Proposal of the FPGA Neural Network Trigger for a Recognition of Chemical Composition of the Ultra High-Energy Cosmic Rays in the Pierre Auger Surface Detector

The standard first-level trigger in the Pierre Auger Observatory surface detectors (data analysis in FPGAs immediately after digitization in ADCs) were developed when FPGAs were relatively simple and additionally expensive. Thus algorithms developed in 90’s of the previous century are relatively simple. Huge progress in electronics allows the implementation of very sophisticated mathematical algorithms in very efficient systems and relatively inexpensive FPGAs. A neural network is an alternative trigger developed recently for recognition neutrino-induced showers gave relatively high efficiency and allowed distinguishing signal profiles from Auger photo-multiplier tubes of water-Cherenkov detectors originating from atmospheric showers induced by high-background neutrinos from other showers. The chemical composition of ultra high-energy cosmic rays (UHECR) is sophisticated and still not known. Additional tool analyzing online in real time a potential chemical composition could help fix this problem.