Simulation-Trained Sparse Coding for High-Precision Phase Imaging in Low-Dose Electron Holography

Abstract

We broaden the applicability of sparse coding, a machine learning method, to low-dose electron holography by using simulated holograms for learning and validation processes. The holograms, with shot noise, are prepared to generate a model, or a dictionary, that includes basic features representing interference fringes. The dictionary is applied to sparse representations of other simulated holograms with various signal-to-noise ratios (SNRs). Results demonstrate that this approach successfully removes noise for holograms with an extremely small SNR of 0.10, and that the denoised holograms provide the accurate phase distribution. Furthermore, this study demonstrates that the dictionary learned from the simulated holograms can be applied to denoising of experimental holograms of a p–n junction specimen recorded with different exposure times. The results indicate that the simulation-trained sparse coding is suitable for use over a wide range of imaging conditions, in particular for observing electron beam-sensitive materials.

Advanced Characterization Techniques for Sulfide‐Based Solid‐State Lithium Batteries

“…Left: total electron dose used for various TEM imaging techniques with different spatial resolutions. [77,[83][84][85][86][87][88][89][90][91][92][93][94] Right: total electron dose used for imaging of beam-sensitive materials. [85,88,[95][96][97][98][99][100][101][102] The electron dose of ADF-STEM (≈1 Å) is calculated using the following information: probe current of 20-100 pA, dwell time of 30-60 µs pix −1 , and pixel size of 0.07-0.14 Å.…”

“…The left side of Figure 4c shows the typical TEMbased characterization techniques and the electron dose per unit area used for each imaging technique in the studies. [77,[83][84][85][86][87][88][89][90][91][92][93][94] The right side of Figure 4c shows the typical electron-beam-sensitive materials and electron dose per unit area used to observe each material in the studies. [85,88,[95][96][97][98][99][100][101][102] For further comparison, SrTiO 3 , which is robust to incident electron beams, is shown.…”

“…c) Total electron dose for TEM analyses for beam-sensitive materials. Left: total electron dose used for various TEM imaging techniques with different spatial resolutions [77,[83][84][85][86][87][88][89][90][91][92][93][94]. Right: total electron dose used for imaging of beam-sensitive materials [85,88,[95][96][97][98][99][100][101][102].…”

Machine learning in electron microscopy for advanced nanocharacterization: current developments, available tools and future outlook

“…For instance, ML has been used to obtain the accurate phase estimation at low SNR, which flattened the path towards the low-dose holography analysis of beam-sensitive materials by training a sparse coding model on simulations. [32][33][34] On the other hand, computer vision routines for automating the electron microscope alignments have already been reported in order to fine-tune the (S)TEM acquisition process. The first approaches, mainly lead by microscope manufacturers, were based on automating the column (fine) alignments through.…”

“…For instance, ML has been used to obtain the accurate phase estimation at low SNR, which flattened the path towards the low-dose holography analysis of beam-sensitive materials by training a sparse coding model on simulations. 32–34…”