7–9 Jan 2026
King's College London
Europe/London timezone

Data-Driven PMT Calibration of Large Liquid Detectors with Unsupervised Learning

8 Jan 2026, 10:32
13m
Safra Lecture Theatre (King's College London)

Safra Lecture Theatre

King's College London

Speaker

Scott DeGraw (University of Oxford)

Description

Event reconstruction in large liquid scintillator neutrino detectors, such as SNO+, rely on hit times from large numbers of photomultiplier tubes (PMTs). We demonstrate a novel method to extract PMT calibration timing constants from physics data using the machinery of unsupervised deep learning. The approach uses a simplified physical model of optical photon transport in the loss function with PMT calibration constants treated as free parameters and the simple assumption that individual events represent point-like emission. The problem is effectively reduced to that of regression on a very large scale made tractable by deep learning architectures and automatic differentiation frameworks. Using data from the SNO+ detector, the method has been shown to reliably extract 4 calibration constants for each PMT using radioactive background events. We believe that this basic approach can be straightforwardly generalised for a wide range of applications.

Author

Scott DeGraw (University of Oxford)

Presentation materials