Event Selection and Background Rejection in Time Projection Chambers Using Convolutional Neural Networks and a Specific Application to the AdEPT Gamma-ray Polarimeter Mission

TL;DR

This paper presents GammaNet, a convolutional neural network designed for on-board event classification in a gamma-ray polarimeter, significantly reducing data rates and improving background rejection for space-based gamma-ray detection.

Contribution

Introduction of GammaNet, a CNN that classifies events in a time projection chamber for gamma-ray polarimetry, enabling efficient data transmission and background discrimination in space missions.

Findings

GammaNet achieves background rejection requirements for cosmic ray protons.

Signal sensitivity varies with downlink speed, from ~1% to 69%.

Feature visualization enhances understanding of GammaNet's focus on relevant event features.

Abstract

The Advanced Energetic Pair Telescope gamma-ray polarimeter uses a time projection chamber for measuring pair production events and is expected to generate a raw instrument data rate four orders of magnitude greater than is transmittable with typical satellite data communications. GammaNet, a convolutional neural network, proposes to solve this problem by performing event classification on-board for pair production and background events, reducing the data rate to a level that can be accommodated by typical satellite communication systems. In order to train GammaNet, a set of 1.1x10^6 pair production events and 10^6 background events were simulated for the Advanced Energetic Pair Telescope using the Geant4 Monte Carlo code. An additional set of 10^3 pair production and 10^5 background events were simulated to test GammaNet's capability for background discrimination. With optimization, GammaNet has achieved the proposed background rejection requirements for Galactic Cosmic Ray proton events. Given the best case assumption for downlink speeds, signal sensitivity for pair production ranged between 1.1 +/- 0.5% to 69 +/- 2% for 5 and 250 MeV incident gamma rays. This range became 0.1 +/- 0.1% to 17 +/- 2% for the worst case scenario of downlink speeds. The application of a feature visualization algorithm to GammaNet demonstrated decreased response to electronic noise and events exiting or entering the frame and increased response to parallel tracks that are close in proximity. GammaNet has been successfully implemented and shows promising results.