Speaker
Description
DUNE is the flagship next-generation neutrino experiment in the United States, designed to decisively measure neutrino CP violation and determine the mass hierarchy. It utilizes the Liquid Argon Time Projection Chamber (LArTPC) technology, which provides exceptional spatial resolution and the potential to accurately identify final state particles and neutrino interactions. However, the high-resolution LArTPC at DUNE also increases the complexity of reconstructing and identifying these interactions. Deep learning techniques offer a promising solution to this problem. At DUNE, convolutional neural networks, graph neural networks and transformers are being developed and have already shown promising results in signal processing, kinematic reconstruction, clustering and interaction/particle identification. Deep learning methods have also been widely applied to areas beyond reconstruction at DUNE. In this talk, I will review the development of these deep learning–based approaches within the DUNE experiment.