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

In brief: This deep-learning technique was used for saturation corrections in the calorimeter of the DAMPE detector. It was deployed in the cosmic-ray helium flux measurement (PhD thesis) as well as in the proton flux measurement (preliminary), as presented at the 38th ICRC.

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.

Link to paper

Recommended citation: Stolpovskiy, M. et al on behalf of the DAMPE collaboration. Machine learning-based method of calorimeter saturation correction for helium flux analysis with DAMPE experiment. JINST, 17, P06031 (2022).