Reconstruction of non-trivial magnetization textures from magnetic field images using neural networks

Spatial imaging of magnetic stray fields from magnetic materials is a useful tool for identifying the underlying magnetic configurations of the material. However, transforming the magnetic image into a magnetization image is an ill-poised problem, which can result in artefacts that limit the inferences that can be made on the material under investigation. In this work, we develop a neural network fitting approach that approximates this transformation, reducing these artefacts. Additionally, we demonstrate that this approach allows the inclusion of additional models and bounds that are not possible with traditional reconstruction methods. These advantages allow for the reconstruction of non-trivial magnetization textures with varying magnetization directions in thin-film magnets, which was not possible previously. We demonstrate this new capability by performing magnetization reconstructions on a variety of topological spin textures.