It is easy to find large meteorites (or their craters) once they hit Earth, but the smaller ones are often neglected – scientists recover less than 2 percent of them. Soon, however, it might just be a matter of sending a robot to do the job. Universe Today reports that researchers have developed a system in which autonomous drones use machine learning to find the smaller meteorites at impact points that are either “hidden” (even if observers were following the fall) or simply inaccessible.
The technology uses a mix of convolutional neural networks to detect meteorites based on training images, both from online imagery and staged footage from the team’s collection. This helps the AI distinguish between space rocks and common stones, even in a variety of shapes and terrain conditions.
The results are not perfect. While a test drone correctly identified meteorites planted, there were also some false positives. It could be a while before robotic aircraft are trustworthy enough to provide accurate results on their own.
However, the implications for space exploration are significant if the technology proves correct. It would help scientists identify and potentially recover meteorites that are either too small to find or too far away. This in turn could help locate meteorite sources and identify the composition of the rocks. Put simply, drones could fill gaps in human understanding of the cosmic debris landing on our doorsteps.
All products recommended by Engadget are selected by our editorial team independently of our parent company. Some of our stories contain affiliate links. If you buy something through one of these links, we may earn an affiliate commission.