Recovery of meteorites using an autonomous drone and machine learning. (9th June 2021)

• Record Type: Journal Article
• Authors: Citron, Robert I.; Jenniskens, Peter; Watkins, Christopher; Sinha, Sravanthi; Shah, Amar; Raissi, Chedy; Devillepoix, Hadrien; Albers, Jim
• Other Names: Zolensky Michael handlingEditor.
• Is Part Of: Meteoritics & planetary science. Volume 56:Number 6(2021)
• Page Start: 1073
• Page End: 1085
• Publication Date: 2021-06-09
• Subjects: Meteorites -- Periodicals; Planetology -- Periodicals; 523.4
• DOI: 10.1111/maps.13663
• Languages: English
• ISSNs: 1086-9379

Abstract

Abstract: The recovery of freshly fallen meteorites from tracked and triangulated meteors is critical to determining their source asteroid families. Even though our ability to locate meteorite falls continues to improve, the recovery of meteorites remains a challenge due to large search areas with terrain and vegetation obscuration. To improve the efficiency of meteorite recovery, we have tested the hypothesis that meteorites can be located using machine learning techniques and an autonomous drone. To locate meteorites autonomously, a quadcopter drone first conducts a grid survey acquiring top‐down images of the strewn field from a low altitude. The drone‐acquired images are then analyzed using a machine learning classifier to identify meteorite candidates for follow‐up examination. Here, we describe a proof‐of‐concept meteorite classifier that deploys off‐line a combination of different convolution neural networks to recognize meteorites from images taken by drones in the field. The system was implemented in a conceptual drone setup and tested in the suspected strewn field of a recent meteorite fall near Walker Lake, Nevada.