Autonomous drones learn to find ‘hidden’ meteor impact sites

Easy to find large size العثور meteorites (or their craters) once they reach Earth, but smaller ones are often neglected—less than 2 percent of them have been recovered by scientists. However, it may soon be just sending a bot to do the job. universe today Reports possessed by researchers advanced The system with autonomous drones uses machine learning to find smaller meteorites at impact sites that are either «hidden» (even if observers track the falls) or simply inaccessible.

The technology uses a combination of convolutional neural networks to identify meteorites based on training images, both from online images and from staging snapshots from the team’s collection. This helps the AI ​​distinguish space rocks from ordinary stones, even with a variety of shapes and terrain conditions.

The results are impeccable. While an experimental drone correctly spotted the implanted meteorites, there were also some false positives. It may take some time before robotic planes are reliable enough to provide accurate results on their own.

The implications for space science are important if the technology proves accurate. It will help scientists discover meteorites that are either too small or too far away to find and possibly recover. This, in turn, can help identify meteorite sources and identify rock formations. Simply put, drones can fill in the gaps in humanity’s understanding of the cosmic debris landing on our doorstep.

All products recommended by Engadget are handpicked by our editorial team, independently of the parent company. Some of our stories include affiliate links. If you buy something through one of these links, we may earn an affiliate commission.

READ  Shocking fossil reveals millipedes the size of a car that slid on Earth 326 million years ago

Olga Dmitrieva

Любитель алкоголя. Возмутитель спокойствия. Интроверт. Студент. Любитель социальных сетей. Веб-ниндзя. Поклонник Бэкона. Читатель

Добавить комментарий

Ваш адрес email не будет опубликован.