We already know that the Moon has a very uneven surface. But a new crater-spotting tool powered by artificial intelligence has found that the moon’s surface is even rougher than we thought.
In a study published in the journal Nature Communications this week, international a team of researchers from China, Italy and Iceland identified and mapped the location over 109,000 new craters in lunar regions of low and medium latitudes using a machine learning algorithm trained with data collected from Chinese lunar orbiters.
The number is surprisingly higher than what scientists previously counted manually. Counting and mapping craters on the moon has always been a slow and arduous process. It conventionally involves researchers studying photos of telescopes and transferring their observations to maps or lunar globes. Because lunar craters can vary dramatically in size, shape, and age, the process can also be subjective, leading to discrepancies between existing databases.
See also: NASA announces that water has been found on the moon
All these problems are now being solved by artificial intelligence. In a new study, researchers led by Chen Yang, a professor of Earth science at Jilin University in China, trained a deep neural network with data from thousands of previously identified lunar craters. Once the system learned the basics of the crater, it was supplied with data collected by Chinese lunar orbiters Chang’e-1 and Chang’e-2 to search for new ones.
“It’s the largest database of lunar craters with automatic extraction for mid- and low-latitude moons,” Yang told Live Science this week.
Impact craters on the Moon form during a meteor impact early in the Earth’s and Moon’s formation. They are the lunar equivalent of a “fossil,” said Yang, who “records the history of the solar system.”
Most of the newly discovered craters have a diameter of 1 to 100 kilometers. Astronomers have previously counted about 5,000 craters more than 12 miles in diameter.
Yang’s team plans to further improve the algorithm by providing it with data from the Chang’e 5 spacecraft, which recently carried lunar samples back to Earth. The program could also be used to study other objects in the solar system, such as planets and large moons.