Detection of Non-uniformity in Parameters for Magnetic Domain Pattern Generation by Machine Learning
This work addresses the detection of non-uniform parameters in magnetic domain patterns, which is an incremental improvement for materials science applications.
The researchers tackled the problem of detecting spatial variations in physical parameters that affect magnetic domain patterns in polycrystalline thin films, achieving this by using convolutional neural networks to estimate parameters from small subregions and demonstrating the capability to detect parameter variations in simulation data.
We estimate the spatial distribution of heterogeneous physical parameters involved in the formation of magnetic domain patterns of polycrystalline thin films by using convolutional neural networks. We propose a method to obtain a spatial map of physical parameters by estimating the parameters from patterns within a small subregion window of the full magnetic domain and subsequently shifting this window. To enhance the accuracy of parameter estimation in such subregions, we employ large-scale models utilized for natural image classification and exploit the benefits of pretraining. Using a model with high estimation accuracy on these subregions, we conduct inference on simulation data featuring spatially varying parameters and demonstrate the capability to detect such parameter variations.