Transmission Electron
Transmission electron microscopy (TEM) is a powerful technique for visualizing materials at the atomic scale, with current research heavily focused on automating image analysis to overcome the limitations of manual processing. This involves employing machine learning, particularly convolutional neural networks and other deep learning architectures like vision transformers and long short-term memory networks, for tasks such as particle detection, segmentation, and strain analysis. These advancements enable high-throughput analysis of complex materials, accelerating research in diverse fields like catalysis, materials science, and virology by providing quantitative insights into nanoscale structures and their properties. The resulting improvements in efficiency and accuracy are transforming how researchers study and understand materials at the atomic level.
Papers
Deep Learning for Automated Experimentation in Scanning Transmission Electron Microscopy
Sergei V. Kalinin, Debangshu Mukherjee, Kevin M. Roccapriore, Ben Blaiszik, Ayana Ghosh, Maxim A. Ziatdinov, A. Al-Najjar, Christina Doty, Sarah Akers, Nageswara S. Rao, Joshua C. Agar, Steven R. Spurgeon
FakET: Simulating Cryo-Electron Tomograms with Neural Style Transfer
Pavol Harar, Lukas Herrmann, Philipp Grohs, David Haselbach