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

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

机构地区：[1]International Center for Quantum Materials,Peking University,Beijing 100871,China [2]School of Physics,Peking University,Beijing 100871,China [3]Institute of Nonequilibrium Systems,School of Systems Science,Beijing Normal University,Beijing 100875,China [4]Collaborative Innovation Center of Quantum Matter,Beijing 100871,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,Beijing 100871,China [7]Beijing Key Laboratory of Environmental Science and Engineering,School of Materials Science and Engineering,Beijing Institute of Technology,Beijing 100081,China [8]Beijing Institute of Technology Chongqing Innovation Center,Chongqing 401120,China

出　　处：《National Science Review》2023年第7期109-118,共10页国家科学评论（英文版）

基　　金：supported by the National Key R&D Program of China(2021YFA1400501);the National Natural Science Foundation of China(11935002 and 12204039);the National Postdoctoral Program for Innovative Talents(BX2021040);the China Postdoctoral Science Foundation(2021M690408);Beijing Institute of Technology Research Fund Program for Young Scholars(XSQD-202210007)。

摘　　要：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 mole cules.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.

关 键 词：machine learning transfer learning atomic force microscopy atomic scale structure identification interfacial ion hydrates 

分 类 号：O562[理学—原子与分子物理] TP181[理学—物理]