Image for production purpose
An international team of researchers has identified more than 109,000 previously unknown impact filters on the moon using machine learning methods. The study, led by researchers from Jilin University, was published in the journal Nature Communications. Impact craters are the most prominent lunar surface feature and occupy most of the lunar surface.
With traditional automated identification methods, it is usually difficult to detect irregular and highly damaging impact filters that can be created in the early stages. To effectively identify filters and estimate age, researchers applied a motion learning method and trained a deep neural network with previously named filter data, reports Xinhua news agency.
Combining the data collected by Chang’e-1 and Chang’e-2 lunar testers in China, researchers identified 109,956 new effect filters. They also estimated the age of 18,996 recently discovered filters larger than 8 km in diameter. At the same time, researchers have set up a new database of lunar influences for the central and latitude regions of the moon. Yang Chen of Jilin University, who is one of the researchers, said that a lunar crater database is very valuable for scientific study of the moon.
“The adopted strategy can be applied to help with crater studies, generating reliable recommendations for planetary exploration,” Yang said. This research model was applied to identify small impact filters at the landing site of the Chang’e-5 probe, Yang added.