Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe
O: Fachverband Oberflächenphysik
O 68: Poster: Scanning Probe Techniques: Method Development
O 68.2: Poster
Mittwoch, 20. März 2024, 18:00–20:00, Poster C
Enhancing AFM image analysis through machine learning with style translation and data augmentation — •Jie Huang1, Niko Oinonen1, Lauri Kurki1, and Adam S. Foster1,2 — 1Department of Applied Physics, Aalto University, Helsinki, Finland — 2WPI Nano Life Science Institute (WPI-NanoLSI), Kanazawa University, Kakuma- machi, Kanazawa, Japan
Atomic Force Microscopy (AFM) is critical for atomic-scale nanostructure characterization. Simulations, especially using Particle Probe AFM (PPAFM), provide a cost-effective means for rapid image generation. Leveraging state-of-the-art machine learning models and substantial PPAFM-generated datasets, properties like molecular structures, electrostatic force potential, and molecular graphs can be accurately predicted using AFM images from simulations or experiments. However, transferring model performance from PPAFM to real AFM images poses challenges due to the subtle variations in real experimental data compared to the seemingly flawless nature of simulations. Our study explores Cycle GANs for style translation to augment data and improve the predictive accuracy of machine learning models in surface property analysis. Focused on mitigating the gap between simulated PPAFM and authentic AFM images, we optimize hyperparameters, showcasing the method's effectiveness through paired data comparisons. This research promises valuable insights, providing a novel approach to enhance machine learning model efficiency in the absence of abundant experimental data.
Keywords: atomic force microscopy; machine learning; data augmentation; style translation; surface property analysis