Deep Learning for Vertex Reconstruction of Neutrino-Nucleus Interaction Events with Combined Energy and Time Data

Conference · 17 April 2019

DOI:https://doi.org/10.1109/ICASSP.2019.8683736· OSTI ID:1542973

Song, Linghao ^[1]; Chen, Fan ^[1]; Young, Steven R. ^[2]; Schuman, Catherine D. ^[2]; Perdue, Gabriel ^[3]; Potok, Thomas E. ^[2]

---

1. Duke U.
2. Oak Ridge
3. Fermilab

We present a deep learning approach for vertex reconstruction of neutrino-nucleus interaction events, a problem in the domain of high energy physics. In this approach, we combine both energy and timing data that are collected in the MINERvA detector to perform classification and regression tasks. We show that the resulting network achieves higher accuracy than previous results while requiring a smaller model size and less training time. In particular, the proposed model outperforms the state-of-the-art by 4.00% on classification accuracy. For the regression task, our model achieves 0.9919 on the coefficient of determination, higher than the previous work (0.96).

• Research Organization: Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States); Fermi National Accelerator Laboratory (FNAL), Batavia, IL (United States)
• Sponsoring Organization: USDOE Office of Science (SC), High Energy Physics (HEP) (SC-25)
• DOE Contract Number: AC02-07CH11359
• OSTI ID: 1542973
• Report Number(s): arXiv:1902.00743; FERMILAB-CONF-19-338-QIS; 1718416
• Country of Publication: United States
• Language: English