Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe
MM: Fachverband Metall- und Materialphysik
MM 53: Data Driven Material Science: Big Data and Workflows VI
MM 53.7: Vortrag
Donnerstag, 21. März 2024, 12:00–12:15, C 243
Advancing In-Situ SEM Imaging: Integrating Deep Learning Super-Resolution for Accelerated Analysis — •Tom Reclik1, Philipp Schumacher1, Setareh Medghalchi1, Maximilian Wollenweber1, Ulrich Kerzel2, and Sandra Korte-Kerzel1 — 1Institute for Physical Metallurgy and Materials Physics, RWTH Aachen University, Aachen, Germany — 2Data Science and Artificial Intelligence in Materials and Geoscience, Faculty of Georesources and Materials Engineering, RWTH Aachen University, Aachen, Germany
Scanning Electron Microscopy (SEM) is pivotal in revealing intricate micro and nanoscale features across various research fields. However, obtaining large-area high-resolution SEM images presents challenges, including prolonged scanning durations and potential sample degradation due to extended electron beam exposure. This challenge is significantly amplified, when the time dimension in in-situ experiments is added. Here we present a new in-situ workflow, accelerating the imaging process step, by employing deep learning super-resolution algorithms coupled with the automated high resolution rescanning of points of interest. Our approach significantly speeds up the imaging process, thereby enabling the discoveries of new physics with a high statistical relevancy.
Keywords: Deep Learning; Super Resolution; Scanning Electron Microscopy; In-Situ; Machine Learning