guest ::
| Home > Publications database > CNN-based Classification of Magnetic States from Atomistic Simulations in thin films |
| Home > Publications database > CNN-based Classification of Magnetic States from Atomistic Simulations in thin films |
| Conference Presentation (After Call) | FZJ-2025-03185 |
; ;
2025
Abstract: The identification and classification of different magnetic states are essential for understanding the complex behavior of magnetic systems. Traditional approaches that rely on handcrafted features or manual inspection often fall short, particularly when dealing with subtle or topologically complex spin textures. In this study, we present a fully automated deep learning model that employs an EfficientNetV1B0 Convolutional Neural Network (CNN) to classify nine distinct magnetic states, including both FM and, for the first time, AFM spin textures such as AFM skyrmions and AFM stripe domains. The spin configurations are generated through atomistic spin dynamics simulations using the \textit{Spirit} code, then visualized with VFRendering script. Our model achieves a classification accuracy and F1-score of 99\%, significantly outperforming established CNN baselines and demonstrating exceptional capability in distinguishing closely related magnetic states.
|
The record appears in these collections: |