Re-optimization of a deep neural network model for electron-carbon scattering using new experimental data

Abstract

We present an updated deep neural network model for inclusive electron-carbon scattering. Using the bootstrap model [Phys.Rev.C 110 (2024) 2, 025501] as a prior, we incorporate recent experimental data, as well as older measurements in the deep inelastic scattering region, to derive a re-optimized posterior model. We examine the impact of these new inputs on model predictions and associated uncertainties. Finally, we evaluate the resulting cross-section predictions in the kinematic range relevant to the Hyper-Kamiokande and DUNE experiments.

15 pages, 12 figures, some additional comments added

References in corpus (30)

• A high-bias, low-variance introduction to Machine Learning for physicists
• NuSTEC White Paper: Status and Challenges of Neutrino-Nucleus Scattering
• Physics Potential of a Long Baseline Neutrino Oscillation Experiment Using J-PARC Neutrino Beam and Hyper-Kamiokande
• Final State Interactions Effects in Neutrino-Nucleus Interactions
• Predicting Porosity, Permeability, and Tortuosity of Porous Media from Images by Deep Learning
• Empirical Fit to Precision Inclusive Electron-Proton Cross Sections in the Resonance Region
• Superscaling of Inclusive Electron Scattering from Nuclei
• Bayesian inference and the parametric bootstrap
• Extensions of Superscaling from Relativistic Mean Field Theory: the SuSAv2 Model
• Empirical Fit to Inelastic Electron-Deuteron and Electron-Neutron Resonance Region Transverse Cross Sections
• Neutrino Interactions with Nucleons and Nuclei: Importance for Long-Baseline Experiments
• Improving the accuracy of neutrino energy reconstruction in charged-current quasielastic scattering off nuclear targets
• Inclusive Electron-Nucleus Scattering at Large Momentum Transfer
• Inclusive electron scattering within the SuSAv2-MEC approach
• Inclusive Electron Scattering And The GENIE Neutrino Event Generator
• First Measurement of the Ti$(e,e^{\prime })\mathrm{X}$ Cross Section at Jefferson Lab
• The Proton Radius from Bayesian Inference
• Scaling of the F_2 structure function in nuclei and quark distributions at x>1
• Deep learning for diffusion in porous media
• Nucleon axial form factor from a Bayesian neural-network analysis of neutrino-scattering data
• Two-Photon Exchange Effect Studied with Neural Networks
• Electron Scattering and Neutrino Physics
• Applications of Neural Networks in Hadron Physics
• Extraction of the Coulomb Sum Rule, Transverse Enhancement, and Longitudinal Quenching from an Analysis of all Available e-${}^{12}$C and e-${}^{16}$O Cross Section Data
• Neural Network predictions of inclusive electron-nucleus cross sections
• Contribution of Nuclear Excitation Electromagnetic Form Factors in ${}^{12}\mathrm{C}$ and ${}^{16}\mathrm{O}$ to the Coulomb Sum Rule
• Implementation and investigation of electron-nucleus scattering in the \textsc{NEUT} neutrino event generator
• Electroweak Single Pion Production and Form Factors of the Δ(1232) Resonance
• Electron-nucleus cross sections from transfer learning
• Machine Learning-Assisted Unfolding for Neutrino Cross-section Measurements with the OmniFold Technique