Modelling force-free neutron star magnetospheres using physics-informed neural networks
Por favor, use este identificador para citar o enlazar este ítem:
http://hdl.handle.net/10045/135572
Título: | Modelling force-free neutron star magnetospheres using physics-informed neural networks |
---|---|
Autor/es: | Urbán, Jorge F. | Stefanou, Petros | Dehman, Clara | Pons, José A. |
Grupo/s de investigación o GITE: | Astrofísica Relativista |
Centro, Departamento o Servicio: | Universidad de Alicante. Departamento de Física Aplicada |
Palabras clave: | Magnetic fields | Stars: magnetars | Stars: neutron | Neural networks | Physics Informed Neural Networks |
Fecha de publicación: | 16-jun-2023 |
Editor: | Oxford University Press |
Cita bibliográfica: | Monthly Notices of the Royal Astronomical Society. 2023, 524(1): 32-42. https://doi.org/10.1093/mnras/stad1810 |
Resumen: | Using Physics-Informed Neural Networks (PINNs) to solve a specific boundary value problem is becoming more popular as an alternative to traditional methods. However, depending on the specific problem, they could be computationally expensive and potentially less accurate. The functionality of PINNs for real-world physical problems can significantly improve if they become more flexible and adaptable. To address this, 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. Although this process increases the dimensionality and is computationally costly, using the trained network to evaluate new general solutions is much faster. Our results indicate that PINN solutions are relatively accurate, reliable, and well-behaved. We applied this idea to the astrophysical scenario of the magnetic field evolution in the interior of a neutron star connected to a force-free magnetosphere. Solving this problem through a global simulation in the entire domain is expensive due to the elliptic solver’s needs for the exterior solution. The computational cost with a PINN was more than an order of magnitude lower than the similar case solved with a finite difference scheme, arguably at the cost of accuracy. These results pave the way for the future extension to 3D of this (or a similar) problem, where generalised boundary conditions are very costly to implement. |
Patrocinador/es: | We acknowledge the support through the grant PID2021-127495NB-I00 funded by MCIN/AEI/10.13039/501100011033 and by the European Union, and the Astrophysics and High Energy Physics programme of the Generalitat Valenciana ASFAE/2022/026 funded by MCIN and the European Union NextGenerationEU (PRTR-C17.I1). JFU is supported by the predoctoral fellowship UAFPU21-103 funded by the University of Alicante. CD is supported by the ERC Consolidator Grant “MAGNESIA” No. 817661 (P.I. N. Rea) and has the partial support of NORDITA. This work has been carried out within the framework of the doctoral program in Physics of the Universitat Autònoma de Barcelona and it is partially supported by the program Unidad de Excelencia María de Maeztu CEX2020-001058-M. |
URI: | http://hdl.handle.net/10045/135572 |
ISSN: | 0035-8711 (Print) | 1365-2966 (Online) |
DOI: | 10.1093/mnras/stad1810 |
Idioma: | eng |
Tipo: | info:eu-repo/semantics/article |
Derechos: | © 2023 The Author(s). Published by Oxford University Press on behalf of Royal Astronomical Society |
Revisión científica: | si |
Versión del editor: | https://doi.org/10.1093/mnras/stad1810 |
Aparece en las colecciones: | INV - Astrofísica Relativista - Artículos de Revistas Investigaciones financiadas por la UE |
Archivos en este ítem:
Archivo | Descripción | Tamaño | Formato | |
---|---|---|---|---|
Urban_etal_2023_MNRAS.pdf | 1,35 MB | Adobe PDF | Abrir Vista previa | |
Todos los documentos en RUA están protegidos por derechos de autor. Algunos derechos reservados.