Probing nanoscale structural perturbation in a WS2 monolayer via explainable artificial intelligence
- 16 April 2025
- journal article
- Published by AIP Publishing in Applied Physics Reviews
- Vol. 12 (2)
Abstract
This study investigates the applicability of the machine learning model in correlative spectroscopy to enhance spatial resolution for probing nanoscale structural perturbations. The developed model demonstrates significant enhancement in spatial resolution, achieving up to 50 nm through the integration of Kelvin probe force microscopy and atomic force microscopy data. The predicted nanoscale Raman image reveals abnormal behaviors associated with strain-induced lattice perturbations, such as the presence of compressive and tensile strains within identical nanoscale wrinkles. Afterward, we interpreted the trained model using explainable artificial intelligence techniques, uncovering synergistic contributions to the Raman features across each input dataset within the nanoscale region. Our analysis demonstrates that the model effectively reflects key strain-induced lattice behaviors, highlighting its nanoscale sensitivity to structural perturbations. Finally, we validated these findings using quantum mechanical calculations, which confirmed the strain-induced changes in Raman-active modes. This study offers comprehensive insights into nanoscale structural perturbations, paving the way for innovative approaches to high-resolution spectroscopic analysis in low-dimensional materials.Keywords
Funding Information
- Ministry of Science and ICT, South Korea (RS-2025-00563421)
- Ministry of Science and ICT, South Korea (RS-2023-00260527)
- Korea Technology and Information Promotion Agency for SMEs (S3207317)
- Defense Acquisition Program Administration (915111201)
- Korea Research Institute of Standards and Science (KRISS-GP2025-0005-02)
- National Research Foundation of Korea (RS-2024-00453339)
- National Supercomputing Center, Korea Institute of Science and Technology Information (KSC-2024-CRE-0075)
This publication has 46 references indexed in Scilit:
- Ultralow‐Frequency Tip‐Enhanced Raman Scattering Discovers Nanoscale Radial Breathing Mode on Strained 2D SemiconductorsAdvanced Materials, 2024
- Hyperspectral imaging of complex dielectric functions in 2D materialsNano Today, 2024
- Discovering Process Dynamics for Scalable Perovskite Solar Cell Manufacturing with Explainable AIAdvanced Materials, 2023
- Explainable Artificial Intelligence Approach to Identify the Origin of Phonon‐Assisted Emission in WSe2 MonolayerAdvanced Intelligent Systems, 2023
- Unraveling the Correlation between Raman and Photoluminescence in Monolayer MoS2 through Machine‐Learning ModelsAdvanced Materials, 2022
- Deep Learning‐Assisted Quantification of Atomic Dopants and Defects in 2D MaterialsAdvanced Science, 2021
- Raman study of D* band in graphene oxide and its correlation with reductionApplied Surface Science, 2021
- Deep‐Learning‐Enabled Fast Optical Identification and Characterization of 2D MaterialsAdvanced Materials, 2020
- The PseudoDojo: Training and grading a 85 element optimized norm-conserving pseudopotential tableComputer Physics Communications, 2018
- Atomic Defects in Two‐Dimensional Materials: From Single‐Atom Spectroscopy to Functionalities in Opto‐/Electronics, Nanomagnetism, and CatalysisAdvanced Materials, 2017