# Machine learning enabled fast optical identification and characterization of 2D materials

**URL:** <https://community.materialssquare.com/t/machine-learning-enabled-fast-optical-identification-and-characterization-of-2d-materials/1058>\
**Category:** News\
**Created:** [December 17, 2024, 7:40pm UTC](https://community.materialssquare.com/t/machine-learning-enabled-fast-optical-identification-and-characterization-of-2d-materials/1058 "2024-12-17T19:40:11Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![gabriele1](https://yyz1.discourse-cdn.com/flex003/user_avatar/community.materialssquare.com/gabriele1/32/20_2.png) [@gabriele1](https://community.materialssquare.com/u/gabriele1)\
**Post date:** [December 17, 2024, 7:40pm UTC](https://community.materialssquare.com/t/machine-learning-enabled-fast-optical-identification-and-characterization-of-2d-materials/1058/1 "2024-12-17T19:40:11Z")

</div>

This article focuses on applying machine learning to efficiently identify and characterize the thickness of two-dimensional (2D) materials using optical microscopy images. Traditional methods, like atomic force microscopy and spectroscopy, are precise but expensive and time-consuming. To address this, the study evaluates the performance of SegNet, 2D U-Net, and 1D U-Net machine learning models for identifying monolayers in optical images. The research incorporates preprocessing techniques, such as grayscale and Lab\* color space transformations, and data augmentation to improve accuracy. Among the models, 2D U-Net demonstrates the best performance, especially when using normalized image preprocessing and transfer learning with pre-labeled datasets. This approach highlights the potential for machine learning to provide a fast, cost-effective solution for 2D material characterization, promoting broader use of these materials in electronics and quantum technologies.

For more details, please continue reading the full article under the following link:

[https://www.nature.com/articles/s41598-024-79386-z](https://www.nature.com/articles/s41598-024-79386-z)

* * *

In general, if you enjoy reading this kind of scientific news articles, I am always keen to connect with fellow researchers in materials science, including the possibility to discuss about any potential interest in the Materials Square cloud-based online platform ( [www.matsq.com](http://www.matsq.com) ), designed for streamlining the execution of materials and molecular modelling simulations!

The Materials Square platform in fact provides extensive web-based functionalities for computational chemistry/materials research and training/education purposes, as detailed also in the following PDF brochure: [https://www.materialssquare.com/wp-content/uploads/Materials\_Square\_Brochure\_2022-compressed\_1674181754.pdf](https://www.materialssquare.com/wp-content/uploads/Materials_Square_Brochure_2022-compressed_1674181754.pdf)

Many thanks for your interest and consideration,

Dr. Gabriele Mogni  
Technical Consultant and EU Representative of Virtual Lab Inc., the parent company of the Materials Square platform  
Website: [Home | Virtual Lab Inc.](http://www.virtuallab.co.kr/en/)  
Email: gabriele@simulation.re.kr

#materials #materialsscience #materialsengineering #computationalchemistry #modelling #chemistry #researchanddevelopment #research #MaterialsSquare #ComputationalChemistry #Tutorial #DFT #simulationsoftware #simulation