Deep Learning-Based Energy Reconstruction of Cosmic Muons in mini-ICAL Detector

The mini-ICAL is a magnetized prototype of the proposed iron calorimeter (ICAL) detector of the upcoming India-Based Neutrino Observatory (INO). The mini-ICAL is designed to study the performance of Resistive Plate Chambers (RPCs) in a magnetic field and the efficiency of reconstruction algorithms. In this study, we investigate the possibility of using a deep learning-based algorithm for muon energy reconstruction in the detector. Deep learning models were developed using the data generated from a simplified geometry of mini-ICAL simulated using the Geant4 package. The models are evaluated for their accuracy in predictions and reconstruction time.