Machine learning-based method of calorimeter saturation correction for helium flux analysis with DAMPE experiment

TL;DR

This paper introduces a machine learning method to correct calorimeter saturation effects in DAMPE space experiment data, enabling accurate cosmic-ray flux measurements at very high energies.

Contribution

It presents a novel machine learning approach to compensate for calorimeter saturation in DAMPE, improving energy measurement accuracy at ultra-high energies.

Findings

Effective saturation correction demonstrated on DAMPE data.

Enhanced accuracy in cosmic-ray flux measurements at energies above tens of TeV.

Machine learning approach outperforms traditional correction methods.

Abstract

DAMPE is a space-borne experiment for the measurement of the cosmic-ray fluxes at energies up to around 100 TeV per nucleon. At energies above several tens of TeV, the electronics of DAMPE calorimeter would saturate, leaving certain bars with no energy recorded. In the present work we discuss the application of machine learning techniques for the treatment of DAMPE data, to compensate the calorimeter energy lost by saturation.