Machine learning super-resolution of laboratory CT images in all-solid-state batteries using synchrotron radiation CT as training data

Abstract

High-performance all-solid-state lithium-ion batteries require observation, control, and optimization of the electrode structure. X-ray computational tomography (CT) is an effective nondestructive method for observing the electrode structure in three dimensions. However, the limited availability of synchrotron radiation CT, which offers high-resolution imaging with a high signal-to-noise ratio, makes it difficult to conduct experiments and restricts the use of X-ray CT in battery development. Conversely, laboratory CT systems are widely available, but they use X-rays emitted from a metal target, resulting in lower image quality and resolution compared with synchrotron radiation CT. This study explores a method for achieving comparable resolution in laboratory CT images of all-solid-state batteries to that of synchrotron radiation CT. Our method involves using the synchrotron radiation CT images as training data for machine learning super-resolution. The results demonstrate that, by employing an appropriate machine learning algorithm and activation function, along with a sufficiently deep network, the image quality of laboratory CT becomes equivalent to that of synchrotron radiation CT.