ИСТИНА

The aim of extensive air shower (EAS) analysis is to reconstruct the physical parameters of the primary particle that initiated the shower. The TAIGA experiment is a hybrid detector system that combines several telescopes and arrays of detector stations to record and analyze EAS data. At present, data from the telescopes and the detector station arrays is analyzed by deriving different sets of auxiliary parameters related to the physical features of the recording hardware. These sets of parameters are chosen empirically, so there is no certainty that they retain all important information contained in the experimental data and are the best suited for the respective problems. Moreover, because the event parameters recorded by different detector types differ in physical nature, their direct merging is unfeasible, which complicates multimodal analysis. We propose to use autoencoders (AE) for the analysis of TAIGA experimental data and replace the conventionally used auxiliary parameters with the parameters of the AE latent space. The advantage of the AE latent space parameters is that they are not biased by pre-established assumptions and constraints and still contain in a compressed form the physical information obtained directly from the experimental data. A separate artificial neural network is used to reconstruct the parameters of the EAS primary particle from the AE latent space parameters. In this paper, the proposed approach is used to reconstruct the energy of the EAS primary particle based on Monte Carlo simulation data for the TAIGA-HiSCORE detector array. The dependence of the energy determination accuracy on the latent space dimension is analyzed, and these results are also compared with the results obtained by the conventional method. For events recorded by TAIGA-HiSCORE, it is shown that when using the AE latent space, the energy of the primary particle is reconstructed with satisfactory accuracy.