Towards an automated data cleaning with deep learning in CRESST

Abstract

The CRESST experiment employs cryogenic calorimeters for the sensitive measurement of nuclear recoils induced by dark matter particles. The recorded signals need to undergo a careful cleaning process to avoid wrongly reconstructed recoil energies caused by pile-up and read-out artefacts. We frame this process as a time series classification task and propose to automate it with neural networks. With a data set of over one million labeled records from 68 detectors, recorded between 2013 and 2019 by CRESST, we test the capability of four commonly used neural network architectures to learn the data cleaning task. Our best performing model achieves a balanced accuracy of 0.932 on our test set. We show on an exemplary detector that about half of the wrongly predicted events are in fact wrongly labeled events, and a large share of the remaining ones have a context-dependent ground truth. We furthermore evaluate the recall and selectivity of our classifiers with simulated data. The results confirm that the trained classifiers are well suited for the data cleaning task.

12 pages, 8 figures, 6 tables

References in corpus (4)

• Testing spin-dependent dark matter interactions with lithium aluminate targets in CRESST-III
• Deep learning based pulse shape discrimination for germanium detectors
• Cait: analysis toolkit for cryogenic particle detectors in Python
• Application of deep learning to the evaluation of goodness in the waveform processing of transition-edge sensor calorimeters

Cited by in corpus (4)

• Insights into Dark Matter Direct Detection Experiments: Decision Trees versus Deep Learning
• Bayesian technique to combine independently-trained Machine-Learning models applied to direct dark matter detection
• Scintillation pulse characterization with spectrum-inspired temporal neural networks: case studies on particle detector signals
• Optimal operation of cryogenic calorimeters through deep reinforcement learning