A deep learning method for the trajectory reconstruction of gamma rays with the DAMPE space mission
The Dark Matter Particle Explorer (DAMPE), a satellite-borne experiment capable of detecting gamma rays from few GeV to 10 TeV, studies the galactic and extragalactic gamma-ray sky and is at the forefront of the search for dark-matter spectral lines in the gamma-ray spectrum.
This report details the development of a convolutional neural network (CNN) model for the trajectory reconstruction of gamma rays. Four distinct models were trained with Monte-Carlo gamma-ray events, each taking a different resolution Hough image of the silicon-tungsten tracker converter (STK) as input. The performance of the standalone and sequential application of the trained models was benchmarked using MC data, and a proof-of-concept with flight data was realized. The results indicate that the developed CNN is a viable approach for gamma-ray track reconstruction. Further studies are ongoing to push the CNN performance beyond the conventional Kalman algorithm.
pdm_parzival_nussbaum.pdf
main document
openaccess
N/A
10.99 MB
Adobe PDF
78547fbfe4c1a036afdc07a37a84e0dd