Energy reconstruction for large liquid scintillator detectors with machine learning techniques: aggregated features approach
This work addresses energy reconstruction for neutrino detection in experiments like JUNO, offering a domain-specific improvement with incremental advancements in feature engineering.
The paper tackled the challenge of achieving fine energy resolution in large liquid scintillator detectors like JUNO by applying machine learning models, such as Boosted Decision Trees and Fully Connected Deep Neural Networks, to aggregated features from photo-multiplier tube data, resulting in an energy resolution of 3% at 1 MeV.
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 $σ= 3\%$ 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.