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

TL;DR

This paper applies machine learning techniques, specifically Boosted Decision Trees and Deep Neural Networks, to improve energy reconstruction in large liquid scintillator detectors like JUNO, achieving a 3% energy resolution at 1 MeV.

Contribution

It introduces an aggregated features approach combined with ML models for enhanced energy resolution in large-scale neutrino detectors, demonstrating significant improvements over traditional methods.

Findings

ML models achieve 3% energy resolution at 1 MeV

Feature engineering is crucial for model performance

Models trained on Monte Carlo data effectively reconstruct energy

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.