First Deep Learning based Event Reconstruction for Low-Energy Excess Searches with MicroBooNE
This paper describes algorithms developed to isolate and accurately reconstruct two-track νµ-like events that are contained within the MicroBooNE detector. This reconstruction has applications to searches for neutrino oscillations and measurements of cross sections using events that are charged-current quasi-elastic-like, among other applications. The algorithms we discuss will be applicable to all detectors running in Fermilab’s SBN program, and any future LArTPC experiment with beam energies ~ 1 GeV.
- Research Organization:
- Fermi National Accelerator Lab. (FNAL), Batavia, IL (United States)
- Sponsoring Organization:
- USDOE Office of Science (SC), High Energy Physics (HEP)
- Contributing Organization:
- MicroBooNE Collaboration
- DOE Contract Number:
- AC02-07CH11359
- OSTI ID:
- 1573220
- Report Number(s):
- FERMILAB-MICROBOONE-NOTE-1042-PUB; MICROBOONE-NOTE-1042-PUB; oai:inspirehep.net:1763005; TRN: US2000099
- Country of Publication:
- United States
- Language:
- English
Similar Records
Vertex-finding and reconstruction of contained two-track neutrino events in the MicroBooNE detector
Selection of νμ Events for the MicroBooNE Deep Learning Low Energy Excess Analysis
Using Deep Learning Techniques to Search for the MiniBooNE Low Energy Excess in MicroBooNE with > 3$\sigma$ Sensitivity
Journal Article
·
Thu Feb 11 00:00:00 EST 2021
· Journal of Instrumentation
·
OSTI ID:1573220
+185 more
Selection of νμ Events for the MicroBooNE Deep Learning Low Energy Excess Analysis
Technical Report
·
Mon Oct 29 00:00:00 EDT 2018
·
OSTI ID:1573220
Using Deep Learning Techniques to Search for the MiniBooNE Low Energy Excess in MicroBooNE with > 3$\sigma$ Sensitivity
Thesis/Dissertation
·
Mon Oct 26 00:00:00 EDT 2020
·
OSTI ID:1573220