Automatic Alignment of an Orbital Angular Momentum Sorter in a Transmission Electron Microscope Using a Convolutional Neural Network

Near-real-time diagnosis of electron optical phase aberrations in scanning transmission electron microscopy using an artificial neural network

The key to optimizing spatial resolution in a state-of-the-art scanning transmission electron microscope is the ability to measure and correct for electron optical aberrations of the probe-forming lenses precisely. Several diagnostic methods for aberration measurement and correction have been proposed, albeit often at the cost of relatively long acquisition times. Here, we illustrate how artificial intelligence can be used to provide near-real-time diagnosis of aberrations from individual Ronchigrams. The demonstrated speed of aberration measurement is important because microscope conditions can change rapidly. It is also important for the operation of MEMS-based hardware correction elements, which have less intrinsic stability than conventional electromagnetic lenses.