A neural-network framework for tracking and identifying cosmic-ray nuclei in the RadMap Telescope

The detailed characterization of the radiation environment aboard spacecraft is a prerequisite for assessing shielding requirements and for minimizing the exposure of crew and equipment during future deep-space missions. The scintillating-fiber tracking calorimeter at the heart of the RadMap Telescop e is designed for detailed studies of cosmic rays within the resource constraints of an operational radiation monitor. We present a neural-network framework that can reconstruct the properties of cosmic-ray nuclei traversing the instrument. Employing the G eant 4 simulation toolkit and a simplified model of the detector to generate training and test data, we achieve the spectroscopic capabilities required for an accurate determination of the biologically relevant dose that astronauts receive in space. We can reconstruct the trajectory of a particle with an angular resolution of better than 1.4° and achieve a charge separation of better than 95% for nuclei with Z ≤ 8; specifically, we reach an accuracy of 99.8% for hydrogen. The energy resolution is < 20% for energies below 1 GeV/n and elements up to iron. We also discuss the limitations of our detector, the reconstruction framework, and this feasibility study, as well as possible improvements.