
Revolutionizing the search for new physics in LArTPC-based neutrino experiments with deep learning techniques
Daisy Kalra, PhD; Columbia University
Current and future-generation Liquid Argon Time Projection Chamber (LArTPC) detectors represent a great opportunity to search for rare, beyond-the-Standard Model (BSM) physics, e.g. baryon number violation. During operation, these detectors generate high-resolution images of particle interactions, making them well-suited for applying and leveraging deep learning (DL) techniques to search for rare signals within their data. This talk will focus on recent results from a DL-based analysis of MicroBooNE data, making use of a sparse convolutional neural network and event topology information to search for argon-bound neutron-antineutron transition-like signals, which demonstrate the capability of LArTPCs in achieving high signal efficiency and strong background rejection when leveraging advances in image analysis techniques. Furthermore, this talk will discuss ongoing research and development (R&D) aimed at developing data-driven data selection for the next-generation LArTPC detectors such as Deep Underground Neutrino Experiment (DUNE) and the proposed Gamma-Ray and AntiMatter Survey (GRAMS) experiments. A major challenge for these large-scale and/or high-resolution
detectors is to continually process their exorbitant data rates to search for rare and exotic signals. The objective of these R&D efforts is to develop real-time data selection schemes as well as offline data analysis for rare signals with very high accuracy and computational performance. Drawing from my own research experience, I will describe how these required advancements will enable sensitive searches for rare and exotic physics signals in the next-generation of liquid argon experiments.
Bio: Postdoctoral Research Scientist Daisy Kalra works on instrumentation R&D and searches for new physics with MicroBooNE, SBN, and DUNE. She is currently based at Fermilab and leading the commissioning of the SBND readout and data acquisition system, as well as TPC trigger development efforts on MicroBooNE and SBND.