Resolution enhancement of scanning electron micrographs using artificial intelligence

Materials & Design, vol. 253, pp. 113955

Abstract

Microscopic imaging of materials often requires the examination of large sample areas at high magnification to identify and analyse rare structural features. High-resolution imaging in scanning electron microscopy is particularly time-intensive, as images are acquired through sequential scanning of an electron beam across the sample surface. This presents a critical challenge, as researchers must balance imaging speed and resolution while ensuring statistically meaningful observations of sparsely distributed features. To address these challenges, we present a novel resolution enhancement method for electron microscopy based on artificial intelligence. Suitable reference images are selected using vector embeddings and processed by a texture-transformer network. Using a tailored dataset of dual-phase steel micrographs, we demonstrate that our trained network outperforms traditional interpolation methods in both quantitative similarity metrics and crucial material-specific features, such as phase boundaries and microstructural voids. The method's transferability is validated using micrographs from a 16MnCrS5 case-hardening steel sample. We achieve a 16-fold acceleration through resolution trade-offs between target and recording and additionally propose a scan-enhance-rescan workflow where resolution-enhanced micrographs guide the identification of regions of interest for targeted high-resolution rescanning. We provide quantitative estimates of expected time savings, offering a practical framework for efficient high-resolution microscopy across large areas. • AI-based resolution enhancement method enables 16-fold faster SEM imaging. • Workflow of deep learning super resolution and vector embeddings. • Trained network preserves small scale microstructural details. • Application to two industrially relevant steels with different microstructures. • Proposed application in a scan-enhance-rescan workflow.

Authors 6

1. Tom Reclik corresponding Aachen Institute for Physical Metallurgy and Materials Physics

   RWTH Aachen University

   Affiliation as printed

   Institute for Physical Metallurgy and Materials Physics, RWTH Aachen University, Aachen, Germany

2. Setareh Medghalchi Aachen Institute for Physical Metallurgy and Materials Physics

   RWTH Aachen University

   Affiliation as printed

   Institute for Physical Metallurgy and Materials Physics, RWTH Aachen University, Aachen, Germany

3. Maximilian A. Wollenweber Aachen Institute for Physical Metallurgy and Materials Physics

   RWTH Aachen University

   Affiliation as printed

   Institute for Physical Metallurgy and Materials Physics, RWTH Aachen University, Aachen, Germany

4. Talal Al‐Samman Aachen Institute for Physical Metallurgy and Materials Physics

   RWTH Aachen University

   Affiliation as printed

   Institute for Physical Metallurgy and Materials Physics, RWTH Aachen University, Aachen, Germany

5. Sandra Korte‐Kerzel Aachen Institute for Physical Metallurgy and Materials Physics

   RWTH Aachen University

   Affiliation as printed

   Institute for Physical Metallurgy and Materials Physics, RWTH Aachen University, Aachen, Germany

6. U. Kerzel Aachen Fakultät für Georessourcen und Materialtechnik

   RWTH Aachen University

   Affiliation as printed

   Data Science and Artificial Intelligence in Materials and Geoscience, Fakultät für Georessourcen und Materialtechnik, RWTH Aachen University, Aachen, Germany