Deep-Learning-Based Kinematic Reconstruction for DUNE

Abstract

In the framework of three-active-neutrino mixing, the charge parity phase, the neutrino mass ordering, and the octant of θ 23 remain unknown. The Deep Underground Neutrino Experiment (DUNE) is a next-generation long-baseline neutrino oscillation experiment, which aims to address these questions by measuring the oscillation patterns of ν µ /ν e and νµ /ν e over a range of energies spanning the first and second oscillation maxima. DUNE far detector modules are based on liquid argon TPC (LArTPC) technology. A LArTPC offers excellent spatial resolution, high neutrino detection efficiency, and superb background rejection, while reconstruction in LArTPC is challenging. Deep learning methods, in particular, Convolutional Neural Networks (CNNs), have demonstrated success in classification problems such as particle identification in DUNE and other neutrino experiments. However, reconstruction of neutrino energy and final state particle momenta with deep learning methods is yet to be developed for a full AI-based reconstruction chain. To precisely reconstruct these kinematic characteristics of detected interactions at DUNE, we have developed and will present two CNN-based methods, 2-D and 3-D, for the reconstruction of final state particle direction and energy, as well as neutrino energy. Combining particle masses with the kinetic energy and the direction reconstructed by our work, the four-momentum of final state particles can be obtained. Our models show considerable improvements compared to the traditional methods for both scenarios.

Bias and Priors in Machine Learning Calibrations for High Energy Physics

“…6b we show results from a maximum likelihood-based calibration trained on the QCD sample, using the Gaussian Ansatz in Eq. (35). The A, B, C, and D networks of the Gaussian Ansatz each consist of three hidden layers with 32 nodes per layer, with the same activation functions, batch size, and epochs as in the Gaussian example.…”

“…In particular, machine learning methods can readily process high-dimensional inputs and therefore can incorporate more information to improve the precision and accuracy of a calibration. There have been a large number of proposals for improving the simulationbased calibrations of various object energies, including single hadrons [16][17][18][19][20][21], muons [22], and jets [23][24][25][26][27][28][29][30][31][32][33] at colliders; kinematic reconstruction in deep inelastic scattering [34]; and neutrino energies in a variety of experiments [35][36][37][38][39][40]. Further ideas can be found in Ref.…”

Machine Learning in the Search for New Fundamental Physics

“…The DUNE collaboration is exploring the use of CNNs for neutrino interaction classification that allows for simultaneous identification and classification of neutrino interaction final states and neutrino interaction type [211], while kinematics reconstruction with the use of 2D and 3D regression CNNs has been proposed in [212]. Micro-BooNE was first to demonstrate the successful use and advantages of CNNs for classifying signal vs. background images, where signal images contain particles produced by a neutrino interaction [213].…”

Constraining nuclear effects in Argon using machine learning algorithms

“…MLAs like Deep learning are being used for interaction vertex reconstruction [25] and kinematic reconstruction [26].…”