What question did this study set out to answer?

The aim is to enhance anomaly detection in LZ dark matter experiment data using autoencoders.

February 5, 20260 citations

Anomaly Detection using Autoencoders on Fundamental LZ Signals

TATyler Anderson MAMaris Arthurs MMMaria Elena Monzani

Key Points

The aim is to enhance anomaly detection in LZ dark matter experiment data using autoencoders.
Utilized autoencoders to analyze PMT waveforms for ionization signals (S2)
Identified unresolved S2 signals from multiple scatter interactions
Extended analysis to scintillation light (S1) PMT waveforms
Investigated latent spaces of variational autoencoders (VAEs) for anomaly detection
Successfully detected previously unresolved S2 signals
Improved methods for identifying anomalies in S1 PMT waveforms
Demonstrated the effectiveness of autoencoders in minimizing reconstruction errors

Abstract

Searching for anomalous data is especially important in rare event searches like that of the LUX-ZEPLIN (LZ) experiment’s hunt for dark matter. While LZ’s data processing provides analyzer-friendly features for all data, searching for anomalous data after minimal reconstruction allows one to find anomalies not captured by reconstructed features, agnostic to any reconstruction errors. Autoencoders can be used to probe for anomalous light-detecting photomultiplier tube (PMT) waveforms resulting from ionization signals (S2) and have found unresolved S2s resulting from multiple scatter interactions. These techniques can be extended by applying them to prompt scintillation light (S1) PMT waveforms and by analyzing the latent-spaces of variational autoencoders (VAEs).

问 AI

Bookmark

View Full Paper