Development of the grade selection of X-ray events using machine learning for a CubeSat application

X-ray observation covering a wide field of view with a good sensitivity is essential to search for an electromagnetic counterpart of gravitational wave events. A Lobster-eye optics (LEO) and a large area CMOS sensor are good instruments to achieve this goal. Furthermore, thanks to the light weight of LEO, it is possible to install on a small platform such as a CubeSat. However, real-time identification of X-ray events is challenging to perform in the restricted resources. Therefore, we utilize one of the machine learning models of convolutional neural network (CNN) to extract X-ray events in the image taken from a CMOS sensor. Moreover, we use a Sony micro board computer, Spresense, ultra-low power consumption, and supports machine learning libraries for the process. This presentation will introduce our machine learning-based X-ray event selection process targetting to use for a CubeSat.