BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Neural Reconstruction of Muon Tracks in Baikal-GVD Using NTSim Sim
 ulations
DTSTART;VALUE=DATE-TIME:20261027T162500Z
DTEND;VALUE=DATE-TIME:20261027T163000Z
DTSTAMP;VALUE=DATE-TIME:20261021T040721Z
UID:indico-contribution-6435@cern.ch
DESCRIPTION:Speakers: Maksim Maksimov (The School of Physics and Engineeri
 ng\, ITMO University)\nMuon reconstruction in the Baikal-GVD neutrino tele
 scope requires inferring particle parameters from sparse\, irregularly dis
 tributed optical signals. We investigate graph neural networks and transfo
 rmer architectures for reconstructing muon direction and track position\, 
 using classical track fitting as a reference. Muon energy estimation is co
 nsidered as an additional task.\n\nUsing Baikal-GVD events simulated with 
 NTSim\, we will compare reconstruction accuracy and computational efficien
 cy under common evaluation conditions. The neural models will use detector
  geometry and the spatial and temporal structure of optical signals. We wi
 ll also explore whether joint estimation of energy and track parameters im
 proves reconstruction.\n\nThe comparison will examine how reconstruction e
 rrors depend on event characteristics and identify conditions in which the
  methods offer complementary strengths. This will help assess the trade-of
 f between accuracy and computational cost when selecting reconstruction me
 thods for Baikal-GVD.\n\nhttps://indico.particle.mephi.ru/event/626/contri
 butions/6435/
LOCATION:Sevastopol hotel Conference Hall 1
URL:https://indico.particle.mephi.ru/event/626/contributions/6435/
END:VEVENT
END:VCALENDAR