DATE2025.04.07 #Press Releases

New AI technique automatically and rapidly identifies rocks on asteroids

ーCan be used in mining, civil engineering, construction, and disaster preventionー

Summary

A research group led by Project Researcher Yuta Shimizu and Professor Hideaki Miyamoto at the School of Engineering, The University of Tokyo, (also affiliated with the Department of Earth and Planetary Science) has successfully developed an innovative and efficient AI-based automatic rock identification algorithm (Figure).

They collected tens of thousands of rock profile data from both terrestrial and extraterrestrial rocks, and used this data set to develop a new AI-based rock identification algorithm. This algorithm enabled them to perform the first comprehensive survey of all meter-sized rocks on the surfaces of the asteroids Ryugu and Bennu. Approximately 3.5 million particles are identified; after removing duplicates across images, the final mapping yields about 200,000 rocks, revealing their shapes and spatial distributions.

The results reveal that the surface gravel on the two asteroids has moved in opposite directions—toward the equator on Bennu and toward the poles on Ryugu. They find that this surface material movement can be determined by only a slight difference in their rotational rates—just a few hours.

The technology in this work has broad potential not only for planetary science, but also for industrial applications, from continuous slope monitoring for disaster mitigation to real-time material management in mining and construction, as well as rapid urban infrastructure inspection and agricultural soil analysis.

Figure:  AI-Based automatic and efficient rock analysis and its applications

Related Link

School of Engineering, The University of Tokyo

Published Journals

Journal name	Scientific Reports
Title of paper	Diverse evolutionary pathways of spheroidal asteroids driven by rotation rate