Zero-Shot Autonomous Microscopy for Scalable and Intelligent Characterization of 2D Materials

作者：H. J. Yang, Ruoyan Avery Yin, Chi Jiang, Yuepeng Hu, Xiaokai Zhu, Xingjian Hu, S. Ananda Kumar, Samantha K. Holmes, Xinghuan Wang, Xiaohua Zhai, Keran Rong, Yunyue Zhu, Tianyi Zhang, Zongyou Yin, Yuan Cao, Haoning Tang, Aaron D. Franklin, Jing Kong, Neil Zhenqiang Gong, Zhichu Ren, Haozhe Wang · 发表于：ACS Nano · 年份：2025 · DOI：10.1021/acsnano.5c09057 · 被引用次数：5 · 研究领域：Machine Learning in Materials Science、Advanced Electron Microscopy Techniques and Applications、Electronic and Structural Properties of Oxides

Characterization of atomic-scale materials traditionally requires human experts with months to years of specialized training. Even for trained human operators, accurate and reliable characterization remains challenging when examining newly discovered materials such as two-dimensional (2D) structures. This bottleneck drives demand for fully autonomous experimentation systems capable of comprehending research objectives without requiring large training data sets. In this work, we present ATOMIC (Autonomous Technology for Optical Microscopy & Intelligent Characterization), an end-to-end framework that integrates foundation models to enable fully autonomous, zero-shot characterization of 2D materials. Our system integrates the vision foundation model (i.e., Segment Anything Model), large language models (i.e., ChatGPT), unsupervised clustering, and topological analysis to automate microscope control, sample scanning, image segmentation, and intelligent analysis through prompt engineering, eliminating the need for additional training. When analyzing typical MoS 2 samples, our approach achieves 99.7% segmentation accuracy for single layer identification, which is equivalent to that of human experts. In addition, the integrated model is able to detect grain boundary slits that are challenging to identify with human eyes. Furthermore, the system retains robust accuracy despite variable conditions, including defocus, color-temperature fluctuations, and exposure variations. It is appli...