Radioactive Direction of Arrival Estimation Using Neural Networks Approach

Abstract

In this paper, we present a comprehensive investigation into improving Direction of Arrival (DOA) estimation for gamma-emitting isotopes using deep neural networks. The direction of arrival estimation is most valuable for Home Land Security (HLS) applications or increased safety in Decontamination and Decommissioning (D&D). Traditional methods, such as beamforming (BF), have limitations in accuracy and sensitivity to noise and background variations. In recent years, data-driven approaches utilizing deep neural networks, including Convolutional Neural Network (CNN) and Gated Recurrent Unit (GRU) models, have shown promise in enhancing DOA estimation. By considering the full energy spectrum and augmenting recorded data, our neural network models outperform traditional BF methods and exhibit greater resilience in diverse background scenarios. The 2-layer CNN model, in particular, achieves up to 40% improvement in estimation accuracy. Our research provides a reliable and data-driven approach for precise DOA estimation with potential applications in nuclear security and safety in D&D.

Keywords

• radiation detection
• direction of arrival (doa) estimation
• convolution neural network (cnn)
• reinforcement neural network (rnn)
• localization of radiation sources