We present a novel methodology for recovering meteorite falls observed and constrained by fireball networks, using drones and machine learning algorithms. This approach uses images of the local terrain for a given fall site to train an artificial neural network, designed to detect meteorite candidates. We have field tested our methodology to show a meteorite detection rate between 75-97%, while also providing an efficient mechanism to eliminate false-positives. Our tests at a number of locations within Western Australia also showcase the ability for this training scheme to generalize a model to learn localized terrain features. Our model-training approach was also able to correctly identify 3 meteorites in their native fall sites, that were found using traditional searching techniques. Our methodology will be used to recover meteorite falls in a wide range of locations within globe-spanning fireball networks.
@article{arxiv.2009.13852,
title = {Machine Learning for Semi-Automated Meteorite Recovery},
author = {Seamus Anderson and Martin Towner and Phil Bland and Christopher Haikings and William Volante and Eleanor Sansom and Hadrien Devillepoix and Patrick Shober and Benjamin Hartig and Martin Cupak and Trent Jansen-Sturgeon and Robert Howie and Gretchen Benedix and Geoff Deacon},
journal= {arXiv preprint arXiv:2009.13852},
year = {2021}
}