Researchers at an Australian university have hit upon an innovative method to locate and retrieve meteorites that crash to Earth.

A team from Curtin’s Space Science and Technology Centre (SSTC) has succeeded in recovering a meteorite that fell onto the Nullarbor Plain in Western Australia using AI to scan drone footage and pinpoint its location. (PHYS.ORG)

Late last year, the new method was successfully used to find a fresh meteorite at Kybo Station.

“A camera-fitted drone flies over and collects images of the fall zone, which are transferred to our field computer where an algorithm scans each image for meteorites and features that resemble them,” said lead researcher and graduate student Seamus Anderson.

AI and meteorites

The innovative approach is a huge improvement over the traditional method in which a group of people search across the estimated impact location of the meteorite.

Compared to this manual method, the combined use of drones for imagery and AI for analysis needed only a tenth of the labor and time and had a much higher success rate.

According to Anderson, the team located and recovered the meteorite within four days of being on site at Kybo Station.

The Desert Fireball Network tracks meteorites and these are especially useful for scientists because they provide a geological insight into the region of the solar system from where they originated.

“By gaining a better understanding of how extraterrestrial material is distributed throughout the solar system, we may one day mine asteroids for precious resources, instead of scrounging for the finite amounts of them on Earth and perhaps harming precious ecosystems in the process,” said Anderson.

Related Story: AI Crunches Simulations Of The Cosmos Into Minutes