NeuralMag: an open-source nodal finite-difference code for inverse micromagnetics

• Published in: npj computational materials Vol. 11; no. 1; pp. 193 - 10
• Main Authors: Abert, C., Bruckner, F., Voronov, A., Lang, M., Pathak, S. A., Holt, S., Kraft, R., Allayarov, R., Flauger, P., Koraltan, S., Schrefl, T., Chumak, A., Fangohr, H., Suess, D.
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 01.01.2025; Nature Publishing Group; Nature Portfolio
• Subjects: 639/766/119/1001; 639/766/119/2793; Algorithms; Characterization and Evaluation of Materials; Chemistry and Materials Science; Computational Intelligence; Computer applications; Energy; Finite difference method; Interfaces; Inverse problems; Machine learning; Materials Science; Mathematical analysis; Mathematical and Computational Engineering; Mathematical and Computational Physics; Mathematical Modeling and Industrial Mathematics; Open source software; Optimization techniques; Python; Simulation; Source code; Tensors; Theoretical; Variables; Ferromagnetism; Spintronics
• ISSN: 2057-3960; 2057-3960
• DOI: 10.1038/s41524-025-01688-1

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.