berkeley National Laboratory (LBNL) propose to show the benefits of data fusion to improve the identification, localization, and characterization of a radioactive source in a complex scene as compared to a singular detector algorithm. We will develop flexible, multi-radiation detector algorithms that can be deployed across radiation detection networks to enable the linking of multiple detector variants and fusing of raw detector outputs into usable information. Our data-driven approach utilizes currently available data to investigate multi-input neural networks and network architectures for identification and anomaly detection to achieve improved performance metrics for low statistics measurements. We will also extend current point estimation and tracking technologies to localize a source faster and/or with fewer detections using a multi-sensor network.