Atom identification in bilayer moire materials with Gomb-Net

TL;DR

This paper introduces Gomb-Net, a deep learning model that accurately identifies atomic positions and species in bilayer moire materials, enabling detailed layer-specific analysis despite complex moire patterns.

Contribution

The paper presents Gomb-Net, a novel deep learning approach that deconvolutes moire patterns to identify atoms and their types in bilayer heterostructures, surpassing previous segmentation limitations.

Findings

Gomb-Net accurately detects atomic positions and species in twisted bilayer materials.

Layer-specific atom distribution remains unaffected by moire pattern variations.

Enables new insights into material physics previously obscured by moire complexity.

Abstract

Moire patterns in van der Waals bilayer materials complicate the analysis of atomic-resolution images, hindering the atomic-scale insight typically attainable with scanning transmission electron microscopy. Here, we report a method to detect the positions and identities of atoms in each of the individual layers that compose twisted bilayer heterostructures. We developed a deep learning model, Gomb-Net, which identifies the coordinates and atomic species in each layer, effectively deconvoluting the moire pattern. This enables layer-specific mapping of quantities like strain and dopant distributions, unlike other commonly used segmentation models which struggle with moire-induced complexity. Using this approach, we explored the Se atom substitutional site distribution in a twisted fractional Janus WS2-WS2(1-x)Se2x heterostructure and found that layer-specific implantation sites are unaffected by the moire pattern's local energetic or electronic modulation. This advancement enables atom identification within material regimes where it was not possible before, opening new insights into previously inaccessible material physics.