Inference of the Mass Composition of Cosmic Rays with energies from 10^18.5 to 10^20 eV using the Pierre Auger Observatory and Deep Learning

We present measurements of the atmospheric depth of the shower maximum X_max, inferred for the first time on an event-by-event level using the Surface Detector of the Pierre Auger Observatory. Using deep learning, we were able to extend measurements of the X_max distributions up to energies of 100 EeV (10^20 eV), not yet revealed by current measurements, providing new insights into the mass composition of cosmic rays at extreme energies. Gaining a 10-fold increase in statistics compared to the Fluorescence Detector data, we find evidence that the rate of change of the average X_max with the logarithm of energy features three breaks at 6.5±0.6 (stat)±1 (sys) EeV, 11± 2 (stat)±1 (sys) EeV, and 31±5 (stat)±3 (sys) EeV, in the vicinity to the three prominent features (ankle, instep, suppression) of the cosmic-ray flux. The energy evolution of the mean and standard deviation of the measured X_max distributions indicates that the mass composition becomes increasingly heavier and purer, thus being incompatible with a large fraction of light nuclei between 50 EeV and 100 EeV.