More than 100,000 new craters have been identified on the Moon thanks to an artificial intelligence system based on machine learning, developed by a group of researchers led by Yang Chen of the Chinese University of Jilin (a former member for several years of the Department of Information Engineering and Computer Science -DISI, first as a doctoral student and then as a post-doctoral researcher) with the contribution of Lorenzo Bruzzone, professor at DISI.
The research work was published in the prestigious Nature Communication
journal in an article
entitled "Lunar impact crater identification and age estimation with Chang'E data by deep and transfer learning"
. This is the largest database of lunar craters in the world
, a dozen times larger than what has been reported in previous databases so far.
The sensational achievement is the result of a machine learning algorithm based on a particular convolutional neural network architecture (CNN or ConvNet). The algorithm used the entire database of images acquired by the two Chinese lunar missions Chang'e-1 and Chang'e-2 and, based on approximately 10,000 known craters defined by the International Astronomical Union (IAU) in previous decades, was able to automatically learn which are the most effective features to model craters and to search for them on the entire lunar surface. In this way, scientists were able to identify 117,240 new craters ranging in diameter from about 1 km up to 532 km, mainly distributed in the mid- and low-latitude regions of the Moon.
Thanks to the machine learning system, the researchers were able not only to detect irregular or degraded craters, but also small craters difficult to identify with conventional systems (88.14% of the detected craters have a diameter of less than 10 km ).
Furthermore, based on morphological and stratigraphic information, the scientists developed a second neural network architecture capable of automatically establishing the geological age of nearly 19,000 new craters located in the mid- and low-latitude regions of the Moon, thus creating a database 13 times larger than any existing one.
The scientific achievement is extremely important as Lunar craters, generated by impacts with asteroids and comets, can be considered as fossils that describe both the evolution of the Moon and of the Earth that were impacted by the same population over time. However, on our planet tectonic plate activity and erosion have deleted many of these traces.
"The automatic learning methodology we have adopted" - explains prof. Bruzzone - is based on Transfer Learning (TL). It is aimed at exploiting what has been learned on the low-resolution images of the Chang'e-1 mission for the analysis of the high-resolution images of the Chang'e-2 mission. Basically, this machine learning system is similar to a supervisor passing on its knowledge and experience from one generation to the next, applying what it has learned previously to solve new problems. This approach allows an automatic, accurate and consistent analysis of craters distribution over an entire celestial body".
In the future, the methodology developed by the researchers could therefore be adapted to other Solar System bodies, for example: Mars, Mercury, Venus, Vesta and Ceres; this will make it possible to automatically and reliably extract information on a global scale that are difficult to derive by conventional manual analyses or automatic techniques of previous generation.
The article was downloaded in a week by more than 3,150 researchers and gained media exposure that made it rank in the top 2% of those published in Nature Communication.
Nature Communication is a peer-reviewed, open-access, multidisciplinary scientific journal, published by Nature Research since 2010.
Convolutional Neural Network (CNN or ConvNet) represents a highly successful artificial neural network architecture in computer vision applications, also widely used in applications that process data such as audio and video. The most popular application of convolutional neural network is to identify by a computer (and with a certain probability) what an image represents. Through the use of filters, particular features of the images are extracted, and depending on the type of filter used it is possible to identify different things on the reference image, for example the contours of the figures, the vertical lines, the horizontal lines, the diagonals, etc.
Transfer learning (TL) is a Machine Learning technique in which a model, already trained on a specific data set and developed for a specific task, is reused as a starting point to solve a problem other than the one for which it was developed initially.