Machine Learning Neutrino-Nucleus Cross Sections

TL;DR

This paper demonstrates that neural networks trained on near-detector data can accurately model neutrino-nucleus cross sections, significantly improving oscillation analysis precision and highlighting the potential of data-driven approaches in neutrino physics.

Contribution

It introduces a neural-network-based method to model neutrino-nucleus cross sections using only Standard-Model symmetries, trained on near-detector data, for improved oscillation analysis.

Findings

Neural network models can learn accurate cross sections from near-detector data.

Data-driven models approach the theoretical limit of cross-section knowledge.

The approach is robust against flux, resolution, and systematic uncertainties.

Abstract

Neutrino-nucleus scattering cross sections are critical theoretical inputs for long-baseline neutrino oscillation experiments. However, robust modeling of these cross sections remains challenging. For a simple but physically motivated toy model of the DUNE experiment, we demonstrate that an accurate neural-network model of the cross section -- leveraging only Standard-Model symmetries -- can be learned from near-detector data. We perform a neutrino oscillation analysis with simulated far-detector events, finding that oscillation analysis results enabled by our data-driven cross-section model approach the theoretical limit achievable with perfect prior knowledge of the cross section. We further quantify the effects of flux shape and detector resolution uncertainties as well as systematics from cross-section mismodeling. This proof-of-principle study highlights the potential of future neutrino near-detector datasets and data-driven cross-section models.