A team of researchers linked to several Chinese institutions, one from Italy and one from Iceland, used an artificial intelligence machine learning app to count and record the location of over 100,000 craters on the moon. In his paper published in the journal Nature Communications, the group describes the programming of their crater recognition system by training it with data collected from Chinese lunar orbiters.
Previous work on identifying and mapping craters on the Moon has been a slow process – mostly done manually, with researchers studying photographs and transferring these observations to maps or lunar globes. In this new effort, researchers have found a way to dramatically speed up the process by teaching computers to identify craters and then count them.
Teaching computers to recognize craters on the moon has been a difficult process because of the many shapes that craters can take. Not all are round and are of different ages, which means that the definitions of characteristics have eroded over long periods of time. Scientists would like to map all the craters on the moon and date each one – this could provide a unique way to study the history of the solar system.
The new approach of the team working in China included training the machine learning application on crater basics. It was then trained to view the crater of a broader perspective with data from the Chinese lunar orbiters Chang’e-1 and Chang’e-2. Once the system learned what to look out for, the researchers used it to analyze data from Chang’e 5, which was part of a Chinese mission to extract rocks from the moon’s surface. The AI application used this data to identify and count craters at the lunar medium and small latitudes. The new system numbered 109,956 craters – far more than ever before on the Moon. It also tracked the location of each of the craters it found and placed each in a predefined geological time period based on how much the crater had eroded.
Study suggests much more water on the moon than previously thought (Update)
Chen Yang et al. Identification of lunar impact craters and age assessment with Chang’E data deep and transfer learning, Nature Communications (2020). DOI: 10.1038 / s41467-020-20215-y
Provides Science X
© 2020 Science X Network
Citation: Using AI to count and map craters on the Moon (2020, December 23) retrieved December 23, 2020 from https://phys.org/news/2020-12-ai-craters-moon.html
This document is protected by copyright. Except for any fair dealing for the purpose of private study or research, no part may be reproduced without written permission. The content is available for informational purposes only.