BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:#StudentSeminar: Modelling force-free neutron star magnetospheres 
 using physics-informed neural networks
DTSTART;VALUE=DATE-TIME:20231127T153000Z
DTEND;VALUE=DATE-TIME:20231127T170000Z
DTSTAMP;VALUE=DATE-TIME:20260712T151329Z
UID:indico-event-7323@indico.ific.uv.es
DESCRIPTION:Physics-Informed Neural Networks (PINNs) is a relatively new b
 ut very promising family of Partial Differencial Equation (PDE) solvers ba
 sed on Machine Learning (ML) techniques. This method uses the very success
 ful modern ML frameworks and incorporates physical knowledge about a given
  system to obtain the solution. In this study\, we employ PINNs to explore
  a diverse range of neutron star magnetospheric models\, specifically focu
 sing on axisymmetric cases. The study successfully reproduced various mode
 ls found in the literature\, including those with non-dipolar configuratio
 ns. In addition\, our work explores the idea of training a PINN for genera
 l boundary conditions and source terms expressed through a limited number 
 of coefficients\, introduced as additional inputs in the network. This res
 earch lays the groundwork for a reliable elliptic Partial Differential Equ
 ation solver tailored for astrophysical problems. Based on these findings\
 , we foresee that the utilisation of PINNs will become the most efficient 
 approach in modelling three-dimensional magnetospheres. This methodology s
 hows significant potential and facilitates an effortless generalisation\, 
 contributing to the advancement of our understanding of neutron star magne
 tospheres.\n\nhttps://indico.ific.uv.es/event/7323/
LOCATION:Campus Burjassot
URL:https://indico.ific.uv.es/event/7323/
END:VEVENT
END:VCALENDAR