Machine learning-aided atomic structure identification of interfacial ionic hydrates from AFM images

Binze Tang; Yizhi Song; Mian Qin; Ye Tian; Zhen Wei Wu; Ying Jiang; Duanyun Cao; Limei Xu

doi:10.1093/nsr/nwac282

Machine learning-aided atomic structure identification of interfacial ionic hydrates from AFM images

Natl Sci Rev. 2022 Dec 14;10(7):nwac282. doi: 10.1093/nsr/nwac282. eCollection 2023 Jul.

Authors

Binze Tang^{1

2}, Yizhi Song^{1

2}, Mian Qin², Ye Tian^{1

2}, Zhen Wei Wu³, Ying Jiang^{1

2

4

5

6}, Duanyun Cao^{7

8}, Limei Xu^{1

2

4

6}

Affiliations

¹ International Center for Quantum Materials, Peking University, Beijing100871, China.
² School of Physics, Peking University, Beijing100871, China.
³ Institute of Nonequilibrium Systems, School of Systems Science, Beijing Normal University, Beijing 100875, China.
⁴ Collaborative Innovation Center of Quantum Matter, Beijing100871, China.
⁵ CAS Center for Excellence in Topological Quantum Computation, University of Chinese Academy of Sciences, Beijing 100049, China.
⁶ Interdisciplinary Institute of Light-Element Quantum Materials and Research Center for Light-Element Advanced Materials, Peking University, Beijing100871, China.
⁷ Beijing Key Laboratory of Environmental Science and Engineering, School of Materials Science and Engineering, Beijing Institute of Technology, Beijing100081, China.
⁸ Beijing Institute of Technology Chongqing Innovation Center, Chongqing401120, China.

Abstract

Relevant to broad applied fields and natural processes, interfacial ionic hydrates have been widely studied by using ultrahigh-resolution atomic force microscopy (AFM). However, the complex relationship between the AFM signal and the investigated system makes it difficult to determine the atomic structure of such a complex system from AFM images alone. Using machine learning, we achieved precise identification of the atomic structures of interfacial water/ionic hydrates based on AFM images, including the position of each atom and the orientations of water molecules. Furthermore, it was found that structure prediction of ionic hydrates can be achieved cost-effectively by transfer learning using neural network trained with easily available interfacial water data. Thus, this work provides an efficient and economical methodology that not only opens up avenues to determine atomic structures of more complex systems from AFM images, but may also help to interpret other scientific studies involving sophisticated experimental results.

Keywords: atomic force microscopy; atomic scale structure identification; interfacial ion hydrates; machine learning; transfer learning.