Transfer Learning for Neutrino Scattering: Domain Adaptation with GANs

TL;DR

This paper demonstrates that transfer learning with GANs effectively models neutrino-nucleus interactions across different targets and models, outperforming traditional training methods especially with limited data, and aids in developing advanced neutrino event generators.

Contribution

It introduces a transfer learning approach using GANs to adapt neutrino scattering models across different nuclei and interaction models, improving accuracy with limited data.

Findings

TL reproduces key lepton kinematic features.

TL outperforms models trained from scratch.

High accuracy maintained with limited event data.

Abstract

Transfer learning (TL) is used to extrapolate the physics information encoded in a Generative Adversarial Network (GAN) trained on synthetic neutrino-carbon inclusive scattering data to related processes such as neutrino-argon and antineutrino-carbon interactions. We investigate how much of the underlying lepton-nucleus dynamics is shared across different targets and processes. We also assess the effectiveness of TL when training data is obtained from a different neutrino-nucleus interaction model. Our results show that TL not only reproduces key features of lepton kinematics, including the quasielastic and $\Delta$-resonance peaks, but also significantly outperforms generative models trained from scratch. Using data sets of 10,000 and 100,000 events, we find that TL maintains high accuracy even with limited statistics. Our findings demonstrate that TL provides a well-motivated and efficient framework for modeling (anti)neutrino-nucleus interactions and for constructing next-generation neutrino-scattering event generators, particularly valuable when experimental data are sparse.