Deep Learning the Effects of Photon Sensors on the Event Reconstruction Performance in an Antineutrino Detector

TL;DR

This paper introduces a deep learning approach to evaluate how photon sensors affect event reconstruction in antineutrino detectors, aiding detector design and upgrade decisions efficiently.

Contribution

It presents a novel deep learning method to assess photon sensor impacts on detector performance, specifically analyzing PMT importance and coverage effects on vertex resolution.

Findings

PMT importance varies for vertex reconstruction

Vertex resolution follows a multi-exponential relation with PMT count

Method can inform future detector upgrade strategies

Abstract

We provide a fast approach incorporating the usage of deep learning for evaluating the effects of photon sensors in an antineutrino detector on the event reconstruction performance therein. This work is an attempt to harness the power of deep learning for detector designing and upgrade planning. Using the Daya Bay detector as a benchmark case and the vertex reconstruction performance as the objective for the deep neural network, we find that the photomultiplier tubes (PMTs) have different relative importance to the vertex reconstruction. More importantly, the vertex position resolutions for the Daya Bay detector follow approximately a multi-exponential relationship with respect to the number of PMTs and hence, the coverage. This could also assist in deciding on the merits of installing additional PMTs for future detector plans. The approach could easily be used with other objectives in place of vertex reconstruction.