Alignment of electron optical beam shaping elements using a convolutional neural network

E Rotunno; A H Tavabi; P Rosi; S Frabboni; P Tiemeijer; R E Dunin-Borkowski; V Grillo

doi:10.1016/j.ultramic.2021.113338

Alignment of electron optical beam shaping elements using a convolutional neural network

Ultramicroscopy. 2021 Sep:228:113338. doi: 10.1016/j.ultramic.2021.113338. Epub 2021 Jun 18.

Authors

E Rotunno¹, A H Tavabi², P Rosi³, S Frabboni⁴, P Tiemeijer⁵, R E Dunin-Borkowski², V Grillo⁶

Affiliations

¹ Istituto di Nanoscienze - CNR, 41125 Modena, Italy. Electronic address: enzo.rotunno@nano.cnr.it.
² Ernst Ruska-Centre for Microscopy and Spectroscopy with Electrons, Forschungszentrum Jülich, 52425 Jülich, Germany.
³ University of Modena and Reggio Emilia, via G. Campi 213/A, 41125 Modena, Italy.
⁴ Istituto di Nanoscienze - CNR, 41125 Modena, Italy; University of Modena and Reggio Emilia, via G. Campi 213/A, 41125 Modena, Italy.
⁵ Thermo Fisher Scientific, PO Box 80066, 5600 KA Eindhoven, the Netherlands.
⁶ Istituto di Nanoscienze - CNR, 41125 Modena, Italy.

PMID: 34218137
DOI: 10.1016/j.ultramic.2021.113338

Abstract

A convolutional neural network is used to align an orbital angular momentum sorter in a transmission electron microscope. The method is demonstrated using simulations and experiments. As a result of its accuracy and speed, it offers the possibility of real-time tuning of other electron optical devices and electron beam shaping configurations.

Keywords: Beam Shaping; Convolution neural network; Orbital Angular Momentum Sorter; Self-Alignment.