Machine-Learning-Enabled Fast Optical Identification and Characterization of 2D Materials

TL;DR

This paper presents a machine learning approach to rapidly identify and characterize monolayer 2D materials from optical images, reducing reliance on time-consuming and expensive traditional methods.

Contribution

It evaluates the performance of three deep learning models—SegNet, 1D U-Net, and 2D U-Net—for accurate layer thickness identification in 2D materials.

Findings

2D U-Net achieved the highest accuracy in monolayer identification.

Machine learning models significantly reduced identification time.

Effective image processing techniques improved model performance.

Abstract

Two-dimensional materials are a class of atomically thin materials with assorted electronic and quantum properties. Accurate identification of layer thickness, especially for a single monolayer, is crucial for their characterization. This characterization process, however, is often time-consuming, requiring highly skilled researchers and expensive equipment like atomic force microscopy. This project aims to streamline the identification process by using machine learning to analyze optical images and quickly determine layer thickness. In this paper, we evaluate the performance of three machine learning models -- SegNet, 1D U-Net, and 2D U-Net -- in accurately identifying monolayers in microscopic images. Additionally, we explore labeling and image processing techniques to determine the most effective method for identifying layer thickness in this class of materials.