Deep Learning Enabled Strain Mapping of Single-Atom Defects in 2D Transition Metal Dichalcogenides with Sub-picometer Precision

Abstract

2D materials offer an ideal platform to study the strain fields induced by individual atomic defects, yet challenges associated with radiation damage have so-far limited electron microscopy methods to probe these atomic-scale strain fields. Here, we demonstrate an approach to probe single-atom defects with sub-picometer precision in a monolayer 2D transition metal dichalcogenide, WSe${}_{2-2x}$Te${}_{2x}$. We utilize deep learning to mine large datasets of aberration-corrected scanning transmission electron microscopy images to locate and classify point defects. By combining hundreds of images of nominally identical defects, we generate high signal-to-noise class-averages which allow us to measure 2D atomic coordinates with up to 0.3 pm precision. Our methods reveal that Se vacancies introduce complex, oscillating strain fields in the WSe${}_{2-2x}$Te${}_{2x}$ lattice which cannot be explained by continuum elastic theory. These results indicate the potential impact of computer vision for the development of high-precision electron microscopy methods for beam-sensitive materials.

All authors are from University of Illinois at Urbana-Champaign. 41 pages, 5 figures, 6 supplementary figures, and supplementary information

References in corpus (4)

• Deep Learning of Atomically Resolved Scanning Transmission Electron Microscopy Images: Chemical Identification and Tracking Local Transformations
• Engineering the structural and electronic phases of MoTe2 through W substitution
• Exciton mapping at subwavelength scales in two-dimensional materials
• Lattice Green function for extended defect calculations: Computation and error estimation with long-range forces

Cited by in corpus (16)

• Deep Learning for Automated Experimentation in Scanning Transmission Electron Microscopy
• Leveraging generative adversarial networks to create realistic scanning transmission electron microscopy images
• Developing and Evaluating Deep Neural Network-based Denoising for Nanoparticle TEM Images with Ultra-low Signal-to-Noise
• STEM image analysis based on deep learning: identification of vacancy defects and polymorphs of $Mo{S}_2$
• Nearly hyperuniform, nonhyperuniform, and antihyperuniform density fluctuations in two-dimensional transition metal dichalcogenides with defects
• Reconstructing the exit wave in high-resolution transmission electron microscopy using machine learning
• Shape-dependent local strain in gold nanorods: data-driven atomic-resolution electron microscopy analysis
• Deep-Learning-Aided Extraction of Optical Constants in Scanning Near-Field Optical Microscopy
• Creation and Microscopic Origins of Single-Photon Emitters in Transition Metal Dichalcogenides and Hexagonal Boron Nitride
• Benchmark tests of atom segmentation deep learning models with a consistent dataset
• Defect complexes in CrSBr revealed through electron microscopy and deep learning
• Bridging microscopy with molecular dynamics and quantum simulations: An AtomAI based pipeline
• Training artificial neural networks for precision orientation and strain mapping using 4D electron diffraction datasets
• Hexatic Phase in Covalent Two-Dimensional Silver Iodide
• Application of deep neural networks for computing the renormalization group flow of the two-dimensional phi^4 field theory
• TEMImageNet Training Library and AtomSegNet Deep-Learning Models for High-Precision Atom Segmentation, Localization, Denoising, and Super-Resolution Processing of Atomic-Resolution Images