Beams Document 8954-v1

DocDB Home ]  [ Search ] [ Last 20 Days ] [ List Authors ] [ List Topics ] [ List Events ]

The MicroBooNE experiment and applications of Machine Learning and Deep Learning

Document #:
Document type:
Submitted by:
Rob Ainsworth
Updated by:
Rob Ainsworth
Document Created:
27 Jan 2021, 10:21
Contents Revised:
27 Jan 2021, 10:21
Metadata Revised:
27 Jan 2021, 10:21
Viewable by:
  • Public document
Modifiable by:

Quick Links:
Latest Version

MicroBooNE is a short baseline neutrino experiment situated at Fermilab. It measures neutrinos from the Booster Neutrino Beam (BNB) with a 85t Liquid Argon Time Projection Chamber (LArTPC) detector. The main scientific goals of MicroBooNE are to explore the low energy electron neutrino spectrum and to measure neutrino-LAr interaction cross-sections. Measuring low energy electron neutrinos is aimed at probing the excess of neutrino-like events observed by the MiniBooNE experiment in the [200,600] MeV region, which may hint at BSM physics. Neutrino cross section measurements on LAr are an important input for the DUNE/LBNF program. Several low-energy excess analyses are taking place in parallel in MicroBooNE, using independent event reconstruction techniques and different signal topologies. The Deep Learning (DL) group employs machine learning techniques to extract information used in event reconstruction. In this talk I will briefly present the status of the DL low-energy excess analysis, then introduce several applications of machine learning and deep learning to LArTPC images. I will conclude with some ideas on future application of ML/DL to accelerator operations.
Files in Document:
DocDB Home ]  [ Search ] [ Last 20 Days ] [ List Authors ] [ List Topics ] [ List Events ]

DocDB Version 8.8.10, contact Beams Document Database Administrators