Astronomy has seen a big boon because of artificial intelligence. It is because space is big and takes a long time to look at. The recent news from astronomers come this month as they used artificial intelligence to find 6000 new craters on the surface of the Moon.
Well this is not significant news on its own. Moon is projected to have many craters on the surface because of asteroids and meteors impact. The Moon has no atmosphere so these space rocks have a free path down to the surface. The lack of weather on the Moon makes these marks permanent and the do not eroded (like we know occurs in earth).
But using AI to find these craters is important, as it demonstrates another way machine learning can automate a labor-intensive task. The less time spent flicking through pictures of the Moon, labeling craters by hand, the more they have to focus on other, more challenging research. Plus, the more we know about the Moon’s craters, the better we can theorize about the history and formation of our Solar System.
The tool used for this particular research is what’s known as a convolutional neural network, or CNN.
This is a common technique that’s particularly good at sorting through visual data. As the researchers who conducted the work explain in an unpublished paper, they trained their network using a data set of craters previously identified by humans. Once the program had learned what craters looked like, it was turned loose on a new section of the Moon’s surface (roughly one-third of its total surface area). There, it found 6,000 new craters.
As the scientists who conducted the work, from the universities of Toronto, Penn State, and Arizona State, write in their paper, the system was consistent and, most importantly, fast. “Once trained, our CNN greatly increases the speed of crater identification, taking minutes to generate predictions for tens of thousands of Lunar DEMs,” they write.
Image via Britainnica