Event reconstruction of Compton telescopes using a multi-task neural network

Abstract

We have developed a neural network model to perform event reconstruction of Compton telescopes. This model reconstructs events that consist of three or more interactions in a detector. It is essential for Compton telescopes to determine the time order of the gamma-ray interactions and whether the incident photon deposits all energy in a detector or it escapes from the detector. Our model simultaneously predicts these two essential factors using a multi-task neural network with three hidden layers of fully connected nodes. For verification, we have conducted numerical experiments using Monte Carlo simulation, assuming a large-area Compton telescope using liquid argon to measure gamma rays with energies up to $3.0\mathrm{MeV}$. The reconstruction model shows excellent performance of event reconstruction for multiple scattering events that consist of up to eight hits. The accuracies of hit order prediction are around $60\%$ while those of escape flags are higher than $70\%$ for up to eight-hit events of $4\pi$ isotropic photons. Compared with two other algorithms, a classical model and a physics-based probabilistic one, the present neural network method shows high performance in estimation accuracy particularly when the number of scattering is small, 3 or 4. Since simulation data easily optimize the network model, the model can be flexibly applied to a wide variety of Compton telescopes.

arXiv comment26 pages, 13 figures, 3 tables, accepted for publication in NIM A

References in corpus (14)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• The Large Area Telescope on the Fermi Gamma-ray Space Telescope Mission
• Deep Learning for Real-time Gravitational Wave Detection and Parameter Estimation: Results with Advanced LIGO Data
• The e-ASTROGAM mission (exploring the extreme Universe with gamma rays in the MeV-GeV range)
• Cobalt-56 gamma-ray emission lines from the type Ia supernova 2014J
• Application of machine learning algorithms to the study of noise artifacts in gravitational-wave data
• Dual MeV Gamma-Ray and Dark Matter Observatory -- GRAMS Project
• Event reconstruction in high resolution Compton telescopes
• The Compton Spectrometer and Imager
• Detection of polarized gamma-ray emission from the Crab nebula with Hitomi Soft Gamma-ray Detector
• Compton scattering sequence reconstruction algorithm for the liquid xenon gamma-ray imaging telescope (LXeGRIT)
• A convolutional neural network approach for reconstructing polarization information of photoelectric X-ray polarimeters
• Bin Mode Estimation Methods for Compton Camera Imaging
• Reconstruction of multiple Compton scattering events in MeV gamma-ray Compton telescopes towards GRAMS: the physics-based probabilistic model

Cited by in corpus (3)

• Reconstruction of multiple Compton scattering events in MeV gamma-ray Compton telescopes towards GRAMS: the physics-based probabilistic model
• First operation of LArTPC in the stratosphere as an engineering GRAMS balloon flight (eGRAMS)
• Enhancing Compton telescope imaging with maximum a posteriori estimation: a modified Richardson-Lucy algorithm for the Compton Spectrometer and Imager