First Full-Event Reconstruction from Imaging Atmospheric Cherenkov Telescope Real Data with Deep Learning

Mikaël Jacquemont (1) , Thomas Vuillaume (1) , Alexandre Benoit (2) , Gilles Maurin (1) , Patrick Lambert (2) , Giovanni Lamanna (1)

1 LAPP - Laboratoire d'Annecy de Physique des Particules
2 LISTIC - Laboratoire d'Informatique, Systèmes, Traitement de l'Information et de la Connaissance

The Cherenkov Telescope Array is the future of ground-based gamma-ray astronomy. Its first prototype telescope built on-site, the Large Size Telescope 1, is currently under commissioning and taking its first scientific data. In this paper, we present for the first time the development of a full-event reconstruction based on deep convolutional neural networks and its application to real data. We show that it outperforms the standard analysis, both on simulated and on real data, thus validating the deep approach for the CTA data analysis. This work also illustrates the difficulty of moving from simulated data to actual data.

Mots clés: deep learning; gamma astronomy; multitasking; learning bias; model generalization to real data

Domaines: Intelligence artificielle [cs.AI]; Réseau de neurones [cs.NE]; Astrophysique [astro-ph]; Instrumentation et méthodes pour l'astrophysique [astro-ph.IM]; Apprentissage [cs.LG]

Mikaël Jacquemont, Thomas Vuillaume, Alexandre Benoit, Gilles Maurin, Patrick Lambert, et al.. First Full-Event Reconstruction from Imaging Atmospheric Cherenkov Telescope Real Data with Deep Learning. International Conference on Content-Based Multimedia Indexing (CBMI), Jun 2021, Lille, France. 6 p., ⟨10.1109/CBMI50038.2021.9461918⟩. ⟨hal-03241475v2⟩