Autonomous Investigations over WS$_2$ and Au{111} with Scanning Probe Microscopy

TL;DR

This paper presents an autonomous hyperspectral scanning tunneling spectroscopy workflow using machine learning to efficiently analyze defects in 2D materials like WS$_2$ and Au{111}, enhancing reproducibility and accessibility.

Contribution

It introduces a machine-driven, customizable workflow for autonomous hyperspectral STS mapping combining Gaussian process regression and neural networks for defect analysis.

Findings

Successful detection of sulfur vacancies in WS$_2$

Identification of different gold surface structures

Demonstration of AI potential in hyperspectral mapping

Abstract

Individual atomic defects in 2D materials impact their macroscopic functionality. Correlating the interplay is challenging, however, intelligent hyperspectral scanning tunneling spectroscopy (STS) mapping provides a feasible solution to this technically difficult and time consuming problem. Here, dense spectroscopic volume is collected autonomously via Gaussian process regression, where convolutional neural networks are used in tandem for spectral identification. Acquired data enable defect segmentation, and a workflow is provided for machine-driven decision making during experimentation with capability for user customization. We provide a means towards autonomous experimentation for the benefit of both enhanced reproducibility and user-accessibility. Hyperspectral investigations on WS$_2$ sulfur vacancy sites are explored, which is combined with local density of states confirmation on the Au{111} herringbone reconstruction. Chalcogen vacancies, pristine WS$_2$, Au face-centered cubic, and Au hexagonal close packed regions are examined and detected by machine learning methods to demonstrate the potential of artificial intelligence for hyperspectral STS mapping.