Neural Networks for 3D Characterization of AGATA Crystals

Abstract: Precise localization of gamma-ray interactions is crucial for the performance of AGATA. The Pulse Shape Analysis (PSA) method used for the position estimation relies on simulated signals database. The Pulse Shape Comparison Scanning (PSCS) method was used to scan AGATA crystals in order to produce an experimental database. This paper presents a novel approach using LSTM neural networks to determine the 3D interaction position of gamma rays within AGATA crystals, trained on data from the Strasbourg scanning tables, allowing for constructing experimental database. A custom masked loss function is introduced to enable training with incomplete position information. The database generated by this new method outperforms the simulated database used so far, and the experimental database obtained from the conventional PSCS algorithm. Crucially, the neural network approach effectively generalizes even when trained with only one known coordinate per interaction, paving the way for simplified 1D scanning procedures.