NeuralMag

Autor(en)

Claas Abert, Florian Bruckner, Andrey Voronov, Martin Lang, Swapneel Amit Pathak, Samuel Holt, Robert Kraft, Ruslan Allayarov, Peter Flauger, Sabri Koraltan, Thomas Schrefl, Andrii Chumak, Hans Fangohr, Dieter Suess

Abstrakt

We present NeuralMag, a flexible and high-performance open-source Python library for micromagnetic simulations. NeuralMag leverages modern machine learning frameworks, such as PyTorch and JAX, to perform efficient tensor operations on various parallel hardware, including CPUs, GPUs, and TPUs. The library implements a novel nodal finite-difference discretization scheme that provides improved accuracy over traditional finite-difference methods without increasing computational complexity. NeuralMag is particularly well-suited for solving inverse problems, especially those with time-dependent objectives, thanks to its automatic differentiation capabilities. Performance benchmarks show that NeuralMag is competitive with state-of-the-art simulation codes while offering enhanced flexibility through its Python interface and integration with high-level computational backends.

Organisation(en)

Physik Funktioneller Materialien, Nanomagnetismus und Magnonik, Forschungsplattform MMM Mathematics-Magnetism-Materials

Externe Organisation(en)

Max-Planck-Institut für Struktur und Dynamik der Materie, Center for Free-Electron Laser Science - CFEL, Technische Universität Wien, Universität für Weiterbildung Krems, University of Southampton

Journal

npj Computational Materials

Band

11

Anzahl der Seiten

10

ISSN

2096-5001

DOI

https://doi.org/10.1038/s41524-025-01688-1

Publikationsdatum

06-2025

Peer-reviewed

Ja

ÖFOS 2012

103017 Magnetismus

Schlagwörter

Link zum Portal

https://ucrisportal.univie.ac.at/de/publications/f167f14d-bfea-404e-a58c-686865cd65ed