In this thesis I propose a full CNN Single-Telescope Reconstruction analysis chain, for the LST of CTA. I compare both simple and state-of-the-art architectures for gamma/hadron separation, energy and direction reconstruction, showing that our analysis chain significantly outperforms the RF algorithm in all three tasks.

Convolutional Neural Network Single-Telescope Reconstruction for the Large Size Telescope of CTA

Marinello, Nicola
2019/2020

Abstract

In this thesis I propose a full CNN Single-Telescope Reconstruction analysis chain, for the LST of CTA. I compare both simple and state-of-the-art architectures for gamma/hadron separation, energy and direction reconstruction, showing that our analysis chain significantly outperforms the RF algorithm in all three tasks.
2019-07-09
imaging atmospheric, Cherenkov, telescope, neural network, deep learning, gamma-ray, reconstruction, classification, regression
File in questo prodotto:
File Dimensione Formato  
ClassicThesis.pdf

accesso aperto

Dimensione 26.42 MB
Formato Adobe PDF
26.42 MB Adobe PDF Visualizza/Apri

The text of this website © Università degli studi di Padova. Full Text are published under a non-exclusive license. Metadata are under a CC0 License

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.12608/28043