Machine Learning for Single-Ended Event Reconstruction in PROSPECT Experiment
Abstract
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 analysis performance. Furthermore, these machine learning methodologies offer promising applications for other segmented particle detectors, underscoring their versatility and impact.
Keywords
Cite
@article{arxiv.2503.06727,
title = {Machine Learning for Single-Ended Event Reconstruction in PROSPECT Experiment},
author = {M. Andriamirado and A. B. Balantekin and C. D. Bass and O. Benevides Rodrigues and E. P. Bernard and N. S. Bowden and C. D. Bryan and R. Carr and T. Classen and A. J. Conant and G. Deichert and A. Delgado and M. J. Dolinski and A. Erickson and M. Fuller and A. Galindo-Uribarri and S. Gokhale and C. Grant and S. Hans and A. B. Hansell and T. E. Haugen and K. M. Heeger and B. Heffron and D. E. Jaffe and S. Jayakumar and J. Koblanski and P. Kunkle and C. E. Lane and B. R. Littlejohn and A. Lozano Sanchez and X. Lu and F. Machado and J. Maricic and M. P. Mendenhall and A. M. Meyer and R. Milincic and P. E. Mueller and H. P. Mumm and R. Neilson and C. Roca and R. Rosero and D. Venegas-Vargas and J. Wilhelmi and M. Yeh and C. Zhang and X. Zhang},
journal= {arXiv preprint arXiv:2503.06727},
year = {2025}
}
Comments
28 pages, 9 figures