Scientific article

Data-driven detector signal characterization with constrained bottleneck autoencoders

Published inJournal of instrumentation, vol. 17, no. 06, P06016
Publication date2022-06-14
First online date2022-06-14

A common technique in high energy physics is to characterize the response of a detector by means of models tuned to data which build parametric maps from the physical parameters of the system to the expected signal of the detector. When the underlying model is unknown it is difficult to apply this method, and often, simplifying assumptions are made introducing modeling errors. In this article, using a waveform toy model we present how deep learning in the form of constrained bottleneck autoencoders can be used to learn the underlying unknown detector response model directly from data. The results show that excellent performance results can be achieved even when the signals are significantly affected by random noise. The trained algorithm can be used simultaneously to perform estimations on the physical parameters of the model, simulate the detector response with high fidelity and to denoise detector signals.

Citation (ISO format)
JESÚS-VALLS, C., LUX, T., SANCHEZ NIETO, Federico. Data-driven detector signal characterization with constrained bottleneck autoencoders. In: Journal of instrumentation, 2022, vol. 17, n° 06, p. P06016. doi: 10.1088/1748-0221/17/06/p06016
Main files (1)
Article (Submitted version)
ISSN of the journal1748-0221

Technical informations

Creation10/06/2022 10:13:00 AM
First validation10/06/2022 10:13:00 AM
Update time03/16/2023 7:56:19 AM
Status update03/16/2023 7:56:18 AM
Last indexation05/06/2024 11:44:49 AM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack