Speaker
Description
The Fluorescence detector Array of Single-pixel Telescopes (FAST) is a next-generation cosmic ray experiment aiming to deploy an array of low-cost, autonomous fluorescence telescopes for observing UHECRs. FAST reconstructs the properties of air showers using a top-down approach, where simulated photomultiplier traces are directly compared to data. This process is called the "top-down reconstruction" and requires an accurate first guess of the shower parameters for successful minimisation. In this contribution, we show the performance of the full FAST reconstruction process using a neural network to provide a first guess to the top-down reconstruction. The method is evaluated using the current and near future FAST prototype installations in simulations before being applied to FAST events observed in coincidence with the Telescope Array experiment.
