Emittance Minimization for Aberration Correction II: Physics-informed Bayesian Optimization of an Electron Microscope

TL;DR

This paper introduces a physics-informed Bayesian optimization method to automate aberration correction in electron microscopes, significantly improving tuning efficiency and accuracy by minimizing beam emittance.

Contribution

It develops a Bayesian approach using a neural network predictor for beam emittance, enabling automated, efficient aberration correction in electron microscopes.

Findings

Outperforms conventional methods in simulation and experiments

Achieves faster convergence to optimal optical state

Effectively models control interactions with neural network kernels

Abstract

Aberration-corrected Scanning Transmission Electron Microscopy (STEM) has become an essential tool in understanding materials at the atomic scale. However, tuning the aberration corrector to produce a sub-{\AA}ngstr\"om probe is a complex and time-costly procedure, largely due to the difficulty of precisely measuring the optical state of the system. When measurements are both costly and noisy, Bayesian methods provide rapid and efficient optimization. To this end, we develop a Bayesian approach to fully automate the process by minimizing a new quality metric, beam emittance, which is shown to be equivalent to performing aberration correction. In part I, we derived several important properties of the beam emittance metric and trained a deep neural network to predict beam emittance growth from a single Ronchigram. Here we use this as the black box function for Bayesian Optimization and demonstrate automated tuning of simulated and real electron microscopes. We explore different surrogate functions for the Bayesian optimizer and implement a deep neural network kernel to effectively learn the interactions between different control channels without the need to explicitly measure a full set of aberration coefficients. Both simulation and experimental results show the proposed method outperforms conventional approaches by achieving a better optical state with a higher convergence rate.