AI Science Tracker
EN

Identification and Structural Characterization of Twisted Atomically Thin Bilayer Materials by Deep Learning

Key Laboratory of Wide Band-Gap Semiconductor Technology & Shaanxi Key Laboratory of High-Orbits-Electron Materials and Protection Technology for Aerospace, School of Advanced Materials and Nanotechnology, Xidian University, Xi'an 710071, China; Department of Materials Science and Engineering, University of Delaware, Newark, Delaware 19716, United States; State Key Laboratory of Superlattices and Microstructures, Institute of Semiconductors, Chinese Academy of Sciences, Beijing 100083, China; Phonon Engineering Research Center of Jiangsu Province, School of Physics and Technology, Nanjing Normal University, Nanjing 210023, China; School of Materials Science and Engineering, Northwestern Polytechnical University, Xi'an 710072, China; Instituto de Ciencia de Materiales de Madrid (ICMM-CSIC), 28049 Madrid, Spain · 26 Feb 2024 · materials

Discovery

Identification and Structural Characterization of Twisted Atomically Thin Bilayer Materials by Deep Learning

Source check: Source checked. Not independent scientific confirmation.

Finding: The model provided twist-angle estimates for CVD-grown bilayer MoS2 samples, including irregular flakes, with sample measurements checked against second-harmonic-generation spectroscopy; Raman spectra also varied with measured twist angle. Predicted angles for actual grown samples were compared with SHG measurements, and Raman spectra were examined across angles. Validation is limited to the reported sample set and does not demonstrate new phases or downstream device performance.

Technology: A supervised CNN segments optical micrographs to classify layer thickness; a ResNet trained on synthetic triangular-flake images predicts twist angles from images of CVD-grown bilayers.

Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.

AI contribution
A supervised CNN segments optical micrographs to classify layer thickness; a ResNet trained on synthetic triangular-flake images predicts twist angles from images of CVD-grown bilayers.
Test and result
The model provided twist-angle estimates for CVD-grown bilayer MoS2 samples, including irregular flakes, with sample measurements checked against second-harmonic-generation spectroscopy; Raman spectra also varied with measured twist angle.
Limitation / still unknown
Predicted angles for actual grown samples were compared with SHG measurements, and Raman spectra were examined across angles. Validation is limited to the reported sample set and does not demonstrate new phases or downstream device performance.
Evidence sources and annotation context

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

Evidence sources: https://pubs.acs.org/doi/10.1021/acs.nanolett.3c04815 · https://raman.semi.cas.cn/fblw_23326/yjcg_yfblz/202311/W020240309811195947244.pdf

Source checked · editorial details

The source page was checked against this entry. Independent confirmation is not assessed by this label.

Source type: paper. Paper: linked separately.

Review date: 22 Nov 2026. Review scope: Primary source full text Methods and Results; version/date checked against bibliographic record..

No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.

Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Open in the full catalog for filters, charts and related discoveries. Browse materials discoveries.