Energy reconstruction for large liquid scintillator detectors with machine learning techniques: aggregated features approach

Abstract

Large-scale detectors consisting of a liquid scintillator target surrounded by an array of photo-multiplier tubes (PMTs) are widely used in the modern neutrino experiments: Borexino, KamLAND, Daya Bay, Double Chooz, RENO, and the upcoming JUNO with its satellite detector TAO. Such apparatuses are able to measure neutrino energy which can be derived from the amount of light and its spatial and temporal distribution over PMT channels. However, achieving a fine energy resolution in large-scale detectors is challenging. In this work, we present machine learning methods for energy reconstruction in the JUNO detector, the most advanced of its type. We focus on positron events in the energy range of 0-10 MeV which corresponds to the main signal in JUNO -- neutrinos originated from nuclear reactor cores and detected via the inverse beta decay channel. We consider the following models: Boosted Decision Trees and Fully Connected Deep Neural Network, trained on aggregated features, calculated using the information collected by PMTs. We describe the details of our feature engineering procedure and show that machine learning models can provide the energy resolution $\sigma =3\%$ at 1 MeV using subsets of engineered features. The dataset for model training and testing is generated by the Monte Carlo method with the official JUNO software.

This is a post-peer-review, pre-copyedit version of an article published in Eur. Phys. J. C. The final published version is available online: https://link.springer.com/article/10.1140/epjc/s10052-022-11004-6

References in corpus (20)

• XGBoost: A Scalable Tree Boosting System
• First Results from KamLAND: Evidence for Reactor Anti-Neutrino Disappearance
• Observation of electron-antineutrino disappearance at Daya Bay
• Observation of Reactor Electron Antineutrino Disappearance in the RENO Experiment
• Indication for the disappearance of reactor electron antineutrinos in the Double Chooz experiment
• Neutrino Physics with JUNO
• Deep Neural Networks and Tabular Data: A Survey
• A survey on modern trainable activation functions
• Deep Learning and its Application to LHC Physics
• Science and Technology of BOREXINO: A Real Time Detector for Low Energy Solar Neutrinos SOLAR NEUTRINOS
• An Empirical Analysis of Feature Engineering for Predictive Modeling
• Machine and Deep Learning Applications in Particle Physics
• Sub-percent Precision Measurement of Neutrino Oscillation Parameters with JUNO
• Calibration Strategy of the JUNO Experiment
• Modern Machine Learning and Particle Physics
• Vertex and Energy Reconstruction in JUNO with Machine Learning Methods
• Event vertex and time reconstruction in large volume liquid scintillator detector
• The Application of SNiPER to the JUNO Simulation
• Parallelized JUNO simulation software based on SNiPER
• The use of Boosted Decision Trees for Energy Reconstruction in JUNO experiment