English

Reconstructing the exit wave in high-resolution transmission electron microscopy using machine learning

Materials Science 2022-11-28 v2 Disordered Systems and Neural Networks

Abstract

Reconstruction of the exit wave function is an important route to interpreting high-resolution transmission electron microscopy (HRTEM) images. Here we demonstrate that convolutional neural networks can be used to reconstruct the exit wave from a short focal series of HRTEM images, with a fidelity comparable to conventional exit wave reconstruction. We use a fully convolutional neural network based on the U-Net architecture, and demonstrate that we can train it on simulated exit waves and simulated HRTEM images of graphene-supported molybdenum disulphide (an industrial desulfurization catalyst). We then apply the trained network to analyse experimentally obtained images from similar samples, and obtain exit waves that clearly show the atomically resolved structure of both the MoS2_2 nanoparticles and the graphene support. We also show that it is possible to successfully train the neural networks to reconstruct exit waves for 3400 different two-dimensional materials taken from the Computational 2D Materials Database of known and proposed two-dimensional materials.

Keywords

Cite

@article{arxiv.2112.14308,
  title  = {Reconstructing the exit wave in high-resolution transmission electron microscopy using machine learning},
  author = {Matthew Helmi Leth Larsen and Frederik Dahl and Lars P. Hansen and Bastian Barton and Christian Kisielowski and Stig Helveg and Ole Winther and Thomas W. Hansen and Jakob Schiøtz},
  journal= {arXiv preprint arXiv:2112.14308},
  year   = {2022}
}

Comments

16 pages, 24 figures

R2 v1 2026-06-24T08:34:04.735Z