Universe unveiled through combined efforts of observation, simulation, and artificial intelligence

Japanese Astronomers Develop AI to Unveil Cosmic Dark Matter

The Institute of Statistical Mathematics (ISM), part of Japan's Research Organization of Information and Systems (ROIS), has made a significant breakthrough in the field of astronomy. A team of Japanese astronomers, led by Masato Shirasaki, has developed a new artificial intelligence (AI) technique to reduce noise in astronomical data caused by random variations in galaxy shapes.

The research, published in the June 2021 issue of Monthly Notices of the Royal Astronomical Society, demonstrates the benefits of combining different types of research: observations, simulations, and AI data analysis. The AI trained on mock data was able to recover previously unobservable fine details, helping to improve our understanding of the cosmic dark matter.

The mission of ROIS is to promote integrated, cutting-edge research beyond the barriers of its institutions. In addition to ISM, ROIS also includes several key data and research centers. ROIS also facilitates research activities of its member institutions, which include inter-university research institutes.

In gravitational lensing, the gravity of a foreground object can distort the image of a background object. Wide area survey data can be used to study the large-scale structure of the Universe through measurements of gravitational lensing patterns. To compensate for shape noise, the team generated 25,000 mock galaxy catalogs based on real data from the Subaru Telescope.

Using this AI on real data covering 21 square degrees of the sky, the team found a distribution of foreground mass consistent with the standard cosmological model. Averaging over many galaxies in an area is required to create a map of foreground dark matter distributions. The new tool has been applied to data from Japan's Subaru Telescope, and the mass distribution derived from it is consistent with the currently accepted models of the Universe.

Masato Shirasaki, the leader of the team, commented that this research demonstrates the benefits of combining different types of research: observations, simulations, and AI data analysis. He emphasized that this approach could lead to further breakthroughs in the field of astronomy.

ISM, with a history of more than 75 years, is an internationally renowned facility for research on statistical mathematics. It comprises three different departments: Department of Statistical Modeling, Department of Statistical Data, and Department of Statistical Inference and Mathematics. ROIS is a parent organization of four national institutes and the Joint Support-Center for Data Science Research.

The DOI for the published research is 10.1093/mnras/stab982. This groundbreaking research not only advances our understanding of cosmic dark matter but also showcases the potential of AI in astronomy.