Curtin researchers have recovered a freshly dropped meteorite after locating its exact location on the vast Nalbore plain in western Australia, with new technology using drones to collect scanned landscape footage using artificial intelligence.
Lead researcher Seamus Anderson, a graduate student from the Curtin Space Science and Technology Center (SSTC), said the successful discovery of the new method at the Kibo station late last year had the potential to greatly increase the number of recovered meteorites. They are observed when falling through the atmosphere.
“The camera-mounted drone flies and collects images of the fall zone, which is then transferred to our field computer, where the algorithm scans each image for meteorites and similar features,” Mr. Anderson said.
“Although our algorithm is ‘trained’ on data collected from past meteorite searches, to bring local data to further train the algorithm, we brought with us previously recovered meteorites and painted them on the ground at the fall site.
“Meteor searches usually involve a group of people walking over a large estimated impact area, but our new method requires only a tenth of the effort and time and has a much higher success rate. . “
Such meteors tracked by the Desert Fireball Network (DFN) are unique. Anderson says that because they provide a geographical model that emerges from a specific area of the solar system, which contributes to the overall understanding of geography. Solar system.
“New solutions like our drone technique will help invest in space science and make meteor studies more cost-effective and effective,” he said. Anderson said.
“In addition to raising our awareness of the solar system, the study of meteorites can be useful for a number of reasons. For example, meteorites often contain high concentrations of rare and valuable elements such as cobalt, which are crucial for the construction of modern batteries.
“Also, by gaining a better understanding of how alien matter is distributed throughout the solar system, we can one day dig asteroids for valuable resources, instead of searching for finite amounts on Earth and harming valuable ecosystems in the process.
“Other potential applications for our new approach using drones and artificial intelligence include wildlife management and conservation, because our model can be easily re-trained to detect objects other than meteorites such as plants and animals.”
An asteroid recently crashed in Australia and the drone explored the area and found it
Successful recovery of the observed asteroid crash using drones and machine learning (2022), by Seamus L. Anderson et al. arXiv: 2203.01466 [astro-ph.EP] arxiv.org/abs/2203.01466
Presented by Curtin University
Citation: Hunting for fallen asteroids in Western Australia for drones and artificial intelligence assistance (2022, March 14) Retrieved from 14 March 2022 at https://phys.org/news/2022-03-drones-artificial-intelligence-aid-fallen.html
This document is subject to copyright. No part may be reproduced without written permission, except for any fair deal for the purpose of private study or research. Content is provided for informational purposes only.