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

TL;DR

NeuralMag is an open-source Python library for micromagnetic simulations that uses modern machine learning frameworks and a novel discretization scheme to improve accuracy and efficiency, especially for inverse problems.

Contribution

NeuralMag introduces a novel nodal finite-difference scheme and leverages machine learning frameworks for flexible, high-performance micromagnetic simulations in Python.

Findings

NeuralMag achieves accuracy improvements over traditional methods.

The library performs competitively with existing simulation codes.

NeuralMag effectively handles inverse problems with automatic differentiation.

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.