NeuralMag: an open-source nodal finite-difference code for inverse micromagnetics
NeuralMag: an open-source nodal finite-difference code for inverse micromagnetics
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.
Abert, C.
7e6aa45c-52b4-4312-a55e-ed008608a87c
Brucknee, F.
63b1b37b-73fe-47fc-8a9d-deabe1a1053d
Voronov, A.
fd1c7592-c935-4251-a08e-5d2044ed4c32
Lang, M.
8f95f540-cb8f-4d53-aeaa-cc903c072b54
Pathak, S.A.
2c18f451-e916-4092-a3f0-4736d5b76034
Holt, S.
50d9e2cb-c405-4292-b159-ce7db4363ed6
Kraft, R.
a60ceea4-4309-4394-be54-11ce4ac24b7b
Allayarov, R.
c8b43d98-d02b-44f9-a5f1-56a362a01e57
Flauger, P.
922601e2-070c-4032-8b55-ce88352bba68
Koraltan, S.
137e6559-a134-4e3d-9cac-3cd27c63700e
Schref, T.
a03a1923-ad84-43db-9c8b-93f3095bc678
Chumak, A.
149c8220-8a08-4009-9aa5-5cd116b36994
Fangohr, H.
9b7cfab9-d5dc-45dc-947c-2eba5c81a160
Suess, D.
4ff6014d-b412-49c7-a265-9aab3d2bbbde
21 June 2025
Abert, C.
7e6aa45c-52b4-4312-a55e-ed008608a87c
Brucknee, F.
63b1b37b-73fe-47fc-8a9d-deabe1a1053d
Voronov, A.
fd1c7592-c935-4251-a08e-5d2044ed4c32
Lang, M.
8f95f540-cb8f-4d53-aeaa-cc903c072b54
Pathak, S.A.
2c18f451-e916-4092-a3f0-4736d5b76034
Holt, S.
50d9e2cb-c405-4292-b159-ce7db4363ed6
Kraft, R.
a60ceea4-4309-4394-be54-11ce4ac24b7b
Allayarov, R.
c8b43d98-d02b-44f9-a5f1-56a362a01e57
Flauger, P.
922601e2-070c-4032-8b55-ce88352bba68
Koraltan, S.
137e6559-a134-4e3d-9cac-3cd27c63700e
Schref, T.
a03a1923-ad84-43db-9c8b-93f3095bc678
Chumak, A.
149c8220-8a08-4009-9aa5-5cd116b36994
Fangohr, H.
9b7cfab9-d5dc-45dc-947c-2eba5c81a160
Suess, D.
4ff6014d-b412-49c7-a265-9aab3d2bbbde
Abert, C., Brucknee, F., Voronov, A., Lang, M., Pathak, S.A., Holt, S., Kraft, R., Allayarov, R., Flauger, P., Koraltan, S., Schref, T., Chumak, A., Fangohr, H. and Suess, D.
(2025)
NeuralMag: an open-source nodal finite-difference code for inverse micromagnetics.
npj Computational Materials, 11.
(doi:10.1038/s41524-025-01688-1).
Abstract
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.
Text
s41524-025-01688-1
- Version of Record
More information
Accepted/In Press date: 2 June 2025
Published date: 21 June 2025
Identifiers
Local EPrints ID: 509168
URI: http://eprints.soton.ac.uk/id/eprint/509168
ISSN: 2057-3960
PURE UUID: bce3f16c-90e3-4bf2-8405-afddb567b47d
Catalogue record
Date deposited: 11 Feb 2026 18:09
Last modified: 12 Feb 2026 02:38
Export record
Altmetrics
Contributors
Author:
C. Abert
Author:
F. Brucknee
Author:
A. Voronov
Author:
M. Lang
Author:
S.A. Pathak
Author:
S. Holt
Author:
R. Kraft
Author:
R. Allayarov
Author:
P. Flauger
Author:
S. Koraltan
Author:
T. Schref
Author:
A. Chumak
Author:
D. Suess
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics
