Artificial intelligence has helped scientists to discover as many as 6,000 new craters on the surface of our moon.
The new AI-powered technique was developed by U of T Scarborough scientists. Researchers involved with the new technique explain that previously many studies have looked at developing algorithms capable of identifying and counting lunar craters; however, none of them actually yielded the desired results. The new technique, scientists claim, can generalize very well to unseen lunar patches, and even other cratered bodies like Mercury thereby leading to discovery of many new craters.
To ensure that the new technique performs well when actually put to test, researchers first trained their neural network on a large data set covering two thirds of the moon. After that they tested their trained network on the remaining third of the moon and this led to discovery of twice as many craters as traditional manual counting. In fact, it was able to identify about 6,000 previously unidentified craters on the moon.
The technique is based on convolutional neural network, which is a class of machine learning algorithms that has been successfully used for computer vision to power robots and even self-driving cars. The data used by the algorithms was taken from elevation maps gathered from orbiting satellites.
One of the reasons why identifying craters on bodies like the moon is important is that it provides us details about the history of our solar system. By studying impact craters of all shapes, sizes and ages, researchers can better understand the distribution of material and the physics that occurred in the early stages of our solar system.
Since the moon lacks an atmosphere, plate tectonics and water, there is little erosion and as a result some impact craters as old as 4 billion years are visible. The ages of large craters can also be determined by counting how many small craters are found inside it.