Automatic alignment of an orbital angular momentum sorter in a transmission electron microscope using a convolution neural network

TL;DR

This paper presents a convolutional neural network that automatically aligns an orbital angular momentum sorter in a transmission electron microscope, optimizing spectral resolution without user input.

Contribution

The study introduces a neural network-based method for automatic, real-time alignment of electron microscopes with orbital angular momentum sorters, reducing manual effort and improving stability.

Findings

Neural network successfully controls microscope parameters autonomously.

Alignment process completes within a few frames.

Maintains stable alignment over time.

Abstract

We report on the automatic alignment of a transmission electron microscope equipped with an orbital angular momentum sorter using a convolutional neural network. The neural network is able to control all relevant parameters of both the electron-optical setup of the microscope and the external voltage source of the sorter without input from the user. It is able to compensate for mechanical and optical misalignments of the sorter, in order to optimize its spectral resolution. The alignment is completed over a few frames and can be kept stable by making use of the fast fitting time of the neural network.