English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

In neutrino experiments, neutrino energy reconstruction is crucial becauseneutrino oscillations and differential cross-sections are functions of neutrinoenergy. It is also challenging due to the complexity in the detector responseand kinematics of final state particles. We propose a regression ConvolutionalNeural Network (CNN) based method to reconstruct electron neutrino energy andelectron energy in the NOvA neutrino experiment. We demonstrate that with rawdetector pixel inputs, a regression CNN can reconstruct event energy even withcomplicated final states involving lepton and hadrons. Compared withkinematics-based energy reconstruction, this method shows a significantlybetter energy resolution. The reconstructed to true energy ratio showscomparable or less dependence on true energy, hadronic energy fractions, andinteraction modes. The regression CNN also shows smaller systematicuncertainties from the simulation of neutrino interactions. The proposed energyestimator provides improvements of $16\%$ and $12\%$ in RMS for $\nu_e$ CC andelectron, respectively. This method can also be extended to solve otherregression problems in HEP, taking over kinematics-based reconstruction tasks.

Improved Energy Reconstruction in NOvA with Regression Convolutional Neural Networks