Neural Object Detection for 4D STEM: High-Throughput Sub-Pixel Electron Diffraction Pattern Recognition

TL;DR

This paper presents an end-to-end neural network framework for high-throughput, sub-pixel accurate analysis of 4D-STEM datasets, enabling rapid strain measurement and phase identification in materials science.

Contribution

It introduces a novel neural network-based object detection method with sub-pixel localization for 4D-STEM data, improving speed and precision over traditional workflows.

Findings

Achieved strain measurement precision of 5x10^{-4}

Processed over 100 frames per second

Enabled rapid crystallographic phase identification

Abstract

High-throughput analysis of multidimensional transmission electron microscopy (TEM) datasets remains a significant challenge, limiting the broader impact on strategic materials research. Conventional workflows typically involve sequential, modular processing steps that necessitate extensive manual intervention and offline parameter tuning. In this work, we introduce an end-to-end post-processing framework for large-scale four-dimensional scanning TEM (4D-STEM) datasets, built around a highly efficient neural network-based object detection model. Central to our method is a sub-pixel accurate object center localization algorithm, which serves as the foundation for high-precision and high-throughput analysis of electron diffraction patterns. We demonstrate a strain measurement precision of 5x$10^{-4}$, quantified by the standard deviation of strain values within the strain-free Si substrate of a Si/SiGe multilayer TEM sample. Furthermore, by implementing an asynchronous, non-blocking object detection workflow, we achieve speeds exceeding 100 frames per second (fps), substantially accelerating the crystallographic phase identification and strain mapping in complex multiphase metallic alloys.