Neural Network-Based Estimation of Muon Content from Data Recorded by the SD-1500 of the Pierre Auger Observatory

Ultra-high-energy cosmic rays (UHECRs) offer insights into the physics beyond the energies of human-made accelerators. However, to fully understand processes such as their acceleration, precise knowledge of their mass composition is crucial. Since the direct detection of UHECRs is infeasible, determining the mass of the primary particles is challenging. One method of accessing this information is to estimate the number of muons produced in extensive air showers (EASs). The direct measurement of high-energy muons in an EAS can be achieved by using arrays of buried detectors, such as the Underground Muon Detector (UMD) at the Pierre Auger Observatory. However, the instrumentation area of the UMD is limited in size. One of the central components of the Pierre Auger Observatory is the Surface Detector (SD), which consists of multiple triangular grids of hybrid detector stations. These stations record the time signals of the secondary particles that are produced in EASs that reach the ground. In this contribution, we present a neural network (NN) that utilizes SD-1500 data, the main surface detector array of the Pierre Auger Observatory, to predict the muon content of EASs. ... mehrThis NN is calibrated indirectly to the UMD measurements using a calibrated NN designed for the SD-750, the second-largest surface detector array located near the UMD.