Jose Bonila

:As we enter the „precision era” in neutrino physics, it is essential to better understand and constrain systematic uncertainties. With the increase in statistics and measurement quality, the uncertainties arising from Monte Carlo (MC) generators, which are used throughout the data analysis pipeline, gain significance. These uncertainties stem from limitations in the theoretical descriptions of neutrino interactions with nuclei. We propose an alternative approach to usual MC generators by employing Machine Learning algorithms that can learn directly from experimental measurements, even in scenarios with limited data availability. In particular, we demonstrate that Generative Adversarial Networks (GANs) can be deployed to describe the kinematics of the resultant lepton in Charged Current muon neutrino scattering off carbon as a function of the incoming neutrino energy. Additionally, we show that the physics learned by the GAN can be used to enhance the efficiency of training a model under different configurations of neutrino scattering.