#StudentSeminar: Modelling force-free neutron star magnetospheres using physics-informed neural networks

by Petros Stefanou

Monday 27 Nov 2023, 16:30 → 18:00 Europe/Madrid

Campus Burjassot

Physics-Informed Neural Networks (PINNs) is a relatively new but very promising family of Partial Differencial Equation (PDE) solvers based on Machine Learning (ML) techniques. This method uses the very successful 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 focusing on axisymmetric cases. The study successfully reproduced various models found in the literature, including those with non-dipolar configurations. In addition, our work explores the idea of training a PINN for general boundary conditions and source terms expressed through a limited number of coefficients, introduced as additional inputs in the network. This research lays the groundwork for a reliable elliptic Partial Differential Equation 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 shows significant potential and facilitates an effortless generalisation, contributing to the advancement of our understanding of neutron star magnetospheres.