Machine Learning Techniques for the EUSO-SPB2 Fluorescence Telescope

Abstract

The Extreme Universe Space Observatory on a Super Pressure Balloon 2 (EUSO-SPB2) is the most advanced balloon mission undertaken by the JEM-EUSO collaboration. EUSO-SPB2 is built on the experience of previous stratosphere missions, EUSO-Balloon and EUSO-SPB, and of the Mini-EUSO space mission currently active onboard the International Space Station. EUSO-SPB2 is equipped with two instruments: a fluorescence telescope aimed at registering ultra-high energy cosmic rays (UHECRs) with an energy above 2 EeV and a Cherenkov telescope built to measure direct Cherenkov emission from cosmic rays with energies above 1 PeV. The EUSO-SPB2 mission will provide pioneering observations on the path towards a space-based multi-messenger observatory. As such, a special attention was paid to the development of triggers and other software aimed at comprehensive data analysis. A whole number of methods based on machine learning (ML) and neural networks was developed during the construction of the experiment and a few others are under active development. Here we provide a brief review of the ML-based methods already implemented in the instrument and the ground software and report preliminary results on the ML-based reconstruction of UHECR parameters for the fluorescence telescope.

Overview and First Results of EUSO-SPB2

“…A central data processor [5] connects the 3 PDMs and enables a synchronized readout if one PDM triggers. In addition to combining the photo count data of all PDMs, it adds GPS information to each event and prioritizes the events for download using a neural network trained on simulation before the flight (see [6]).…”