Neural-based reconstruction of radioactivity distribution in large water volumes with underwater gliders

This work focuses on the problem of reconstructing the 3D distribution of radioactivity in large water volumes based on measurements collected with underwater gliders. We present a high-level simulation environment to study radioactivity reconstruction accuracy and efficiency considering different reference radioactivity distributions and under different types of glider trajectories, also taking into account the limitations of radioactivity detection in the water. A neural-based sampling approach is adopted for reconstructing the radioactivity distribution based on the highly sparse measurements.