Rapid morphology characterization of two-dimensional TMDs and lateral heterostructures based on deep learning

2025-03-01

AI Summary

To address the low efficiency and manual dependency in morphological characterization of two-dimensional transition metal dichalcogenides (TMDs) and their lateral heterostructures, this work proposes a deep learning–based real-time optical image analysis method. We adapt the YOLO object detection framework for automated identification and classification of monolayer MoS₂, MoSe₂, and their lateral heterojunctions—marking the first such application in this domain. A cross-material transfer learning strategy is introduced to significantly enhance model generalizability across diverse TMD systems. Furthermore, model lightweighting enables millisecond-level inference latency. The method achieves >94.67% classification accuracy on optical micrographs, exhibits strong robustness against imaging artifacts and noise, and substantially reduces both characterization time and cost. Finally, the pipeline is fully integrated into a standalone desktop application for practical deployment.

Technology Category

• Machine Learning: Multimodal Learning
• Computer Vision: Object Detection & Categorization
• Search and Optimization: Learning to Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Two-dimensional (2D) materials and heterostructures exhibit unique physical properties, necessitating efficient and accurate characterization methods. Leveraging advancements in artificial intelligence, we introduce a deep learning-based method for efficiently characterizing heterostructures and 2D materials, specifically MoS2-MoSe2 lateral heterostructures and MoS2 flakes with varying shapes and thicknesses. By utilizing YOLO models, we achieve an accuracy rate of over 94.67% in identifying these materials. Additionally, we explore the application of transfer learning across different materials, which further enhances model performance. This model exhibits robust generalization and anti-interference ability, ensuring reliable results in diverse scenarios. To facilitate practical use, we have developed an application that enables real-time analysis directly from optical microscope images, making the process significantly faster and more cost-effective than traditional methods. This deep learning-driven approach represents a promising tool for the rapid and accurate characterization of 2D materials, opening new avenues for research and development in material science.

Problem

• Develops deep learning for 2D material characterization.
• Enhances accuracy in identifying MoS2-MoSe2 heterostructures.
• Enables real-time analysis from optical microscope images.

Innovation

• Deep learning for 2D material characterization
• YOLO models achieve over 94.67% accuracy
• Real-time analysis via optical microscope images