Logo image
Back
Machine Learning for Single-Ended Event Reconstruction in PROSPECT Experiment
Preprint

Machine Learning for Single-Ended Event Reconstruction in PROSPECT Experiment

M Andriamirado, A. B Balantekin, C. D Bass, O. Benevides Rodrigues, E. P Bernard, N. S Bowden, C. D Bryan, R Carr, T Classen, A. J Conant, …
09 Mar 2025
DOI: https://doi.org/10.48550/arxiv.2503.06727
url
https://doi.org/10.48550/arxiv.2503.06727View
Open

Abstract

Physics - Data Analysis, Statistics and Probability Physics - High Energy Physics - Experiment Physics - Instrumentation and Detectors Physics - Nuclear Experiment
The Precision Reactor Oscillation and Spectrum Experiment, PROSPECT, was a segmented antineutrino detector that successfully operated at the High Flux Isotope Reactor in Oak Ridge, TN, during its 2018 run. Despite challenges with photomultiplier tube base failures affecting some segments, innovative machine learning approaches were employed to perform position and energy reconstruction, and particle classification. This work highlights the effectiveness of convolutional neural networks and graph convolutional networks in enhancing data analysis. By leveraging these techniques, a 3.3% increase in effective statistics was achieved compared to traditional methods, showcasing their potential to improve performance. Furthermore, these machine learning methodologies offer promising applications for other segmented particle detectors, underscoring their versatility and impact.

Metrics

8 Record Views

Details

Logo image