Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

A deep-learning framework reveals whole-body perturbations at cell level.

Nature·2026
Same author

Enhancing Charge Transport and Extraction in Ta<sub>3</sub>N<sub>5</sub> Photoanodes Via Ti Doping and TiN Contact Layers.

Small (Weinheim an der Bergstrasse, Germany)·2026
Same author

Machine learning-augmented lateral flow assays for point-of-care infectious disease diagnostics.

Lab on a chip·2026
Same author

Single-crystalline Ba<sub>x</sub>Sr<sub>1-x</sub>TaO<sub>2</sub>N solid-solution photocatalyst with low defect concentrations for solar-driven water splitting.

Nature communications·2026
Same author

Optical spectroscopic determination of photoexcited small-polaron hopping in transition metal oxide photocatalysts.

Chemical science·2026
Same author

Optical sensors for continuous glucose monitoring.

Progress in biomedical engineering (Bristol, England)·2025

Related Experiment Video

Updated: Nov 20, 2025

Differentiation and Characterization of Neural Progenitors and Neurons from Mouse Embryonic Stem Cells
08:47

Differentiation and Characterization of Neural Progenitors and Neurons from Mouse Embryonic Stem Cells

Published on: May 15, 2020

5.4K

3D Deep Learning Enables Accurate Layer Mapping of 2D Materials.

Xingchen Dong1, Hongwei Li2, Zhutong Jiang1

  • 1Institute for Measurement Systems and Sensor Technology, Department of Electrical and Computer Engineering, Technical University of Munich, 80333 Munich Germany.

ACS Nano
|January 19, 2021
PubMed
Summary

This study introduces a deep learning method (DALM) to quickly map atomic layer numbers in 2D materials like MoS2. DALM accurately identifies flake thicknesses using combined hyperspectral and RGB images, improving photonics device development.

Keywords:
2D materialsdeep learninghyperspectral imaging microscopylayer number identificationsemantic segmentation

More Related Videos

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.7K
3D Scanning Technology Bridging Microcircuits and Macroscale Brain Images in 3D Novel Embedding Overlapping Protocol
10:14

3D Scanning Technology Bridging Microcircuits and Macroscale Brain Images in 3D Novel Embedding Overlapping Protocol

Published on: May 12, 2019

7.5K

Related Experiment Videos

Last Updated: Nov 20, 2025

Differentiation and Characterization of Neural Progenitors and Neurons from Mouse Embryonic Stem Cells
08:47

Differentiation and Characterization of Neural Progenitors and Neurons from Mouse Embryonic Stem Cells

Published on: May 15, 2020

5.4K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.7K
3D Scanning Technology Bridging Microcircuits and Macroscale Brain Images in 3D Novel Embedding Overlapping Protocol
10:14

3D Scanning Technology Bridging Microcircuits and Macroscale Brain Images in 3D Novel Embedding Overlapping Protocol

Published on: May 12, 2019

7.5K

Area of Science:

  • Materials Science
  • Nanotechnology
  • Photonics

Background:

  • Layered, two-dimensional (2D) materials are crucial for advanced photonics.
  • Accurate determination of atomic layer numbers in 2D materials is challenging and time-consuming.
  • Existing hyperspectral imaging offers spectral detail but lacks spatial resolution.

Purpose of the Study:

  • To develop an automated, high-resolution method for identifying and segmenting 2D material flakes based on atomic layer number.
  • To integrate hyperspectral and RGB imaging data for enhanced material characterization.
  • To overcome the limitations of low spatial resolution in hyperspectral imaging and improve upon RGB-only methods.

Main Methods:

  • A novel 3D deep learning model, DALM (deep-learning-enabled atomic layer mapping), was developed.
  • DALM merges hyperspectral reflection images (high spectral resolution) with RGB images (high spatial resolution).
  • The model was trained on a limited dataset to predict layer distributions and segment MoS2 flakes (mono-, bi-, tri-, and multilayer).

Main Results:

  • DALM accurately identifies and segments MoS2 flakes with varying layer thicknesses.
  • The method demonstrates robustness against variations in illumination and contrast.
  • DALM outperforms existing state-of-the-art models that rely solely on RGB images.

Conclusions:

  • DALM offers a fast, accurate, and high-resolution AI-supported solution for mapping atomically thin materials.
  • This technique enables reliable computer-aided identification of 2D materials, crucial for fabricating next-generation photonics devices.
  • The integration of hyperspectral and RGB data via deep learning provides a significant advancement in materials characterization.