Application of machine learning techniques to lepton energy reconstruction in water Cherenkov detectors

TL;DR

This paper demonstrates that machine learning significantly improves lepton energy reconstruction in water Cherenkov detectors, offering a versatile and more accurate alternative to traditional methods.

Contribution

It introduces machine learning techniques for lepton energy reconstruction in water Cherenkov detectors, showing over 50% improvement in energy resolution compared to lookup table methods.

Findings

Over 50% improvement in energy resolution.

Machine learning methods are adaptable to various detector configurations.

Results are comparable to existing likelihood-based techniques.

Abstract

The application of machine learning techniques to the reconstruction of lepton energies in water Cherenkov detectors is discussed and illustrated for TITUS, a proposed intermediate detector for the Hyper-Kamiokande experiment. It is found that applying these techniques leads to an improvement of more than 50% in the energy resolution for all lepton energies compared to an approach based upon lookup tables. Machine learning techniques can be easily applied to different detector configurations and the results are comparable to likelihood-function based techniques that are currently used.