BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Physics-Informed Neural Network for Kilonova Light Curves Modeling
DTSTART;VALUE=DATE-TIME:20260705T044500Z
DTEND;VALUE=DATE-TIME:20260705T050000Z
DTSTAMP;VALUE=DATE-TIME:20261027T035439Z
UID:indico-contribution-813@indico.narit.or.th
DESCRIPTION:Speakers: Surojit Saha (Institute of Astronomy\, National Tsin
 g Hua University\, Taiwan)\nPhysics-informed neural networks (PINNs) have 
 gained considerable importance in recent years in the domain of Astronomy 
 \\& Astrophysics\, particularly as a potential tool to solve differential 
 equations within the given boundary conditions\, not only for making accur
 ate predictions but also for providing an efficient approach for large com
 putations. In this work\, we have focused on solving the kilonova equation
 s adopted from a specific kilonova model through the direct implementation
  of the PINN on the differential equations and the respective boundary con
 ditions provided in the model. The PINN architecture is trained on differe
 ntial equations conditioned on certain boundary conditions\, thus learning
  the evolution of KNe light curves based on given ranges of physical param
 eters. To test the performance\, after successful training\, predictions o
 f the light curve for a known set of physical parameters are given as inpu
 t\, and a comparison is made between the true and predicted light curves. 
 Current results point to stable training with significant recovery of the 
 light curves\, showing a low mean squared error between them. Training and
  inference for the light curves are completed in under 2 hours. The ultima
 te goal is to develop an accurate PINN-based kilonova model for light-curv
 e generation and low-latency parameter estimation.\n\nhttps://indico.narit
 .or.th/event/236/contributions/813/
LOCATION:National Astronomical Research Institute of Thailand (NARIT) Andr
 omeda Meeting Room
URL:https://indico.narit.or.th/event/236/contributions/813/
END:VEVENT
END:VCALENDAR