Artificial Intelligence-Assisted Workflow for Transmission Electron Microscopy: From Data Analysis Automation to Materials Knowledge Unveiling

Abstract

(Scanning) transmission electron microscopy ((S)TEM) has significantly advanced materials science but faces challenges in correlating precise atomic structure information with the functional properties of devices due to its time-intensive nature. To address this, we introduce an analytical workflow for the holistic characterization, modelling, and simulation of device heterostructures. This workflow automates the experimental (S)TEM data analysis, providing an in-depth characterization of crystallographic information, 3D orientation, elemental composition, and strain distribution. It reduces a process that typically takes days for a trained human into an automatic routine solved in minutes. Utilizing a physics-guided artificial intelligence model, it generates representative descriptions of materials and samples. The workflow culminates in creating digital twins, 3D finite element and atomic models of millions of atoms, enabling simulations that provide crucial insights into device behaviour in practical applications. Demonstrated with SiGe planar heterostructures for scalable spin qubits, the workflow links digital twins to theoretical properties, revealing how atomic structure impacts materials and functional properties such as spatially-resolved phononic or electronic characteristics, or (inverse) spin orbit lengths. The versatility of our workflow is demonstrated through its application to a wide array of materials systems, device configurations, and sample morphologies.

References in corpus (24)

• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• SIESTA: recent developments and applications
• Deep Learning of Atomically Resolved Scanning Transmission Electron Microscopy Images: Chemical Identification and Tracking Local Transformations
• A deep learning approach to identify local structures in atomic-resolution transmission electron microscopy images
• Adaptive Finite Element Method for Simulation of Optical Nano Structures
• Model for the on-site matrix elements of the tight-binding hamiltonian of a strained crystal: Application to silicon, germanium and their alloys
• Deep Learning Analysis of Defect and Phase Evolution During Electron Beam Induced Transformations in WS2
• A singlet triplet hole spin qubit in planar Ge
• AtomAI: A Deep Learning Framework for Analysis of Image and Spectroscopy Data in (Scanning) Transmission Electron Microscopy and Beyond
• Automated Structure Discovery in Atomic Force Microscopy
• Linear Scaling Quantum Transport Methodologies
• Deep Learning for Automated Experimentation in Scanning Transmission Electron Microscopy
• Reducing charge noise in quantum dots by using thin silicon quantum wells
• Hard superconducting gap in germanium
• Hole spin driving by strain-induced spin-orbit interactions
• Semiconductor materials stacks for quantum dot spin qubits
• Universal image segmentation for optical identification of 2D materials
• Low disorder and high valley splitting in silicon
• Efficient first principles simulation of electron scattering factors for transmission electron microscopy
• A Context-aware Delayed Agglomeration Framework for Electron Microscopy Segmentation
• Quantifying the dynamics of protein self-organization using deep learning analysis of atomic force microscopy data
• MPFit: A robust method for fitting atomic resolution images with multiple Gaussian peaks
• Linear-in-momentum spin orbit interactions in planar Ge/GeSi heterostructures and spin qubits
• Improved ACOM pattern matching in 4D STEM through adaptive sub pixel peak detection and image reconstruction