Deep learning-based noise filtering toward millisecond order imaging by using scanning transmission electron microscopy

This article highlights the latest result from an on-going research project by Ihara, Saito, Yoshinaga (graduate student), Avala (PD) and Murayama.

Since the STEM has more than twice the tolerance of specimen thickness compared to the CTEM, in-situ observation by using the STEM can capture dynamic evolution of phenomena with less effects of surface. The STEM also enables us to obtain the chemical components and bonding state, etc., at the same time when we observe a texture of a sample, providing a large amount of data even in one experiment. Such a big data-like data acquisition could be a standard tool in the current data-driven materials science. Because of these reasons, the STEM would be a better tool compared to the CTEM for operand observation utilizing data science. Therefore, the denoising technique developed in this study could be an essential approach for electron microscope observation which is difficult to establish in the conventional way, such as observing a dynamic evolution of dislocation structures in a thick sample under external stimuli.