Gamma/Neutron Online Discrimination Based on Machine Learning With CLYC Detectors

Abstract

An embedded system (ES) for gamma and neutron discrimination in mixed radiation environments is proposed, validated with an off-the-shelf detector consisting of a Cs2LiYCl6:Ce (CLYC) crystal coupled to a silicon photomultiplier (SiPM) cell array. This solution employs a machine learning classification model based on a multilayer perceptron (MLP) running on a commercial field-programmable gate array (FPGA), providing online single-event identification with 98.2% overall accuracy at rates higher than 200 kilocounts/s. Thermal neutrons and fast neutrons up to 5 MeV can be detected and discriminated from gamma events, even under pile-up scenarios with a dead-time lower than $2.5~\mu $ s. The system exhibits excellent size, weight, and power consumption (SWaP) characteristics, packed in a volume smaller than 0.6 l and weighing less than 0.5 kg, while ensuring continuous operation with only 1.5 W. These features render our proposal suitable for embedded applications where low SWaP is critical and radiation levels manifest large count rates variability, such as space exploration, portable dosimeters, radiation surveillance on uncrewed aerial vehicles (UAVs), and soil moisture monitoring.