Universal uncertainty estimation for nuclear detector signals with neural networks and ensemble learning
Abstract
Characterizing uncertainty is a common issue in nuclear measurement and has important implications for reliable physical discovery. Traditional methods are either insufficient to cope with the heterogeneous nature of uncertainty or inadequate to perform well with unknown mathematical models. In this paper, we propose using multi-layer convolutional neural networks for empirical uncertainty estimation and feature extraction of nuclear pulse signals. This method is based on deep learning, a recent development of machine learning techniques, which learns the desired mapping function from training data and generalizes to unseen test data. Furthermore, ensemble learning is utilized to estimate the uncertainty originating from trainable parameters of the network and to improve the robustness of the whole model. To evaluate the performance of the proposed method, simulation studies, in comparison with curve fitting, investigate extensive conditions and show its universal applicability. Finally, a case study is made using data from a NICA-MPD electromagnetic calorimeter module exposed to a test beam at DESY, Germany. The uncertainty estimation method successfully detected out-of-distribution samples and also achieved good accuracy in time and energy measurements.
- Publication:
-
Journal of Instrumentation
- Pub Date:
- February 2022
- DOI:
- 10.1088/1748-0221/17/02/P02032
- arXiv:
- arXiv:2110.04975
- Bibcode:
- 2022JInst..17P2032A
- Keywords:
-
- Analysis and statistical methods;
- Pattern recognition;
- cluster finding;
- calibration and fitting methods;
- Calorimeters;
- Electronic detector readout concepts (solid-state);
- Physics - Data Analysis;
- Statistics and Probability
- E-Print:
- 24 pages, 15 figures. This is the Accepted Manuscript version of an article accepted for publication in Journal of Instrumentation. Neither SISSA Medialab Srl nor IOP Publishing Ltd is responsible for any errors or omissions in this version of the manuscript or any version derived from it. The Version of Record is available online at https://doi.org/10.1088/1748-0221/17/02/P02032