The scientists, using data on 7,895 previously identified craters and 1,411 dated craters, were able to apply machine learning to train a deep neural network. With information from China’s first and second monthly orbits – Chang’e 1 and Chang’e 2 – the network has identified 109,956 new craters. The two unmanned spacecraft were launched in 2007 and 2010, respectively.
“Impact craters (are) the most diagnostic features of the lunar surface. This is in stark contrast to the Earth’s surface. It is very difficult to trace the history of Earth, which has been affected by asteroids and comets in the last 4 billion years, “said the author of the study Chen Yang, from Jilin University College of Earth Sciences and the key lunar and deep space exploration laboratory at the Chinese Academy of Sciences.
“Earth and the moon have been hit by the same impact population over time, but large lunar craters have experienced limited degradation over billions of years. Therefore, lunar impact craters can track the evolution of the Earth,” he said. she said by e-mail.
Craters on the Moon lack water, atmosphere, and tectonic plate activity – three forces that erode the Earth’s surface, meaning that all but the most recent meteorological effects are not visible.
The latest study is not the first to conduct machine learning to detect lunar craters, said Mohamad Ali-Dib of the University of Montreal’s Exoplanet Research Institute.
“Machine learning can be used to detect craters on the moon,” he said in an email. Craters are “a window to the dynamic history of the solar system.