Deep Learning the Effects of Photon Sensors on the Event Reconstruction Performance in an Antineutrino Detector
Residual curves for (a) and (b) as a function of the number of PMTs used in the reconstruction. The results plotted as solid squares are those from the brute force search. An empirical fit to the bottleneck DNN results was done with a triple exponential. Resolutions from random choice of PMTs are shown as empty squares. A zoom-in on the residual curves is also shown in the figures.