Classifying meteorites with MetNet : A deep learning approach using reflectance spectroscopy

Abstract

Abstract–Meteorites, remnants of asteroids that successfully survive their passage through theEarth’s atmosphere, hold critical information about the evolution and history of the solarsystem. Traditional methods of analyzing these rare and precious specimens often involvedestructive geochemical techniques, which deplete the sample and limit subsequent analyses.The accurate classification of meteorites, typically determined through petrological examination,is crucial before any further analytical steps. Reflectance spectroscopy, which interprets asample’s characteristics by analyzing reflected light, has emerged as a nondestructive alternativewith significant potential for meteorite classification. In this technique, apparently, sometimeswe do not need to process the sample. This technique allows for the examination of spectralfeatures such as absorption bands, symmetry, band centers, inflection points, and overall slope.In this study, we employed spectral reflectance data from 1781 meteorite samples to develop andfine-tune a deep learning model capable of accurate classification. The model was trained on75% of the dataset and validated on the remaining 25%, achieving a validation accuracy of93%. These results demonstrate the efficiency of using deep learning and reflectancespectroscopy for meteorite classification, offering a nondestructive and accurate alternative totraditional methods.