Searching for EeV photons with Telescope Array Surface Detector and neural networks

Abstract

Ultra-high-energy photons play an important role in probing astrophysical models and beyond-Standard-Model scenarios. We report updated limits on the diffuse photon flux using Telescope Array's Surface Detector data collected over 14 years of operation. Our method employs a neural network classifier to effectively distinguish between proton-induced and photon-induced events. The input data include both reconstructed composition-sensitive parameters and raw time-resolved signals registered by the Surface Detector stations. To mitigate biases from Monte Carlo simulations, we fine-tune the network with a subset of experimental data. The number of observed photon candidates is found to be consistent with the expected hadronic background, yielding upper limits on photon flux $\hat{I}{¦}_{\hat{I}}^3(E_{\hat{I}}^3>10^{19}\text{eV})<2.3\cdot 10^{-3}$, and $\hat{I}{¦}_{\hat{I}}^3(E_{\hat{I}}^3>10^{20}\text{eV})<3.0\cdot 10^{-4}$ $({\text{km}}^2\cdot \text{sr}\cdot \text{yr}{)}^{-1}$.