The researchers, 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 lunar orbits – Chang’e 1 and Chang’e 2 – the network 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 moon’s surface. This is in stark contrast to the Earth’s surface. It is very difficult to trace the Earth’s history of being affected by asteroids and comets over the last 4 billion years,” Chen Yang, from the College of Earth Sciences at Jilin University and the Key Laboratory of Lunar and Deep Space Exploration at the Chinese Academy of Sciences.
“Earth and the moon have been affected by the same impact population over time, but large lunar craters have experienced limited degradation over billions of years. Therefore, lunar craters can track the evolution of the Earth,” she said via email.
The craters on the moon lack water, an atmosphere and tectonic plate activity – three forces that erode the earth’s surface, meaning that all but the latest meteor impacts are not visible.
This latest study is not the first to implement machine learning to detect lunar craters, said Mohamad Ali-Dib of the Institute for Research on Exoplanets at the University of Montreal.
“Machine learning can be used to detect craters on the moon,” he said via email. Craters are “a window into the dynamic history of the solar system.