Denoising Scanning Tunneling Microscopy Images of Graphene with Supervised Machine Learning

TL;DR

This paper introduces a simulation-based machine learning approach to denoise atomic-scale STM images of graphene, outperforming traditional filters and enabling clearer analysis of experimental data.

Contribution

It presents a novel CNN training method using simulated STM images to effectively denoise experimental images of graphitic materials.

Findings

ML method outperforms traditional filters in noise removal

Effective denoising of both simulated and experimental STM images

Method can handle various image characteristics and artifacts

Abstract

Machine learning (ML) methods are extraordinarily successful at denoising photographic images. The application of such denoising methods to scientific images is, however, often complicated by the difficulty in experimentally obtaining a suitable expected result as an input to training the ML network. Here, we propose and demonstrate a simulation-based approach to address this challenge for denoising atomic-scale scanning tunneling microscopy (STM) images, which consists of training a convolutional neural network on STM images simulated based on a tight-binding electronic structure model. As model materials, we consider graphite and its mono- and few-layer counterpart, graphene. With the goal of applying it to any experimental STM image obtained on graphitic systems, the network was trained on a set of simulated images with varying characteristics such as tip height, sample bias, atomic-scale defects, and non-linear background. Denoising of both simulated and experimental images with this approach is compared to that of commonly-used filters, revealing a superior outcome of the ML method in the removal of noise as well as scanning artifacts - including on features not simulated in the training set. An extension to larger STM images is further discussed, along with intrinsic limitations arising from training set biases that discourage application to fundamentally unknown surface features. The approach demonstrated here provides an effective way to remove noise and artifacts from typical STM images, yielding the basis for further feature discernment and automated processing.