BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Deep learning approaches to galaxy merger identification and class
 ification
DTSTART;VALUE=DATE-TIME:20260907T101000Z
DTEND;VALUE=DATE-TIME:20260907T104000Z
DTSTAMP;VALUE=DATE-TIME:20260922T191357Z
UID:indico-contribution-2046@events.ncbj.gov.pl
DESCRIPTION:Speakers: Subhrata Dey (National Centre for Nuclear Research)\
 nGalaxy mergers are fundamental to the hierarchical assembly and evolution
  of galaxies\, often driving starburst activity and AGN fueling. Identifyi
 ng mergers and their stages\, such as pre- and post-coalescence\, from ima
 ging alone\, especially given the vast size of modern datasets\, remains e
 xtremely challenging. We develop a supervised deep learning framework usin
 g Convolutional Neural Networks (CNNs) to classify galaxies as non-mergers
 \, pre-mergers\, or post-mergers. Our training uses mock Hyper Suprime-Cam
  (HSC) images from the IllustrisTNG simulations (Margalef-Bentabol et al. 
 2024). HSC\, a precursor to LSST\, is ideal for developing and validating 
 machine learning methods for future surveys. We test our model on syntheti
 c and real HSC data to assess robustness and generalizability. This approa
 ch demonstrates the potential of simulation-driven machine learning to rev
 eal galaxy merger histories in upcoming wide-field surveys.\n\nhttps://eve
 nts.ncbj.gov.pl/event/468/contributions/2046/
LOCATION:
URL:https://events.ncbj.gov.pl/event/468/contributions/2046/
END:VEVENT
END:VCALENDAR