Xu Suheng, McLeod Alexander S, Chen Xinzhong, Rizzo Daniel J, Jessen Bjarke S, Yao Ziheng, Wang Zhicai, Sun Zhiyuan, Shabani Sara, Pasupathy Abhay N, Millis Andrew J, Dean Cory R, Hone James C, Liu Mengkun, Basov D N
Department of Physics, Columbia University, New York, New York 10027, United States.
Department of Physics and Astronomy, Stony Brook University, Stony Brook, New York 11794, United States.
ACS Nano. 2021 Nov 23;15(11):18182-18191. doi: 10.1021/acsnano.1c07011. Epub 2021 Oct 29.
Deep learning (DL) is an emerging analysis tool across the sciences and engineering. Encouraged by the successes of DL in revealing quantitative trends in massive imaging data, we applied this approach to nanoscale deeply subdiffractional images of propagating polaritonic waves in complex materials. Utilizing the convolutional neural network (CNN), we developed a practical protocol for the rapid regression of images that quantifies the wavelength and the quality factor of polaritonic waves. Using simulated near-field images as training data, the CNN can be made to simultaneously extract polaritonic characteristics and material parameters in a time scale that is at least 3 orders of magnitude faster than common fitting/processing procedures. The CNN-based analysis was validated by examining the experimental near-field images of charge-transfer plasmon polaritons at graphene/α-RuCl interfaces. Our work provides a general framework for extracting quantitative information from images generated with a variety of scanning probe methods.
深度学习（DL）是一种在科学和工程领域中新兴的分析工具。受深度学习在揭示海量成像数据中的定量趋势方面取得成功的鼓舞，我们将这种方法应用于复杂材料中传播的极化激元波的纳米级深亚衍射图像。利用卷积神经网络（CNN），我们开发了一种实用的协议，用于对图像进行快速回归，以量化极化激元波的波长和品质因数。使用模拟近场图像作为训练数据，可以使CNN在比普通拟合/处理程序快至少3个数量级的时间尺度上同时提取极化激元特征和材料参数。通过检查石墨烯/α-RuCl界面处电荷转移等离子体激元极化激元的实验近场图像，验证了基于CNN的分析。我们的工作提供了一个通用框架，用于从通过各种扫描探针方法生成的图像中提取定量信息。
