Abstract
The Jiangmen Underground Neutrino Observatory (JUNO) is a neutrino experiment with a broad physical program. The main goals of JUNO are the determination of the neutrino mass ordering and high precision investigation of neutrino oscillation properties. The precise reconstruction of the event energy is crucial for the success of the experiment. JUNO is equiped with 17 612 + 25 600 PMT channels of two kind which provide both charge and hit time information. In this work we present a fast Boosted Decision Trees model using small set of aggregated features. The model predicts event energy deposition. We describe the motivation and the details of our feature engineering and feature selection procedures. We demonstrate that the proposed aggregated approach can achieve a reconstruction quality that is competitive with the quality of much more complex models like Convolution Neural Networks (ResNet, VGG and GNN).
Highlights
Jiangmen Underground Neutrino Observatory (JUNO) is a neutrino observatory under construction in southern China
Earlier we demonstrated that the Machine Learning (ML) approach can have the quality required for the JUNO experiment on our data and has the advantage of speed and ease of application [4]
In this work we use Boosted Decision Trees (BDT) [5] for energy reconstruction in the energy range of 0–10 MeV covering the region of interest for inverse beta-decay (IBD) events from reactor electron antineutrinos
Summary
JUNO is a neutrino observatory under construction in southern China. Its physical program covers a wide range of problems [1]. Neutrinos, which are produced in nuclear reactors, interact with the protons of the scintillator in the detector via the inverse beta-decay (IBD) channel: νe + p → e+ + n. To resolve the neutrino mass ordering the energy resolution must be σ 3% at 1 MeV, which is very close to the statistical limit corresponding to the light yield in JUNO, about 1300 detected photons (hits) at 1 MeV. We use ML approach for energy reconstruction in the JUNO experiment. The data (time and charge information) collected by PMTs is used as input for supervised training of ML model. In this work we use Boosted Decision Trees (BDT) [5] for energy reconstruction in the energy range of 0–10 MeV covering the region of interest for IBD events from reactor electron antineutrinos. Compared to [4] we designed and studied new features and achieved much better resolution with BDT, which is comparable to the resolution of more complex models
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have