Ultrafast Atomic Force Microscopy Imaging of Phase Transition Phenomena on Ice Surface by Machine Learning

2022 Fiscal Year Final Research Report

• Project/Area Number: 21K18876
• Research Category: Grant-in-Aid for Challenging Research (Exploratory)
• Allocation Type: Multi-year Fund
• Review Section: Medium-sized Section 28:Nano/micro science and related fields
• Research Institution: Osaka University
• Principal Investigator: Abe Masayuki 大阪大学, 大学院基礎工学研究科, 教授 (00362666)
• Project Period (FY): 2021-07-09 – 2023-03-31
• Keywords: 氷表面 / 非接触原子間力顕微鏡 / 圧縮センシング / 機械学習

Outline of Final Research Achievements

In this study, we solved the following problems in scanning probe microscopy (SPM) on ice surfaces: (1) correction of thermal drift when temperature changes, (2) speed-up of the measurement, and (3) automatic adjustment of the SPM tip, by using software technology including machine learning. For (1), we established a thermal drift correction method using the feature point extraction method, which enabled observation at the same field of view for up to three days. For (2), we have demonstrated that the measurement time can be reduced to one-eighth without hardware modification by speeding up the measurement through data completion using compressed sensing. For (3), we developed a fully automatic probe adjustment technique using machine learning.

Free Research Field

走査型プローブ顕微鏡

Academic Significance and Societal Importance of the Research Achievements

本研究で解決した上記の走査型プローブ顕微鏡における課題は、研究者が望んでいる実験データを得るために問題となっていた。本研究によって氷表面だけでなく、様々な分野への測定に利用することで、これまで行えなかった実験研究を可能にしたことに学術的意義がある。さらに、実験研究に積極的にソフトウェアの技術を導入することで、走査型プローブ顕微鏡以外への横展開も可能になってきたといえる。